Search • Rankings • TrustOps • Docs • Pricing • Claim/Manage

awesome-openaccountants/openaccountants

openaccountants/openaccountants

openaccountants/openaccountants openaccountants/openaccountants](https://glama.ai/mcp/servers/openaccountants/openaccountants) 📇 ☁️ - Open-source AI accounting skills, checked by licensed accountants jurisdiction by jurisdiction. 3 tools: list skills by country/category, get full skill content, and get individual sections. Skills teach AI agents tax computations (income tax, VAT, payroll) across 134 countries plus US states and Canadian provinces. Hosted at `https://www.openaccountants.com/api/mcp`.

JSON report • Policy • Badge metadata • History API • • Global feed

DECISION SUMMARY

Block For Production

Score

72.4

Rank suppressed while production readiness shows a blocking verdict.

Confidence

High

Based on evidence completeness, recency, and validation density.

Evidence age

3.1h old

Freshness: fresh. Snapshot trustsnap_52212483c3924fc6.

Top risk drivers

Utility Coverage
Transport Compliance
Resource Contract

Recommended actions

Align MCP-Protocol-Version, MCP-Session-Id, DELETE teardown, and expired-session handling with the transport spec.
Only send roots/list, sampling/createMessage, or elicitation/create requests while handling an active client-initiated…
Confirm which endpoint is canonical, correct or retire the stale registry entry, and re-sync so every alias agrees on o…

Next action

revalidate, add safeguards, export policy

write/admin actions need confirmation safeguards + unauthenticated behavior not proven

Compare alternatives Export policy Open report JSON Dispute this assessment

Observed Attention

Moderate observed attention

AI discovery detected. This MCP server has recently appeared in AI-assisted discovery or evaluation traffic on Verify.

Machine trust evaluator activity
Search crawler activity
profile / compare API inspection

Bucketed signal based on recent segmented Verify telemetry. Crawler and evaluator activity is not treated as confirmed human demand.

Claim this profile to control the metadata agents are reading and publish verified ownership, security contact, policy metadata, badge status, and Intelligence API fields.

Risk Compatibility Evidence Fix it Governance

Status

Healthy

Score

72.4

Transport

streamable-http

Tools

Ownership

Unclaimed

Claim, revalidate, or manage this server

DISPUTE THIS ASSESSMENT

Dispute this assessment

If any published claim about this server -- its score, a risk flag, a capability classification, or its taxonomy -- is factually wrong, tell us what evidence shows and we will review it. This does not require claiming or verifying ownership of the server first.

Verify responds to disputes within 5 business days and resolves them within 15.

Dispute history

No disputes filed for this server.

Risk

Security posture

Tools analyzed

High-risk tools

Destructive tools

Exec tools

Egress tools

Secret tools

Bulk-access tools

Risk distribution

medium:14

Tool capability & risk inventory

Tool	Capabilities	Risk	Findings	Notes
`list_skills`	read network admin	Medium	arbitrary network egress freeform input surface	Safeguards hinted in metadata.
`get_skill`	read network	Medium	arbitrary network egress	No explicit safeguard hints detected.
`get_skill_sections`	read network	Medium	arbitrary network egress	No explicit safeguard hints detected.
`search_skills`	read network	Medium	arbitrary network egress freeform input surface	No explicit safeguard hints detected.
`search_rules`	read network	Medium	arbitrary network egress	Safeguards hinted in metadata.
`get_deadlines`	read network	Medium	arbitrary network egress	No explicit safeguard hints detected.
`list_rule_facets`	read network	Medium	arbitrary network egress	No explicit safeguard hints detected.
`start_help`	read network	Medium	arbitrary network egress	No explicit safeguard hints detected.
`start`	read network	Medium	arbitrary network egress	No explicit safeguard hints detected.
`list_jurisdictions`	read network	Medium	arbitrary network egress	No explicit safeguard hints detected.
`list_verifiers`	read network	Medium	arbitrary network egress	No explicit safeguard hints detected.
`validate_vat_number`	read network	Medium	arbitrary network egress freeform input surface	Safeguards hinted in metadata.
`check_audit_exemption`	read network	Medium	arbitrary network egress	No explicit safeguard hints detected.
`share_with_openaccountants`	write network	Medium	arbitrary network egress	No explicit safeguard hints detected.

Write-action governance

Governance status

Safe to publish

✓

Auth boundary

oauth_or_auth_required

Blast radius

Low

High-risk tools

Confirmation signals

search_rules, start_help, validate_vat_number

Safeguard count

Status detail: No unsafe write-action governance gaps detected on the latest validation.

Tool	Risk	Flags	Safeguards
No high-risk tools were detected on the latest run.

Action-controls diff

Snapshot changed

yes

Disabled-by-default candidates

check_audit_exemption get_deadlines get_skill get_skill_sections list_jurisdictions list_rule_facets list_skills list_verifiers search_rules search_skills share_with_openaccountants start start_help validate_vat_number

Manual review candidates

New actions

Action	Risk	Flags
`check_audit_exemption`	Medium	arbitrary network egress
`get_deadlines`	Medium	arbitrary network egress
`get_skill`	Medium	arbitrary network egress
`get_skill_sections`	Medium	arbitrary network egress
`list_jurisdictions`	Medium	arbitrary network egress
`list_rule_facets`	Medium	arbitrary network egress
`list_skills`	Medium	arbitrary network egress freeform input surface
`list_verifiers`	Medium	arbitrary network egress
`search_rules`	Medium	arbitrary network egress
`search_skills`	Medium	arbitrary network egress freeform input surface
`share_with_openaccountants`	Medium	arbitrary network egress
`start`	Medium	arbitrary network egress
`start_help`	Medium	arbitrary network egress
`validate_vat_number`	Medium	arbitrary network egress freeform input surface

Changed actions

Action	Change types	Risk
No materially changed actions.

