Agent Audit MCP server
Immutable audit trail for agent-to-agent interactions
2 stars
Reviews
Write oneNobody has reviewed Agent Audit yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Agent Audit tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualityno auth information5/15
- Maintenancelast push 61 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Agent Audit compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 63/100
- higher than 19% of 4,460 AI and agents servers
- GitHub stars
- 2
- more than 65% of 2,711 AI and agents servers
Install Agent Audit in Claude Code, Cursor or VS Code
The registry entry has no remote endpoint or installable package.
What the publisher says
From the Agent Audit repository's README, as published. We do not edit it. Read it on GitHub
AgentAudit MCP
Your agent now has an immutable, tamper-evident log of every action it takes — each event cryptographically linked to the previous one so any modification breaks the chain and is immediately detectable.
What your agent can do
- Log any of 16 event types (payments, tasks, disputes, identity checks, messages) with a SHA-256 hash that includes the previous event's hash
- Retrieve the full history of any agent by ID — every action, in order, with timestamps
- Search across the audit trail by agent, event type, severity level, or date range
- Verify chain integrity between any two events and get a per-event pass/fail breakdown showing exactly which link was tampered
- Track five severity levels — info, notice, warning, error, critical — for compliance triage
- Get statistics across the entire audit trail: events by type, by severity, and most active agents
Installation
Requires: Python 3.10+, mcp and fastmcp packages.
pip install mcp fastmcpClaude Desktop — add to ~/Library/Application Support/Claude/claudedesktopconfig.json (macOS) or %APPDATA%\Claude\claudedesktopconfig.json (Windows):
{
"mcpServers": {
"agent-audit": {
"command": "python",
"args": ["/absolute/path/to/agent-audit-mcp/server.py"]
}
}
}Cursor — add to .cursor/mcp.json in your project root:
{
"mcpServers": {
"agent-audit": {
"command": "python",
"args": ["/absolute/path/to/agent-audit-mcp/server.py"]
}
}
}Data is stored locally at ~/.agentaudit/chain.json. No data leaves your machine.
Tool Reference
Supported event types: taskcreated, taskassigned, taskcompleted, taskfailed, paymentsent, paymentreceived, paymentrefunded, disputeraised, disputeresolved, identityverified, capabilityused, agentregistered, agentrated, agentoffline, messagesent, messagereceived
Security
Audit data is written atomically (write-to-temp, then os.replace) to prevent partial writes from corrupting the chain. The hash covers every field including the previous event's hash — you cannot insert, delete, or modify any event without breaking all subsequent hashes. auditverifychain recomputes each hash from scratch rather than trusting stored values.
All data is stored locally. No network requests are made by this server.
Pricing
Subscribe via Stripe
License
Proprietary — see subscription terms. Source: github.com/Rumblingb/agent-audit-mcp
Nothing above is checked by us. What we check is on the safety report.
Agent Audit: common questions
- Is Agent Audit MCP server safe?
- With care: it is graded C, so read the findings first (63/100). Read the Agent Audit safety report
- Does Agent Audit need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Agent Audit maintained?
- The last commit was 99 days ago (2026-07-28). The latest release is v1.0.0.
- What can I use instead of Agent Audit?
- Servers from other publishers that do the same job: Roast My Design System MCP server, Roast My Design System MCP server and three.ws Provenance MCP server.
- How does Agent Audit compare with other AI and agents MCP servers?
- safety score 63/100 (higher than 19% of 4,460 AI and agents servers); github stars 2 (more than 65% of 2,711 AI and agents servers). Full comparison.
Alternatives to Agent Audit
Same job from other publishers: the closest match first, then the best rated.
- Roast My Design SystemAudit your Design System and serve your Agent the rules that keep AI-written UI on-system.not reviewedEstablishedA
- Roast My Design SystemAudit your Design System and serve your Agent the rules that keep AI-written UI on-system.not reviewedEstablishedA
- three.ws ProvenanceAppend-only, signed, on-chain-verifiable agent action log — record and audit what agents did.not reviewedEstablishedB