Mmcp.market

mcp-audit MCP server

by saagpatel·io.github.saagpatel/mcp-audit·v2.7.0
No reviews yet

Scan, enumerate, and risk-score every MCP server configured on your machine.

A89/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A89/100

full report

Adoption
Growing

4 stars41 downloads/wk

Reviews

Write one

Nobody has reviewed mcp-audit yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

mcp-audit tools (13, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • check_server

    Audit a single server by name. Returns JSON audit result.

  • get_artifact_verify_findings

    Return byte-level artifact drift vs the pin baseline. Returns JSON `{findings, warnings}`.

  • get_escalation_findings

    Return capability-escalation findings vs the pin baseline. Returns JSON `{findings, warnings}`.

  • get_high_risk_servers

    Return servers with composite risk score ≥ 7.0. Returns JSON list.

  • get_injection_findings

    Return all prompt injection findings across all servers. Returns JSON `{findings, warnings}`.

  • get_integrity_findings

    Return launch-artifact integrity drift vs the pin baseline. Returns JSON `{findings, warnings}`.

  • get_package_verify_findings

    Return registry package-hash drift vs the pin baseline. Returns JSON `{findings, warnings}`.

  • get_provenance_findings

    Return launch-config provenance drift vs the pin baseline. Returns JSON `{findings, warnings}`.

  • get_shadowing_findings

    Return all cross-server tool-name shadowing findings. Returns JSON `{findings, warnings}`.

  • get_ssrf_findings

    Return all SSRF findings across all servers. Returns JSON `{findings, warnings}`.

  • get_trifecta_findings

    Return per-server and fleet-level lethal-trifecta findings. Returns JSON `{findings, warnings}`.

  • list_discovered_servers

    Return names and clients of all discovered MCP servers. Returns JSON list.

  • scan_mcp_serverswrite action

    Run a full audit of all discovered MCP servers. Returns JSON report.

Public scan report

scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it

no findings
  • Code scan80 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 5 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 89/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the mcp-audit repository's README, as published. We do not edit it. Read it on GitHub

mcp-audit

<!-- mcp-name: io.github.saagpatel/mcp-audit -->

### Audit what your AI agents can actually touch.

Every MCP server wired into your editor is a process that can read your files, reach the network, or run shell commands on your behalf — frequently launched from a remote npx/uvx package that can change underneath you. mcp-audit reads the MCP configs already on your machine and tells you what each server can do, how risky it is, whether its tool descriptions hide adversarial instructions, and whether anything changed since you last looked.

Read-only by default: it never edits a config and reports env-var key names only (never values). Use --skip-connect for a zero-touch config-only pass that does not spawn MCP servers or contact remote endpoints; connected scans, package verification, downloads, and LLM analysis make their extra reach explicit in the command.

For pre-run behavioral evidence, MCPAudit also includes Proof Before Action: a local-only CLI that runs a synthetic command in a disposable no-network container, compares observed effects with a declaration, joins repository MCP dependencies to local mcp-trust evidence, and exports verifiable JSON plus offline HTML.

For MCP 2026-07-28 cache behavior, the experimental Cache Contract Auditor runs a bounded logical-clock simulator over program-owned JSON traces. It checks required ttlMs/cacheScope, private authorization partitions, exact request keys, expiry/refresh and validated change-event behavior, linked page scope, and deterministic tools ordering without running a client, server, or proxy.

For the experimental MCP Tasks extension, the MCP Task Time Machine runs seed-free synthetic lifecycles on a virtual clock. It explains creation, polling, input, retry, cooperative cancellation races, expiry, success, failure, duplicates, stale observations, and forbidden terminal transitions without discovering or contacting an MCP server or reading credentials.

🌐 Try it in your browser, no install: paste any MCP client config at mcp-audit.saagarpatel.dev for an instant config-only trust report. It runs this exact engine, never launches configured servers, never contacts configured endpoints, and stores nothing. The CLI below adds the connected deep checks (prompt-injection, SSRF, the lethal trifecta, schema drift, SARIF).

⚡ 60-second start

No install required — uv runs it in a throwaway environment. This reads the MCP configs already on your machine, connects to each configured server to read its real tool schemas, and flags SSRF-shaped tools:

uvx --from mcp-audits mcp-audit scan --ssrf-check

It stays read-only the whole time — it never edits a config and reports env-var key names only, never values. Sample output:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

claude mcp add mcp-audit -- uvx mcp-audits
Add to Cursor

mcp-audit: common questions

Is mcp-audit MCP server safe?
Yes, by our scan: it is graded A (89/100). Read the mcp-audit safety report
How do I install mcp-audit?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does mcp-audit need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is mcp-audit maintained?
The last commit was 6 days ago (2026-09-18). The latest release is v2.7.0.
What can I use instead of mcp-audit?
Servers from other publishers that do the same job: RadioChron MCP server, Solsnap MCP server and Moltline Code Review MCP server. Compare all mcp-audit alternatives.

Alternatives to mcp-audit

Same job from other publishers: the closest match first, then the best rated.

All mcp-audit alternatives →
  • RadioChron
    Local-first Wi-Fi incident diagnostics with native BLE scan, history, and risk evidence.
    A
  • Solsnap
    Solana token/wallet rug-risk scoring. Free scan; $2 SOL unlocks full wallet report. No signup.
    B
  • Moltline Code Review
    Risk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account.
    B
  • DNS Doctor
    Scan, fix, verify and monitor DNS: SPF, DMARC, DKIM, propagation, health, expiry. Validated fixes.
    A
  • OpenQR
    Generate, edit and track dynamic (editable) QR codes with scan analytics. Hosted MCP and REST API.
    A
mcp-audit vs RadioChronmcp-audit vs Solsnapmcp-audit vs Moltline Code Review

More from saagpatel →