Critical alerts

High/critical-severity alerts

Production verdicts degrade quickly when high or critical-severity alerts are active.

Compatibility

Client compatibility verdicts

Client compatibility only means the server shape can work with a client. Production trust decision and write-action publishing are evaluated separately so a client-compatible server can still be blocked for production.

Client compatibility: ChatGPT

Client-compatible

Transport compliance should be in good shape.

Confidence: high (83.75)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history, server_card

Disagreements: none

initialize • OK
tools_list • OK
transport_compliance_probe • Error
step_up_auth_probe • Warning
connector_replay_probe • OK — Frozen tool snapshots must survive refresh.
request_association_probe • Warning — Roots, sampling, and elicitation should stay request-scoped.

Client compatibility: Claude

Client-compatible

Transport behavior should match Claude-compatible HTTP expectations.

Confidence: high (83.75)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history, server_card

Disagreements: none

initialize • OK
tools_list • OK
transport_compliance_probe • Error

Write-action publishing

Publishing allowed

Current write surface is bounded enough for cautious review with production policy controls.

Confidence: high (83.75)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history

Disagreements: none

action_safety_probe • OK

Snapshot churn risk

Medium

The live tool surface changed between recent validations.

Confidence: high (83.75)

Evidence provenance

Winner: history

Supporting sources: history, live_validation

Disagreements: none

tool_snapshot_probe • OK
connector_replay_probe • OK

Client compatibility gate details

ChatGPT custom connector

Client-compatible

Remediation checklist

Transport compliance should be in good shape.
The tool surface is not limited to search/fetch-style read tools.
This client profile expects a read/search-only tool surface, but write, delete, or exec-capable tools are present.
A connector refresh would break existing tool references (new required arguments or removed tools) -- an admin must re-approve the connector before this is safe.
Not yet safe for company-knowledge use: requires a search/fetch-only surface with no write actions present.
Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.

Claude remote MCP

Client-compatible

Remediation checklist

Transport behavior should match Claude-compatible HTTP expectations.
The tool surface is not limited to search/fetch-style read tools.
This client profile expects a read/search-only tool surface, but write, delete, or exec-capable tools are present.
A connector refresh would break existing tool references (new required arguments or removed tools) -- an admin must re-approve the connector before this is safe.
Not yet safe for company-knowledge use: requires a search/fetch-only surface with no write actions present.
Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.

Write-safe publishing

Blocked

Remediation checklist

Production readiness is blocked by an active alert: Tool snapshot changed.
Production readiness is blocked by an active alert: Auth mode changed.

Verdict traces

Production verdict

Needs remediation

Degraded from Safe for evaluation: 2 open high/critical-severity alert(s) are active, including at least one that blocks even evaluation-level trust.

Confidence: high (83.75)

Winning source: live_validation

Triggering alerts

tool_snapshot_changed • high • Tool snapshot changed
auth_mode_changed • high • Auth mode changed

Client verdict trace table

Verdict	Status	Checks	Winning source	Conflicts
`openai_connectors`	Client-compatible	initialize, tools_list, transport_compliance_probe, step_up_auth_probe, connector_replay_probe, request_association_probe	live_validation	none
`claude_desktop`	Client-compatible	initialize, tools_list, transport_compliance_probe	live_validation	none
`unsafe_for_write_actions`	Publishing allowed	action_safety_probe	live_validation	none
`snapshot_churn_risk`	Medium	tool_snapshot_probe, connector_replay_probe	history	none

Publishability policy profiles

ChatGPT custom connector compatibility

Compatible with review

Transport compliance should be in good shape. Compatibility is not a production approval; company knowledge and Messages API gates remain separate.

Search Fetch Only: No
Write Actions Present: Yes
Oauth Configured: Yes
Admin Refresh Required: Yes
Safe For Company Knowledge: No
Safe For Messages Api Remote Mcp: No

Claude remote MCP compatibility

Connector-compatible

Transport behavior should match Claude-compatible HTTP expectations. Compatibility is not a production approval; company knowledge and Messages API gates remain separate.

Search Fetch Only: No
Write Actions Present: Yes
Oauth Configured: Yes
Admin Refresh Required: Yes
Safe For Company Knowledge: No
Safe For Messages Api Remote Mcp: No

Compatibility fixtures

ChatGPT custom connector fixture

Passes

Transport compliance should be in good shape.

remote_http_endpoint: Passes
oauth_discovery: Passes
frozen_tool_snapshot_refresh: Passes
request_association: Passes

Anthropic remote MCP fixture

Degraded

Transport behavior should match Claude-compatible HTTP expectations.

remote_transport: Passes
tool_discovery: Passes
auth_connect: Passes
safe_write_review: Passes

Recommended for

OpenAI connectors

OpenAI connectors is marked compatible with score 89.

Claude Desktop

Claude Desktop is marked compatible with score 83.

Smithery

Smithery is marked compatible with score 80.

Generic Streamable HTTP

Generic Streamable HTTP is marked compatible with score 100.

Evidence

Current trust snapshot

Snapshot ID

trustsnap_52212483c3924fc6

Use this ID to compare server page, report, policy, MCP, homepage, ranking, and shortlist surfaces.

Snapshot generated

Aug 06, 2026 10:20:32 PM UTC

All page, report, policy, and MCP surfaces use this same server-detail snapshot shape.

