Open-source MCP and AI agent security scanner
Exposure management for your AI agent stack.
Your developers have installed MCP servers and agent tools that your existing scanners don't inventory. mcp-audit discovers them across 10 AI clients, matches them against published advisories, and shows what each one can reach. It runs on your machine: a default scan reads files, never runs them, and makes no network calls.
pip install mcp-audit-scannermcp-audit scan --project . --include-agent-filesThe package is mcp-audit-scanner; the command is mcp-audit. It needs Python 3.11 or later. Standalone binaries for macOS (Apple silicon), macOS (Intel), Linux (x86-64) and Windows (x86-64) are on GitHub Releases.
Install and run For security teams
Current release: 0.32.0, released 2026-11-16. Apache 2.0, every feature free.
What it reads in a repository
your-repo/- Can start a program:
.mcp.json - Can start a program:
opencode.json - Can start a program:
opencode.jsonc - Read as instructions:
CLAUDE.md - Read as instructions:
CLAUDE.local.md - Read as instructions:
AGENTS.md - Read as instructions:
AGENTS.override.md - Read as instructions:
SOUL.md - Read as instructions:
USER.md - Read as instructions:
MEMORY.md - Read as instructions:
HEARTBEAT.md .agents/- Read as instructions:
skills/**/SKILL.md
- Read as instructions:
.amazonq/- Can start a program:
mcp.json
- Can start a program:
.claude/- Can start a program:
settings.json - Can start a program:
settings.local.json - Can start a program:
scheduled_tasks.json - Can start a program:
workflows - Read as instructions:
commands/*.md - Read as instructions:
skills/**/SKILL.md - Read as instructions:
CLAUDE.md - Read as instructions:
agents/**/*.md - Read as instructions:
rules/**/*.md - Read as instructions:
AGENTS.md
- Can start a program:
.codex/- Can start a program:
config.toml - Can start a program:
hooks.json - Read as instructions:
skills/**/SKILL.md
- Can start a program:
.cursor/- Can start a program:
mcp.json - Can start a program:
settings.json - Read as instructions:
skills/**/SKILL.md - Read as instructions:
rules/*.mdc
- Can start a program:
.gemini/- Can start a program:
settings.json - Can start a program:
.env - Read as instructions:
skills/**/SKILL.md
- Can start a program:
.github/- Read as instructions:
skills/**/SKILL.md - Read as instructions:
copilot-instructions.md - Read as instructions:
instructions/*.instructions.md - Read as instructions:
prompts/*.prompt.md - Can start a program:
workflows/*.yml
- Read as instructions:
.mcphub/- Can start a program:
servers.json
- Can start a program:
.vscode/- Can start a program:
mcp.json - Can start a program:
tasks.json - Can start a program:
settings.json
- Can start a program:
can start a program, on your machine or in CI is read by the agent as instructions
Taken from the scanner's own discovery lists. The tags are the finding families checked in each file.
Security properties you can check
Each one links to the evidence in the source repository.
- Offline by designscan and check make no network calls unless you add a network flag. fix, sbom and lock look up package versions online by default; --offline stops that.
- Reads, never runsScanned files are parsed, never executed: no servers started, no scripts, no git.
- No telemetryNo usage data, no crash reports and no account to create.
- Signed advisory feedOSV 1.6.0 records signed with the project's minisign key, published weekly.
- Attested releasesPyPI Trusted Publishing with PEP 740 attestations, and a CycloneDX SBOM for every binary.
- 10,382 automated testsThe suite runs on Linux, macOS and Windows with Python 3.11 and 3.12 on every push and pull request.
- OWASP MCP Top 10Findings map to 10 of 10 categories, and CI checks the mapping on every change.
- Measured in publicPoisoning recall is 75% on a public benchmark and none of 46 findings on the top-100 npm servers was real. GAPS.md lists what we miss.
What it checks
225 finding IDs, grouped by what mcp-audit reads. The catalog shows what each one flags, its severity and its OWASP MCP Top 10 category.
