MCPAuditBLOCK
Audit all locally configured MCP servers for permission risks, prompt injection threats, and schema drift
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://pypi.org/project/mcp-audits/) [](https://pypi.org/project/mcp-audits/) [](https://github.com/saagpatel/MCPAudit/actions/workflows/ci.yml) [](https://github.com/saagpatel/MCPAudit/actions/workflows/codeql.yml) [](LICENSE)
See what your AI tools' MCP servers can reach.
MCPAudit reviews MCP server configuration and, when asked, lists the tools a server exposes. It highlights declared capabilities, instruction-shaped text heuristics, and changes from a saved pin so you can decide what to investigate. Findings are review signals: a high score means broader capability exposure, not that a server is malicious or unsafe.
[!IMPORTANT] The package ismcp-audits; the command ismcp-audit. The default check is static.check --connectand legacyscancan start configured local programs or contact configured endpoints. Package verification, downloads, and LLM analysis are separate opt-in operations. MCPAudit does not edit configs, and reports environment variable key names, never their values. Review generated reports before sharing them.
Try it
mcp-audit # static review of supported configs mcp-audit check --config ./mcp.json # review this file only; no connections mcp-audit demo # see a bundled synthetic example mcp-audit explain MCP007
134a36f1934bOBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-audits -- uvx mcp-audits==2.9.0 serve
Exposed tools (5)
3 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
execute_command | write | Run a shell command and return its output. |
ping | read | Return a JSON object as text. |
read_file | read | Read a file from disk at the given path. |
status | read | 🙂 |
write_file | write | Write content to a file at the given path. |
Trust audit
BLOCKgrade F · trust 41/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (11 observation(s))
- Network
- declared (9 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- pinned
- Secrets in source
- found
Findings (25)
raw: Any = yaml.load(data.decode("utf-8"), Loader=_NoAliasSafeLoader) # noqa: S506 - loader subclasses SafeLoaderhome / ".netrc",
".netrc",
"id_ecdsa",
"id_ed25519",
"id_rsa",
"--insecure",
REDIRECT = "http://127.0.0.1:43119/callback"
REDIRECT_OTHER = "http://127.0.0.1:43119/other"
REDIRECT_EPHEMERAL = "http://127.0.0.1:49152/callback"
sys.settrace(trace)
sys.settrace(previous)
"AKIAABCDEFGHIJKLMNOP",
"AKIAABCDEFGHIJKLMNOP",
"AKIAABCDEFGHIJKLMNOP",
"text": "postgresql://app:p@[email protected]:5432/app",
"text": "mysql://app:p@[email protected]:5432/app",
"text": "redis://app:p@[email protected]:5432/app",
secret = "abcdefghijklmnopqrstuvwxyz0123456789"
secret = "abcdefghijklmnopqrstuvwxyz0123456789"
"ghp_SECRETVALUE1234567890abcdefABCDEF12",
"ghp_abcdefghijklmnopqrstuvwxyz0123456789",
("ghp_abcdefghijklmnopqrstuvwxyz0123456789", "vwxyz"),"ghp_SECRETVALUE1234567890abcdefABCDEF12",
"xoxb-SLACKSECRET-123456",
Gates applied: no_behavioural_pass.
134a36f1934bfull audit observations/trust-audit/mcp-server/saagpatel__mcpaudit.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 134a36f1934b | BLOCK | F | 41 | first audit |
Questions
What is the MCPAudit MCP server?
Audit all locally configured MCP servers for permission risks, prompt injection threats, and schema drift
What tools does MCPAudit expose?
5 in total: 3 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is MCPAudit safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (41/100) and found 7 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does MCPAudit need?
It reads ANTHROPIC_API_KEY and MCP_AUDIT_PIN_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does MCPAudit run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as mcp-audits.
How current is this page?
The grade is for one exact copy of the source (134a36f1934b), read on 2026-10-11. The repository is watched and re-audited when it changes.