Last validated

Aug 06, 2026 07:15:13 PM UTC

Age: 3.09h • evidence age tier: Verified in last 24h • display score: 72.4

Canonical machine links

Compare index

/compare.json

Compare API

/v1/compare?server=awesome-openaccountants%2Fopenaccountants

Trust summary

/v1/servers/awesome-openaccountants/openaccountants/trust-summary

Report JSON

/v1/servers/awesome-openaccountants/openaccountants/report

Policy export

/v1/servers/awesome-openaccountants/openaccountants/policy

Badge metadata

/v1/servers/awesome-openaccountants/openaccountants/badge

Ledger evidence

/v1/servers/awesome-openaccountants/openaccountants/ledger

Human compare URL

/compare?server=awesome-openaccountants%2Fopenaccountants

Evidence confidence

Confidence score

83.8

Based on 7 recent validations, 27 captured checks, and validation age of 3.1 hours.

Live checks captured

More direct checks increase trust in the current verdict.

Validation age

3.1h

Lower age means fresher evidence.

Latest validation evidence

Latest summary

Healthy

Validation profile

remote_mcp

Started

Aug 06, 2026 07:15:10 PM UTC

Latency

3125.3 ms

Failures

openid_configuration Client error '404 Not Found' for url 'https://www.openaccountants.com/.well-known/openid-configuration' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
resources_list JSON-RPC error -32601: Method not found: resources/list
transport_compliance_probe Issues: missing protocol header, bad protocol not rejected, delete session unexpected, expired session not 404 (bad protocol=200, DELETE=405, expired session=200).

Checks

Check	Status	Latency	Evidence
`action_safety_probe`	OK	n/a	No high-risk write, destructive, or exec tools detected.
`advanced_capabilities_probe`	Warning	n/a	Only 3 capability signal(s): prompts, sampling, structured outputs.
`connector_publishability_probe`	Warning	n/a	Publishability blockers: transport compliance.
`connector_replay_probe`	OK	n/a	Backward compatible with no breaking tool-surface changes.
`determinism_probe`	OK	177.5 ms	Check completed
`initialize`	OK	192.2 ms	Protocol 2025-03-26
`interactive_flow_probe`	OK	n/a	Check completed
`oauth_authorization_server`	OK	78.2 ms	authorization_endpoint, code_challenge_methods_supported, grant_types_supported, issuer
`oauth_protected_resource`	OK	77.6 ms	1 authorization server(s)
`official_registry_probe`	Warning	n/a	Check completed
`openid_configuration`	Error	89.7 ms	Client error '404 Not Found' for url 'https://www.openaccountants.com/.well-known/openid-configuration' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
`probe_noise_resilience`	OK	77.9 ms	Fetched https://www.openaccountants.com/robots.txt
`prompt_get`	OK	177.7 ms	1 prompt message(s) returned
`prompts_list`	OK	171.7 ms	13 prompt(s) exposed
`protocol_version_probe`	Warning	n/a	Claims 2025-03-26; 2 release(s) behind 2025-11-25.
`provenance_divergence_probe`	Not_Assessed	n/a	Check completed
`request_association_probe`	Warning	75.3 ms	Advertised=sampling; observed=none.
`resource_read`	Missing	n/a	no resource uri
`resources_list`	Error	178.4 ms	JSON-RPC error -32601: Method not found: resources/list
`schema_divergence_probe`	Missing	n/a	no server card tools
`server_card`	OK	638.6 ms	authentication, branding, capabilities, categories
`session_resume_probe`	OK	176.6 ms	14 tool(s) exposed
`step_up_auth_probe`	Warning	n/a	Scopes=email, openid, profile.
`tool_snapshot_probe`	OK	n/a	Check completed
`tools_list`	OK	185.9 ms	14 tool(s) exposed
`transport_compliance_probe`	Error	241.5 ms	Issues: missing protocol header, bad protocol not rejected, delete session unexpected, expired session not 404 (bad protocol=200, DELETE=405, expired session=200).
`utility_coverage_probe`	Warning	178.2 ms	No completions evidence; pagination supported; tasks missing.

Raw evidence view

Show raw JSON evidence

Large evidence payload summarized to keep this page fast. Full raw evidence remains available from the JSON report.

