Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

mcp-audit

PYPI · MCP-AUDITS · SCANNED SEP 20

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

Available components

0 this week 77 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security94
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs a script at install time (build_backend) that we could not recognise. It may be perfectly ordinary, but we do not read the published tarball, so we cannot say what it does. View diagnostics → Partial
  • 1 of 38 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency35
Schema Quality & AI Usability72
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 662 tokens (~50/item across 13 items; 13 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
  • Stability observed for 28 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the mcp-audit server?

mcp-audit runs locally as a PyPI package, launched with uvx mcp-audits. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · mcp-audits

# add to Claude Code
claude mcp add saagpatel-mcp-audit -- uvx mcp-audits
// .cursor/mcp.json
{
  "mcpServers": {
    "saagpatel-mcp-audit": {
      "command": "uvx",
      "args": [
        "mcp-audits"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "saagpatel-mcp-audit": {
      "command": "uvx",
      "args": [
        "mcp-audits"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add saagpatel-mcp-audit -- uvx mcp-audits
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "saagpatel-mcp-audit": {
      "type": "local",
      "command": [
        "uvx",
        "mcp-audits"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add saagpatel-mcp-audit --command uvx --arg mcp-audits
# ~/.hermes/config.yaml
mcp_servers:
  saagpatel-mcp-audit:
    command: "uvx"
    args: ["mcp-audits"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "saagpatel-mcp-audit": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "mcp-audits"
      ]
    }
  }
}
# add to Vellum
assistant mcp add saagpatel-mcp-audit -t stdio -c uvx -a mcp-audits
// mcp.json
{
  "mcpServers": {
    "saagpatel-mcp-audit": {
      "command": "uvx",
      "args": [
        "mcp-audits"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 15 Sept 26 +16
    • Malware scan: unverified → pass security
    • Stability: 0.97 → pass security
  • 14 Sept 26 −15
    • Malware scan: pass → unverified security
  • 13 Sept 26 +16
    • Malware scan: unverified → pass security
  • 11 Sept 26 −14
    • Malware scan: pass → unverified security
  • 8 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/mcp-audits@2.7.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend unreviewed mcp_audit_build_backend

Background: Why install scripts are a supply-chain risk →

Dependencies 38 packages
Packages resolved 38
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 13 exposed · ~641 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_server ~27

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

NameTypeReqDescription
namestringyes
NameTypeReqDescription
resultstringyes

No examples provided.

get_artifact_verify_findings ~91

Return byte-level artifact drift vs the pin baseline. Returns JSON `{findings, warnings}`. NETWORK: downloads npm/PyPI artifact bytes and hashes them. Requires a pin baseline captured with `mcp-audit pin --download-artifacts`; without one `findings` is empty and `warnings` explains why. Does not connect to the audited MCP servers (skip_connect).

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

get_escalation_findings ~72

Return capability-escalation findings vs the pin baseline. Returns JSON `{findings, warnings}`. Requires a pin baseline (run `mcp-audit pin` first); without pins `findings` is empty and `warnings` carries a `pin_baseline_missing` entry explaining why.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

get_high_risk_servers ~27

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

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

get_injection_findings ~29

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

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

get_integrity_findings ~76

Return launch-artifact integrity drift vs the pin baseline. Returns JSON `{findings, warnings}`. Requires a pin baseline that captured artifact hashes (run `mcp-audit pin` first); without one `findings` is empty and `warnings` explains why. Offline — only on-disk bytes are hashed.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

get_package_verify_findings ~87

Return registry package-hash drift vs the pin baseline. Returns JSON `{findings, warnings}`. NETWORK: contacts the npm/PyPI registry. Requires a pin baseline captured with `mcp-audit pin --verify-artifacts`; without one `findings` is empty and `warnings` explains why. Does not connect to the audited MCP servers (skip_connect).

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

get_provenance_findings ~84

Return launch-config provenance drift vs the pin baseline. Returns JSON `{findings, warnings}`. Requires a pin baseline with a config snapshot (run `mcp-audit pin` first); without one `findings` is empty and `warnings` carries a `pin_baseline_missing` or `pin_baseline_stale` entry explaining why.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

get_shadowing_findings ~30

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

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

get_ssrf_findings ~29

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

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

get_trifecta_findings ~33

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

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

list_discovered_servers ~24

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

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

scan_mcp_servers ~32

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

NameTypeReqDescription
skip_connectboolean
NameTypeReqDescription
resultstringyes

No examples provided.

Common questions

What is the mcp-audit server?

mcp-audit is listed in the public MCP registry as io.github.saagpatel/mcp-audit. Scan, enumerate, and risk-score every MCP server configured on your machine. This page covers its PyPI package (mcp-audits).

Is the mcp-audit server safe to use?

mcp-audit scores 77 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the mcp-audit server expose?

mcp-audit exposes 13 tools: scan_mcp_servers, get_high_risk_servers, check_server, get_injection_findings, get_ssrf_findings, and 8 more. Their descriptions and schemas cost roughly 641 tokens of context every time the server is loaded.

Is the mcp-audit server still maintained?

mcp-audit is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.