coso-mcp
Server Details
Open COSO internal-control review MCP: scope, risk, controls, sampling, testing, workpapers.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- simonmak-ascent/coso-mcp
- GitHub Stars
- 0
- Server Listing
- coso-mcp
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 39 tools
Most tools map to a unique resource+action (register_risk vs register_control, assess_component vs assess_principle, compute_sample_size vs select_sample). The main overlap is get_activity_log vs get_audit_log (both append-only logs) and, to a lesser degree, note_exception vs a failed record_test_result. Overall the boundaries are clear enough for reliable selection.
Nearly all tools follow a snake_case verb_noun pattern (create_engagement, list_controls, register_risk, add_review_note, resolve_review_note). Minor deviations are framework_integration_check (noun phrase) and sign_off (verb only), but the convention is highly predictable overall.
39 tools is on the heavy side for an agent to navigate, even for a broad internal-control review lifecycle. Each tool is distinct and earns a place, but the numerous list_* / get_* pairs and static reference lookups could be consolidated. Borderline over-scoped.
The surface covers the full review lifecycle: engagement, scope, risks, controls, populations, sampling, testing, exceptions, deficiencies, workpapers, review notes, sign-offs, reporting, and COSO framework assessment. The notable gap is the absence of update/delete operations (arguably intentional for an append-only audit trail) and no explicit deficiency-creation tool beyond classify_deficiency.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Paid remote MCP for server intake risk reports, tool review, approvals, and readiness.
Paid remote MCP for AI Studio Workspace approval gate MCP, structured receipts, audit logs, and revi
Evidence-linked MCP selection and non-executing Safe-Call review; surfaces unknowns.
Your audit methodology inside Claude: findings, risks, controls and workpapers in your team format.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceMCP server with 20 internal-audit SKILLs grounded in global standards (IIA, COSO, NIST, ISO, IFRS, COBIT, ACFE), written in Spanish. Enables audit planning, control evaluation, and specialty audits via natural language.CC BY-SA 4.0

convergeqa-mcpofficial
AlicenseBqualityDmaintenanceMCP servers for multi-model document review with critique/iterate and compare/due-diligence tools, using public verification receipts.16MIT- AlicenseAqualityCmaintenanceEnables AI clients to query and trace ITGC audit workpapers, including controls from risk to test result, findings by rating and status, and open items.4MIT

CodexRun Ledger MCPofficial
FlicenseNot gradedqualityDmaintenancePaid remote MCP for generating trustworthy code run receipts, scope summaries, missing evidence checks, and client handoff exports.-
Glama MCP Gateway
Add one secure layer between your agents and this server.