{
  "checks": {
    "count": 27,
    "items": {
      "action_safety_probe": {
        "auth_present": true,
        "safeguard_count": 3,
        "status": "ok"
      },
      "advanced_capabilities_probe": {
        "status": "warning"
      },
      "connector_publishability_probe": {
        "status": "warning"
      },
      "connector_replay_probe": {
        "status": "ok"
      },
      "determinism_probe": {
        "latency_ms": 177.5,
        "status": "ok"
      },
      "initialize": {
        "http_status": 200,
        "latency_ms": 192.15,
        "payload_omitted": true,
        "status": "ok"
      },
      "interactive_flow_probe": {
        "status": "ok"
      },
      "oauth_authorization_server": {
        "http_status": 200,
        "latency_ms": 78.23,
        "payload_omitted": true,
        "status": "ok"
      },
      "oauth_protected_resource": {
        "http_status": 200,
        "latency_ms": 77.64,
        "payload_omitted": true,
        "status": "ok"
      },
      "official_registry_probe": {
        "status": "warning"
      },
      "openid_configuration": {
        "latency_ms": 89.68,
        "reason": "Client error '404 Not Found' for url 'https://www.openaccountants.com/.well-known/openid-configuration'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "status": "error"
      },
      "probe_noise_resilience": {
        "http_status": 200,
        "latency_ms": 77.88,
        "status": "ok"
      },
      "prompt_get": {
        "http_status": 200,
        "latency_ms": 177.73,
        "payload_omitted": true,
        "status": "ok"
      },
      "prompts_list": {
        "http_status": 200,
        "latency_ms": 171.71,
        "payload_omitted": true,
        "status": "ok"
      },
      "protocol_version_probe": {
        "status": "warning"
      },
      "provenance_divergence_probe": {
        "status": "not_assessed"
      },
      "request_association_probe": {
        "http_status": 405,
        "latency_ms": 75.33,
        "status": "warning"
      },
      "resource_read": {
        "reason": "no_resource_uri",
        "status": "missing"
      },
      "resources_list": {
        "http_status": 200,
        "latency_ms": 178.36,
        "payload_omitted": true,
        "status": "error"
      },
      "schema_divergence_probe": {
        "reason": "no_server_card_tools",
        "status": "missing"
      },
      "server_card": {
        "http_status": 200,
        "latency_ms": 638.64,
        "payload_omitted": true,
        "status": "ok"
      },
      "session_resume_probe": {
        "http_status": 200,
        "latency_ms": 176.6,
        "payload_omitted": true,
        "status": "ok",
        "tool_count": 14,
        "tool_names_preview": [
          "list_skills",
          "get_skill",
          "get_skill_sections",
          "search_skills",
          "search_rules",
          "get_deadlines",
          "list_rule_facets",
          "start_help",
          "start",
          "list_jurisdictions",
          "list_verifiers",
          "validate_vat_number",
          "check_audit_exemption",
          "share_with_openaccountants"
        ]
      },
      "step_up_auth_probe": {
        "status": "warning"
      },
      "tool_snapshot_probe": {
        "status": "ok"
      },
      "tools_list": {
        "http_status": 200,
        "latency_ms": 185.87,
        "payload_omitted": true,
        "status": "ok",
        "tool_count": 14,
        "tool_names_preview": [
          "list_skills",
          "get_skill",
          "get_skill_sections",
          "search_skills",
          "search_rules",
          "get_deadlines",
          "list_rule_facets",
          "start_help",
          "start",
          "list_jurisdictions",
          "list_verifiers",
          "validate_vat_number",
          "check_audit_exemption",
          "share_with_openaccountants"
        ]
      },
      "transport_compliance_probe": {
        "latency_ms": 241.52,
        "protocol_header_present": false,
        "status": "error"
      },
      "utility_coverage_probe": {
        "latency_ms": 178.22,
        "status": "warning"
      }
    },
    "omitted_count": 0
  },
  "failures": {
    "count": 3,
    "items": {
      "openid_configuration": {},
      "resources_list": {},
      "transport_compliance_probe": {}
    },
    "omitted_count": 0
  },
  "message": "Raw evidence is summarized in HTML to keep server detail pages fast. Use the JSON report or evidence API for the full payload.",
  "remote_url": "https://www.openaccountants.com/api/mcp",
  "server_card": {
    "name": null,
    "raw_payload_omitted": false,
    "version": null
  },
  "server_identifier": "awesome-openaccountants/openaccountants",
  "truncated": true
}

Known versions

No versions recorded.

Validation history

7 day score delta

n/a

30 day score delta

n/a

Recent healthy ratio

100%

Freshness

3.1h

Timestamp	Status	Score	Latency	Tools
Aug 06, 2026 07:15:13 PM UTC	Healthy	72.4	3125.3 ms	14
Aug 06, 2026 01:14:48 PM UTC	Healthy	43.4	2628.6 ms	0
Aug 06, 2026 07:14:17 AM UTC	Healthy	43.8	2672.1 ms	0
Aug 06, 2026 01:14:11 AM UTC	Healthy	42.9	2693.0 ms	0
Aug 05, 2026 07:04:18 PM UTC	Healthy	46.8	2897.3 ms	0
Aug 04, 2026 08:49:03 PM UTC	Healthy	46.2	2814.2 ms	0
Jul 31, 2026 06:25:21 AM UTC	Healthy	45.3	2645.3 ms	0

Validation timeline

Validated	Summary	Score	Protocol	Auth mode	Tools	Changes
Aug 06, 2026 07:15:13 PM UTC	Healthy	72.4	2025-03-26	oauth_supported	14	auth_mode_changed tool_snapshot_changed
Aug 06, 2026 01:14:48 PM UTC	Healthy	43.4	unknown	unknown	0	none
Aug 06, 2026 07:14:17 AM UTC	Healthy	43.8	unknown	unknown	0	none
Aug 06, 2026 01:14:11 AM UTC	Healthy	42.9	unknown	unknown	0	none
Aug 05, 2026 07:04:18 PM UTC	Healthy	46.8	unknown	unknown	0	none
Aug 04, 2026 08:49:03 PM UTC	Healthy	46.2	unknown	unknown	0	none
Jul 31, 2026 06:25:21 AM UTC	Healthy	45.3	unknown	unknown	0	none

Recent validation runs

Recent validation runs for this MCP server
Started	Status	Summary	Latency	Checks
Aug 06, 2026 07:15:10 PM UTC	Completed	Healthy	3125.3 ms	action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 06, 2026 01:14:46 PM UTC	Completed	Healthy	2628.6 ms
Aug 06, 2026 07:14:15 AM UTC	Completed	Healthy	2672.1 ms
Aug 06, 2026 01:14:08 AM UTC	Completed	Healthy	2693.0 ms
Aug 05, 2026 07:04:15 PM UTC	Completed	Healthy	2897.3 ms
Aug 04, 2026 08:49:00 PM UTC	Completed	Healthy	2814.2 ms
Jul 31, 2026 06:25:18 AM UTC	Completed	Healthy	2645.3 ms