- Repository files that run code8 checks
Files a cloned repository can use to start programs when you open or trust it: project MCP configs, VS Code tasks that run when the folder opens, auto-run files for Gemini CLI, Codex and Claude Code, git settings and hooks that run a program when an agent runs git, and symlinks that point somewhere else.
TRUST- AI agents in CI workflows3 checks
GitHub Actions workflows where an AI coding agent step reads text a stranger can write, such as an issue or a comment, while it holds secrets, write access and tools that can run commands. Workflow files are parsed as data and never run.
WORKFLOW- Coding-agent settings and permission rules39 checks
Claude Code settings that skip permission prompts, approve every project server, or pre-approve commands that can write or reach the network. Permission rules that Claude Code ignores or that are not a boundary. Sandbox settings a repository can loosen. Hook commands that reach the network or touch agent config files. Servers that your organisation's managed Claude Code policy would block, policy set only where the user can change it, safety settings that got weaker since the last scan, editor extension allowlists that are not enforced, and credential files a session can read without a prompt.
CFHYGEXTPOLGUARDHARNESSHOOKMANAGEDPERMREACHSANDBOX- Agent instruction files, skills and subagents22 checks
Text the agent reads as instructions: Claude Code commands, CLAUDE.md and AGENTS.md files, the files they import, Cursor rules, and Copilot instruction and prompt files. mcp-audit looks for injected orders, hidden characters, outside links and heartbeat files that hide a step. It reads every file in a Claude Code skill, not only SKILL.md, for install steps that run remote code. It reads subagent definitions for looser permissions, hooks and their own MCP servers, and reports when an instruction file changed since the last scan.
AGENTINSTRMEMSKILL- Claude Code plugins and mods10 checks
Installed plugins whose recorded version or checkout does not match their marketplace pin, or that follow an unpinned branch, and mods that can approve tool calls, read secrets and send data out, change what Claude reads, or start programs. Mods are read, never run.
MODPLUGIN- MCP server configs20 checks
How each configured server is launched and reached: secrets written into the config, plain-HTTP endpoints, sudo launches, unpinned package fetches, remote servers with no authentication, and config files other users can read or write. If a check crashes on a server, the scan reports it instead of passing that server as clean.
AUTHCFHYGCREDSCANTRANSPORT- Tool descriptions29 checks
Orders hidden in the descriptions an agent reads: exfiltration instructions, prompt-format injection, behaviour overrides, invisible Unicode and lookalike characters. With
--connectit reads live tool lists, flags a tool name claimed by two servers, and flags descriptions that name another server's tool or tell the agent to rewrite other tools' arguments. It also flags a tool marked read-only whose own inputs run commands or write.ANNOTCOLLIDEDELEGPOISON- Dangerous combinations of servers12 checks
Servers that are harmless alone but together let an injected prompt read data and send it out, including by posting to GitHub, Slack or Jira, or write a file another server can run.
killchainranks the changes that break the most paths.INTEGTOXIC- Packages and supply chain18 checks
Lookalike package names, unscoped twins of known servers, packages listed as malicious in OSV, recorded advisories for a package, deprecated versions, and missing or mismatched Sigstore provenance. Provenance, hash and CVE checks use the network, so they are opt-in.
ATTESTSCVULN- Approved servers and drift23 checks
What changed since you approved a setup: servers added, removed or launched differently, a hand-edited lock file, and, with
--connect, tools added or changed since approval. A server started throughmcp-audit runis checked against the lock as it launches and while it runs, and a policy can require every server to be wrapped that way.BLLOCKRUGPULLRUNWRAP- Community rules41 checks
YAML rules in an open format that run on every scan: risky launch commands, inline code, shell metacharacters, sensitive variable names, sampling, and more.
COMMSTDIO
Two ways in
The same scanner, from one developer's laptop to every repository and machine in an organisation. A plain scan uses no network, and the commands that do are listed on the security page.
For developers
Check a server before you install it
mcp-audit vet @modelcontextprotocol/server-filesystemPublisher, recorded advisories, capabilities and lookalike names, offline.
Scan a cloned repo before your editor trusts it
mcp-audit scan --project . --include-agent-filesProject MCP configs, agent settings, editor auto-run files and instruction files.