Public server reputation

Validation success 7d

1.0

Validation success 30d

1.0

Mean time to recover

n/a

Breaking diffs 30d

Registry drift frequency 30d

Snapshot changes 30d

Incident & change feed

Timestamp	Event	Details
Aug 06, 2026 07:15:13 PM UTC	Latest validation: healthy	Score 72.4 with status healthy.
Aug 06, 2026 07:15:13 PM UTC	Score changed	Score delta +29.0 versus the previous run.
Aug 06, 2026 07:15:13 PM UTC	Tool snapshot changed	Added 14, removed 0, and changed 0 tool contracts.
Aug 06, 2026 07:15:13 PM UTC	Auth mode changed	Auth mode moved from unknown to oauth_supported.
Aug 06, 2026 01:14:48 PM UTC	Score changed	Score delta -0.3 versus the previous run.
Aug 06, 2026 07:14:17 AM UTC	Score changed	Score delta +0.9 versus the previous run.
Aug 05, 2026 10:58:23 AM UTC	Score corrected (post-1.0.503 remediation, R1 zero-anchoring)	Prior: 77.08. Corrected: 74.62.

Capabilities

OAuth: ✓
DCR/CIMD: ✓
Prompts: ✓
Homepage: https://github.com/openaccountants/openaccountants
Docs: https://github.com/openaccountants/openaccountants
Support: https://github.com/openaccountants/openaccountants
Icon: none
Remote endpoint: https://www.openaccountants.com/api/mcp
Server card: https://www.openaccountants.com/.well-known/mcp/server-card.json

Use-case taxonomy

development database search communication

Benchmark tasks

Benchmark task	Status	Evidence
Discover tools	Passes	`initialize` • OK `tools_list` • OK
Read-only fetch flow	Likely to fail	`resource_read` • Missing `read_only_tool_surface` • Missing
OAuth-required connect	Passes	`oauth_protected_resource` • OK `step_up_auth_probe` • Warning
Safe write flow with confirmation	Passes	`action_safety_probe` • OK

Utility coverage

Probe status

Warning

Completions

not detected

Completion probe target: { "argument_name": "skillSlug", "name": "skill-review", "type": "prompt" }

Pagination

supported

No nextCursor evidence.

Tasks

Missing

Advertised: no

Transport compliance drilldown

Probe status

Error

Transport

streamable-http

Session header

yes

Protocol header

Bad protocol response

200

DELETE teardown

405

Expired session retry

200

Last-Event-ID visible

Issues: missing_protocol_header, bad_protocol_not_rejected, delete_session_unexpected, expired_session_not_404

Request association

Status

Warning

Advertised capabilities

sampling

Observed idle methods

none

Violating methods

none

Probe HTTP status

405

Issues

idle_stream_not_observable

Connector replay

Status

Backward compatible

✓

Would break after refresh

Added tools

none

Removed tools

none

Additive output changes

none

Required-argument replay breaks

Tool	Added required args	Removed required args
No required-argument replay breaks detected.

Output-schema replay breaks

Tool	Removed properties	Added properties
No output-schema replay breaks detected.

Tool snapshot diff & changelog

Snapshot changed

yes

Added tools

Removed tools

none

Required-argument changes

Tool	Added required args	Removed required args
No required-argument changes detected.

Output-schema drift

Tool	Previous properties	Latest properties
No output-schema drift detected.

Validation diff

Score delta

28.96

Summary changed

Tool delta

Prompt delta

Auth mode changed

yes

Write surface expanded

Protocol regressed

Registry drift changed

Regressed checks: openid_configuration, provenance_divergence_probe, resources_list, transport_compliance_probe

Improved checks: action_safety_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, probe_noise_resilience, prompt_get, prompts_list, server_card, session_resume_probe, tool_snapshot_probe, tools_list

Newly assessed dimensions: none

No longer assessed dimensions: none

Component	Previous	Latest	Delta
No component deltas between the latest two runs.

Registry & provenance divergence

Probe status

Error

Direct official match

Drift fields

homepage registry_identifier registry_source remote_url

Field	Registry	Live server card
Title	n/a	openaccountants
Version	n/a	1.4.0
Homepage	n/a	https://www.openaccountants.com

Active alerts

Tool snapshot changed (high)
Tools were added, removed, or materially changed between the latest two validations.
Auth mode changed (high)
Auth mode changed from unknown to oauth_supported.

Aliases & registry graph

Identifier	Source	Canonical	Score
`awesome-openaccountants/openaccountants`	awesome_mcp_servers	yes	72.4
`openaccountants/openaccountants`	glama_registry	no	n/a

Alias consolidation

Canonical identifier

awesome-openaccountants/openaccountants

Duplicate aliases

Registry sources

awesome_mcp_servers glama_registry

Remote URLs

https://glama.ai/mcp/servers/do7jqh56go

https://www.openaccountants.com/api/mcp

Homepages

https://github.com/openaccountants/openaccountants

https://glama.ai/mcp/servers/do7jqh56go

Source disagreements

Field	What differs	Observed values
Registry source	Multiple registries or registry sync paths claim this same canonical server.	awesome_mcp_servers glama_registry
Remote URL	Aliases currently point at different MCP endpoints, which can indicate mirrors, stale registry data, or a real endpoint split.	https://glama.ai/mcp/servers/do7jqh56go https://www.openaccountants.com/api/mcp
Homepage	Registry entries disagree on the primary homepage for this server.	https://github.com/openaccountants/openaccountants https://glama.ai/mcp/servers/do7jqh56go
Registry identifier	Different registry-specific identifiers resolve to the same canonical server record here.	awesome_mcp_servers:openaccountants/openaccountants glama_registry:do7jqh56go

Fix it

Why this score?

Access & Protocol

35/44

Connectivity, auth, and transport expectations for common clients.

Interface Quality

37/56

How well the tool/resource interface communicates and behaves under automation.

Security Posture

27/36

How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.

Reliability & Trust

21/24

Operational stability, consistency, and trustworthiness over time.

Discovery & Governance

14/28

How well the server is documented, listed, and governed in public registries.

Adoption & Market

5/8

Adoption clues and public evidence that the server is intended for external use.

Algorithmic score breakdown

Auth Operability

4/4

Measures whether auth discovery and protected access behave predictably for clients.

Error Contract Quality

1/4

Grades machine-readable error structure, status alignment, and remediation hints.

Rate-Limit Semantics

2/4

Checks whether quota/throttle responses are deterministic and automation-friendly.

Schema Completeness

3/4

Completeness of tool descriptions, parameter docs, examples, and schema shape.

Backward Compatibility

4/4

Stability score across tool schema/name drift relative to prior validations.

SLO Health

3/4

Availability, latency, and burst-failure profile across recent validation history.

Security Hygiene

2/4

HTTPS posture, endpoint hygiene, and response-surface hardening checks.

Task Success

4/4

Can an agent reliably initialize, enumerate tools, and execute core MCP flows?

Trust Confidence

2/4

Confidence-adjusted reliability score that penalizes low evidence volume.

Abuse/Noise Resilience

4/4

How well the server preserves core behavior in the presence of noisy traffic patterns.

Prompt Contract

3/4

Quality of prompt metadata, argument shape, and prompt discoverability for clients.

Resource Contract

1/4

How completely resources and resource templates describe URIs, types, and usage shape.

Discovery Metadata

3/4

Homepage, docs, icon, repository, support, and license coverage for directory consumers.

Registry Consistency

2/4

Agreement between stored registry metadata, live server-card data, and current validation output.

Installability

4/4

How cleanly a real client can connect, initialize, enumerate tools, and proceed through auth.

Session Semantics

4/4

Determinism and state behavior across repeated MCP calls, including sticky-session surprises.

Tool Surface Design

4/4

Naming clarity, schema ergonomics, and parameter complexity across the tool surface.

Result Shape Stability

4/4

Stability of declared output schemas across validations, with penalties for drift or missing shapes.

OAuth Interop

4/4

Depth and client compatibility of OAuth/OIDC metadata beyond the minimal protected-resource check.

Recovery Semantics

1/4

Whether failures include actionable machine-readable next steps such as retry or upgrade guidance.

Maintenance Signal

2/4

Versioning, update recency, and historical validation cadence that indicate active stewardship.

Adoption Signal

2/4

Directory presence and distribution clues that suggest the server is intended for external use.

Freshness Confidence

4/4

Confidence that recent validations are current enough and dense enough to trust operationally.

Transport Fidelity

4/4

Whether declared transport metadata matches the observed endpoint behavior and response formats.

Spec Recency

2/4

How close the server’s claimed MCP protocol version is to the latest known public revision.

Session Resume

4/4

Whether Streamable HTTP session identifiers and resumed requests behave cleanly for real clients.

Step-Up Auth

3/4

Whether OAuth metadata and WWW-Authenticate challenges support granular, incremental consent instead of broad upfront scopes.

Transport Compliance

1/4

Checks session headers, protocol-version enforcement, session teardown, and expired-session behavior.

Utility Coverage

1/4

Signals support for completions, pagination, and task-oriented utility surfaces that larger clients increasingly expect.

Advanced Capability Coverage

1/4

Coverage of newer MCP surfaces like roots, sampling, elicitation, structured output, and related metadata.

Connector Publishability

3/4

How ready the server looks for client catalogs and managed connector programs.

Tool Snapshot Churn

4/4

Stability of the tool surface across recent validations, including add/remove and output-shape drift.

Connector Replay

4/4

Whether a previously published frozen connector snapshot would remain backward compatible after the latest tool refresh.

Request Association

2/4

Whether roots, sampling, and elicitation appear tied to active client requests instead of arriving unsolicited on idle sessions.

Interactive Flow Safety

4/4

Whether prompts and docs steer users toward safe auth flows instead of pasting secrets directly.

Action Safety

3/4

Risk-weighted view of destructive, exec, egress, and confirmation semantics across the tool surface.

Official Registry Presence

3/4

Whether the server appears directly or indirectly in the official MCP registry.

Safety Transparency

3/4

Clarity of docs, auth disclosure, support links, and other trust signals visible to integrators.

Tool Capability Clarity

4/4

How clearly the tool surface communicates whether each action reads, writes, deletes, executes, or exports data.

Destructive Operation Safety

3/4

Penalizes delete/revoke/destroy style tools unless auth and safeguards reduce blast radius.

Egress / SSRF Resilience

2/4

Assesses arbitrary URL fetch, crawl, webhook, and remote-request exposure on the tool surface.

Execution / Sandbox Safety

4/4

Evaluates shell, code, script, and command-execution exposure and whether that surface appears contained.

Data Exfiltration Resilience

3/4

Assesses export, dump, backup, and bulk-read behavior against the surrounding auth and safeguard signals.

Least Privilege Scope

3/4

Rewards scoped auth metadata and penalizes broad or missing scopes around privileged tools.

Secret Handling Hygiene

3/4

Assesses secret-bearing tools, token leakage risk, and whether the public surface avoids obvious secret exposure.

Supply Chain Signal

1/4

Public metadata signal for repository, changelog, license, versioning, and recency that supports supply-chain trust.

Input Sanitization Safety

3/4

Penalizes risky freeform string inputs when schemas do not constrain URLs, code, paths, queries, or templates.

Tool Namespace Clarity

4/4

Measures naming uniqueness and ambiguity across the tool namespace to reduce collision and confusion risk.