Grade your setup and apply safe fixes
mcp-audit checkThe top findings with a fix for each.
mcp-audit fixshows the safe fixes as a diff;--applywrites them.See findings as you work
Use the editor extension for VS Code and Cursor and pre-commit hooks.
For security teams
Gate pull requests in CI
The GitHub Action uploads SARIF to code scanning, fails at the severity you choose and verifies
mcp-lock.jsonagainst the servers you approved.Enforce what is allowed
A
.mcp-audit-policy.ymlfile sets approved servers, a minimum score, transport rules and finding tolerances. Scans find it on their own.See every machine
mcp-audit shadowlists servers nobody approved;mcp-audit mergeturns many machines' scans into one fleet report.Keep evidence
CycloneDX SBOMs, Sigstore-signed snapshots you can replay later, and a PDF report from
scan --report pdf.Feed your vulnerability management
SARIF, Nucleus Security FlexConnect through
push-nucleus, and NDJSON streams for a SIEM.
Fits the tools you already run
Open formats in, open formats out. No agent to deploy and no service to connect.
- GitHub code scanningSARIF output with the OWASP MCP Top 10 taxonomy.
- GitHub ActionsA composite Action, pinned to
v0.32.0, that scans, uploads SARIF and gates the job. - pre-commit2 hooks: a scan, and lock verification that blocks drift.
- VS Code and CursorAn Open VSX extension that shows findings inline as you edit.
- Nucleus SecurityFlexConnect output and a direct push for vulnerability management programs.
- CycloneDXSBOMs and AI/ML-BOM snapshots, optionally signed with Sigstore.
- OSVA signed advisory feed with a bundle osv-scanner can read.
- SIEMNDJSON from
snapshot --streamandshadow --continuous, with Splunk and Sentinel recipes.
Look up a server before you install it
The registry lists 56 MCP server packages (45 npm, 11 PyPI). 26 have a verified publisher. 15 have recorded advisories, and 5 of those have at least one with no fix. Each package has a page and a JSON verdict.
Browse the registry Add your server
Why remote servers matter
- A measurement study found that 40.55% of 7,973 live remote MCP servers expose tools without authentication (arXiv 2605.22333).
AUTH-001flags a remote server in your config that sends no credentials. - Censys counted 12,520 MCP services reachable from the internet (MCP Servers on the Internet).
We publish our false positives
We scanned the 100 most-downloaded MCP servers on npm and published every aggregate number. mcp-audit's poisoning rules raised 661 findings, and none of them was a real attack. 488 of them came from one rule, POISON-060, which the data shows misfiring.
Recent releases
The lead lines of the newest entries in the changelog.
0.32.0 2026-11-16
- CRED-006: a Claude Code settings file that a container image or npm package will ship
- Known-malicious packages that npx ran on this machine (SC-011, CRITICAL; STORY-0158)
- Skills in every agent's skills directory, not only Claude Code's
0.31.0 2026-11-16
agent-files scannow checks AGENTS.md, CLAUDE.md, GEMINI.md and .cursorrules left in Downloads and Desktop (MEM-007, MEDIUM), and flags instruction files that tell the agent to edit a machine-wide agent config, change the model base URL, or turn approvals off (MEM-008; HIGH outside a git repository, MEDIUM inside one)- HOOK-004 / HOOK-005: guard hooks that will never run, and Cursor
hooks.jsonfiles - CRED-005: a secret in a permission rule that git history still holds
- Registry: this week's malicious MCP packages, the MCP Inspector RCE, and
affectedfor CVE-2026-88968
0.30.0 2026-11-11
mcp-audit run: launch an MCP server through mcp-auditmcp-audit runcan refuse a server that isn't approvedmcp-audit runchecks the tools a server offers while it runsmcp-audit runalso checks live tool text for poisoning
Open source, with nothing held back
mcp-audit is Apache 2.0. Every command ships in the free package: no license keys, no seats, no account and no paid tier. The source, the test suite, the detection sources and the known gaps are all public.
The community rule format is open. Accepted rules are credited in the changelog and in the contributors list.