Actionable remediation

Severity	Remediation	Why it matters	Recommended action
High	Align session and protocol behavior with Streamable HTTP expectations	Clients increasingly rely on MCP-Protocol-Version, session teardown, and expired-session semantics.	Align MCP-Protocol-Version, MCP-Session-Id, DELETE teardown, and expired-session handling with the transport spec. Playbook Return `Mcp-Session-Id` and `Mcp-Protocol-Version` headers consistently on streamable HTTP responses. Honor `DELETE` session teardown and return `404` when a deleted session is reused. Reject invalid protocol-version headers with `400 Bad Request`.
High	Associate roots, sampling, and elicitation with active client requests	Modern MCP guidance expects roots, sampling, and elicitation traffic to be tied to an active client request instead of arriving unsolicited on idle sessions.	Only send roots/list, sampling/createMessage, or elicitation/create requests while handling an active client-initiated request, never on idle sessions. Playbook Only send `roots/list`, `sampling/createMessage`, or `elicitation/create` requests while handling an active client-initiated request. Avoid emitting these requests on idle or newly-initialized sessions with no pending client request. Revalidate and confirm `request_association_probe` no longer returns `missing` or `warning`.
High	Resolve conflicting endpoints across registry aliases	Registry aliases for this canonical server currently resolve to different live MCP endpoints (https://glama.ai/mcp/servers/do7jqh56go, https://www.openaccountants.com/api/mcp). An agent following one registry entry reaches a different server than one following another.	Confirm which endpoint is canonical, correct or retire the stale registry entry, and re-sync so every alias agrees on one remote_url. Playbook Identify which of the listed remote_url values is the operator's actual, currently-maintained endpoint. Update or remove the registry entries pointing at any other endpoint (a mirror, a stale fork, or a decommissioned deployment). Re-run registry sync and confirm the alias-consolidation view shows a single remote_url before treating this as resolved.
High	Respond to auth mode changed	Auth mode changed from unknown to oauth_supported.	Document the new auth posture and confirm protected-resource and challenge metadata still match reality.
High	Respond to tool snapshot changed	Tools were added, removed, or materially changed between the latest two validations.	Publish a first-class changelog for tool additions, removals, and breaking schema changes. Playbook Review the tool snapshot diff for adds, removals, required-arg changes, and output-schema drift. Publish a changelog before managed connector clients refresh their frozen tool snapshots. Revalidate after the changelog and connector metadata are in sync.
High	Sync the published server card's tool schemas with the live tool surface	The server card and live tools/list disagree on parameter names, required sets, or types -- clients that trust the published card will construct invalid calls.	Regenerate the published server card from the live tool schemas (or vice versa) so parameter names, required sets, and types match exactly. Playbook Diff the published `/.well-known/mcp/server-card.json` tool schemas against a live `tools/list` response. Fix parameter name mismatches, required-set mismatches, and type mismatches per tool. Regenerate or hand-sync the server card whenever the live tool schemas change -- treat drift as a release blocker, not a documentation nit.
Medium	Adopt a current MCP protocol revision	Older protocol revisions reduce compatibility with newer clients and registry programs.	Advertise a current MCP protocol revision (2025-06-18 or later) in both the initialize response and the MCP-Protocol-Version header. Playbook Update the server's advertised protocol version to a current MCP revision (2025-06-18 or later). Return the negotiated version consistently in both the `initialize` response and the `MCP-Protocol-Version` header. Revalidate and confirm `protocol_version_probe` reports `ok`.
Medium	Close connector-publishing gaps	Connector catalogs care about protocol recency, session behavior, auth clarity, and tool-surface stability.
Medium	Document minimal scopes and return cleaner auth challenges	Modern clients expect granular scopes and step-up auth signals such as WWW-Authenticate scope hints.	Return granular scopes and WWW-Authenticate challenge hints instead of forcing overly broad auth upfront. Playbook Advertise the narrowest viable scopes in OAuth metadata. Return `WWW-Authenticate` challenges with scope or insufficient-scope hints when additional consent is needed. Revalidate with both public discovery and auth-required flows.
Medium	Publish OpenID configuration	OIDC metadata improves token validation and client compatibility.	Expose /.well-known/openid-configuration with issuer, jwks_uri, and supported grants. Playbook Serve `/.well-known/openid-configuration` with `issuer`, `jwks_uri`, `authorization_endpoint`, and `token_endpoint`. List supported grant types in `grant_types_supported` and scopes in `scopes_supported`. Revalidate and confirm the `openid_configuration` check returns `ok`.
Medium	Reconcile registry, server-card, and repository metadata	Directory trust falls quickly when official registry fields drift from the live server card or public repo metadata.
Medium	Repair resources/list or stop advertising resources	Resource metadata should either work live or be removed from the advertised capability set.	Only advertise resources if resources/list works and resources expose stable URIs/types. Playbook Only advertise resources with stable URIs and read semantics. Add MIME/type hints where possible. Run a live `resources/list` and `resources/read` check after updates.
Low	Expose modern utility surfaces like completions, pagination, or tasks	Utility coverage improves interoperability with larger clients and long-lived agent workflows.	Expose completions, pagination, and task metadata where supported so larger clients can plan and resume work safely. Playbook Advertise `completions`, pagination cursors, and `tasks` only when they are actually supported. Return `nextCursor` on large list operations when pagination is available. Document task support and whether it requires step-up auth.
Low	Publish newer MCP capability signals	Roots, sampling, elicitation, structured outputs, and related metadata improve client understanding and ranking.	Advertise only the advanced capabilities (roots, sampling, elicitation) you have actually implemented end to end in the initialize capabilities object. Playbook Add the capabilities you actually support (`roots`, `sampling`, `elicitation`) to the `capabilities` object returned from `initialize`. Only advertise a capability once the corresponding request/response flow is implemented end to end. Revalidate and confirm `advanced_capabilities_probe` reflects the updated capability set.
Low	Publish or reconcile the server in the official MCP registry	Official registry presence improves discovery confidence and cross-source consistency.

Point loss breakdown

Component	Current	Points missing
Utility Coverage	1/4	-3.0
Transport Compliance	1/4	-3.0
Resource Contract	1/4	-3.0
Recovery Semantics	1/4	-3.0
Error Contract	1/4	-3.0
Dependency Supply Chain Signal	1/4	-3.0
Advanced Capability Coverage	1/4	-3.0
Trust Confidence	2/4	-2.0
Spec Recency	2/4	-2.0
Security Hygiene	2/4	-2.0
Request Association	2/4	-2.0
Registry Consistency	2/4	-2.0

Compatibility profiles

OpenAI Connectors

88.9

compatible

Transport compliance should be in good shape.

Connector URL: https://www.openaccountants.com/api/mcp
# Complete OAuth in the client when prompted.
# Server: awesome-openaccountants/openaccountants

Claude Desktop

83.3

compatible

Transport behavior should match Claude-compatible HTTP expectations.

{
  "mcpServers": {
    "openaccountants": {
      "command": "npx",
      "args": ["mcp-remote", "https://www.openaccountants.com/api/mcp"]
    }
  }
}

Smithery

80.0

compatible

Machine-readable failure semantics should be present.

smithery mcp add "https://www.openaccountants.com/api/mcp"

Generic Streamable HTTP

100.0

compatible

No major blockers detected.

curl -sS https://www.openaccountants.com/api/mcp -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'

Governance

MCP TrustOps

TrustOps turns this report into operational controls: freshness SLAs, authenticated validation, semantic benchmarks, policy exports, alert subscriptions, badges, cost/compliance metadata, and runtime routing. Fresh trusted index decisions stay separate from long-tail inventory so stale scores do not masquerade as current evidence.

Evidence age tier

Verified in last 24h

Policy SLA (contractual, distinct from the public 24h freshness window): 168.0h • confidence-weighted score (display score discounted for evidence age and confidence -- an internal TrustOps input, not the public score): 60.6 • evidence too old to display: ✕

Policy exports

Export policy

Formats: json, rego, yaml, github_action, gateway_config, client_report

Runtime routing

/v1/decide

Returns allowed tools, blocked tools, approval requirement, and reason.

Hosted runtime

Verify Hosted MCP

Deploy trusted servers from GitHub with secrets, egress controls, releases, rollback, and audit events.

Authenticated validation

Premium publisher feature: paid authenticated runs verify scopes, write-action safeguards, and authorized tool execution.

Active trust badges

Freshly Validated OAuth Verified OpenAI App Compatible Claude Remote MCP Compatible

Semantic benchmarks

available

Templates cover GitHub, database, healthcare, web search, and CRM least-privilege jobs.

Supply chain

metadata signal

Deep scan checks are marked separately from public metadata signals.

Compliance metadata

Terms, privacy, SOC 2, HIPAA, GDPR, retention, deletion, and audit-log fields are tracked as enterprise metadata.

Alert subscription types

Status changes Score drops or recovers Freshness SLA breach Validation schema drift OAuth or auth behavior changes Tool surface changes New or changed write tool Supply-chain signal changes Legal or compliance metadata changes

MCP Runtime hosting

Verify Hosted MCP turns a trusted server report into a managed remote MCP endpoint with GitHub deployment provenance, sandbox policy, encrypted secrets, release history, rollback, and audit/usage events.

Activation readiness

✓

Trusted hosted runtimes require fresh validation, a passing server state, a remote endpoint, and a minimum score.

Minimum tier

TrustOps

Publisher claim plus paid TrustOps tier are required before secrets or releases can be created.

Hosted endpoint

/hosted/{namespace}/{name}/mcp

The endpoint enforces egress allowlists and records audit/usage events.

Blockers

none

Deployment	Status	Endpoint	Release
No hosted runtime deployments yet.

Authenticated validation sessions

Public validation is free. Authenticated validation is paid and proves scoped behavior, write-action safeguards, and authenticated tool execution.

Latest profile

remote_mcp

Authenticated session used

Public score isolation

✓

Preview endpoint

/v1/verify

CI preview endpoint

/v1/ci/preview

Install snippets

Openai Connectors

Connector URL: https://www.openaccountants.com/api/mcp
# Complete OAuth in the client when prompted.
# Server: awesome-openaccountants/openaccountants

Claude Desktop

{
  "mcpServers": {
    "openaccountants": {
      "command": "npx",
      "args": ["mcp-remote", "https://www.openaccountants.com/api/mcp"]
    }
  }
}

Smithery

smithery mcp add "https://www.openaccountants.com/api/mcp"

Generic Http

curl -sS https://www.openaccountants.com/api/mcp -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'

Agent access & tool surface

Live server tools

list_skills get_skill get_skill_sections search_skills search_rules get_deadlines list_rule_facets start_help

Showing 8 of 14 tools.

Observed from the latest live validation against https://www.openaccountants.com/api/mcp. This is the target server surface, not Verify's own inspection tools.

Live capability counts

14 tools • 13 prompts • 0 resources

Counts come from the latest tools/list, prompts/list, and resources/list checks.

Inspect with Verify

search fetch search_servers recommend_servers get_server_report compare_servers

Use Verify itself to search, recommend, compare, and fetch the full report for awesome-openaccountants/openaccountants.

Direct machine links

JSON report • Compare this server • Verify MCP API