Audits Model Context Protocol servers against the OWASP MCP Top 10 to identify security vulnerabilities and assign safety grades.
Also known as CodingSelim/mcp-scan, owasp-mcp-scan
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.2.1
- Last commit
- Oct 10, 2026
- License
- MIT
What is scan MCP?
scan audits Model Context Protocol servers against the OWASP MCP Top 10 to identify security vulnerabilities and assign safety grades.
Summary generated from the project's README
About scan MCP server
Auditing Model Context Protocol servers for security vulnerabilities is the primary function of mcp-scan. This tool evaluates live servers against the OWASP MCP Top 10 to identify risks like command injection, path traversal, and secret exposure. It assigns a safety grade from A to F based on its findings, helping developers verify the safety of a server before integrating it into their workflows.
Users can run the scanner via a command line interface using npx, targeting local stdio servers or remote HTTP endpoints. It is designed to be passive and read-only, meaning it analyzes advertised capabilities without ever invoking tools or sending exploits, making it safe for production environments. The scanner provides results in console, JSON, or SARIF formats for integration into CI/CD pipelines.
Beyond individual tool checks, the scanner uses a specialized toxic-flow analysis to detect the lethal trifecta of reading private data, ingesting untrusted content, and exfiltrating information. It can also be installed as an MCP server itself, allowing AI clients like Claude Desktop, Cursor, or Windsurf to perform on-demand security audits using the scan_mcp_server tool.
What you can do with it
- 1Audit a local serverA developer can run a security check on a local filesystem MCP server before connecting it to an agent.
- 2Automate security in CI/CDTeams can gate their deployment pipelines by failing builds if a server receives a high-risk security grade.
- 3Detect complex data exfiltrationSecurity researchers can identify servers that combine data reading and exfiltration capabilities through the toxic-flow check.
Written from the project's README. Every use case is checked against a quote from it.
How to install scan MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall scan MCP in Claude Code
$ claude mcp add mcp-scan -- npx -y owasp-mcp-scanInstall scan MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp-scan": {
"command": "npx",
"args": [
"-y",
"owasp-mcp-scan"
]
}
}
}Install scan MCP in VS Code
.vscode/mcp.json
{
"servers": {
"mcp-scan": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"owasp-mcp-scan"
]
}
}
}Install scan MCP in VS Code CLI
$ code --add-mcp '{"name":"mcp-scan","type":"stdio","command":"npx","args":["-y","owasp-mcp-scan"]}'Install scan MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"mcp-scan": {
"command": "npx",
"args": [
"-y",
"owasp-mcp-scan"
]
}
}
}Install scan MCP in Codex
$ codex mcp add mcp-scan -- npx -y owasp-mcp-scanInstall scan MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp-scan] command = "npx" args = ["-y", "owasp-mcp-scan"]
Install scan MCP in Gemini CLI
$ gemini mcp add -s user mcp-scan npx -- -y owasp-mcp-scanInstall scan MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp-scan": {
"command": "npx",
"args": [
"-y",
"owasp-mcp-scan"
]
}
}
}Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablecodingselim/mcp-scan is public and reachablegithub.com/codingselim/mcp-scan ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-10github.com/codingselim/mcp-scan ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from owasp-mcp-scanPass
- No critical advisory in the package or its dependencies100 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHub🛡️ mcp-scan
Passive security scanner for Model Context Protocol servers. Point it at any running MCP server; it audits the live server against the OWASP MCP Top 10 and grades it A–F. Read-only, so it is safe to run against production.
npx owasp-mcp-scan --stdio "npx -y @modelcontextprotocol/server-filesystem /tmp"
I ran it against the 12 most-installed MCP servers. 9 of them failed. No install, no config, no exploiting anything.
Why
MCP tool descriptions are fed straight into your model's context, and most public servers were never security-reviewed. A bad one can hide instructions in a description, expose a raw-shell tool, or leak a key; and your agent acts on it. Endor Labs found 82% of servers prone to path traversal, 34% to command injection.
mcp-scan is the gut-check before you wire a server in. It's passive: it reads advertised capabilities and analyzes them statically, never invoking tools, so it's safe against production servers.
How it works
- Connects to the server over stdio or Streamable HTTP and enumerates every advertised tool, prompt, and resource.
- Runs 12 static checks across that surface: secrets, injection, SSRF, path traversal, tool poisoning, excessive scope, and more.
toxic-flowreasons across the whole toolset for the lethal trifecta (reads private data + ingests untrusted content + can exfiltrate), the shape single-tool scanners miss.- Scores 0-100 and grades A-F (any critical forces F). Emits console, JSON, or SARIF.
It never calls a tool, never fuzzes, and never sends an exploit. The worst it does is read what the server already tells everyone.
Real findings on real servers
12 popular npm servers, actual output (snapshot 2026-07-11, full benchmark):
| Server | Tools | Grade | 🔴 | 🟠 | 🟡 | Notable |
|---|---|---|---|---|---|---|
firecrawl-mcp |
26 | F | 2 | 11 | 1 | lethal trifecta (MCP10) + code exec (MCP05) |
@modelcontextprotocol/server-filesystem |
14 | F | 0 | 1 | 11 | unconstrained path params (MCP01) |
@modelcontextprotocol/server-puppeteer |
7 | F | 1 | 2 | 0 | script param executes JS (MCP05) |
tavily-mcp |
5 | F | 0 | 3 | 1 | untrusted-input + exfiltration (MCP10) |
@modelcontextprotocol/server-memory |
9 | F | 0 | 3 | 0 | delete_* tools, no confirmation (MCP02) |
@modelcontextprotocol/server-github |
26 | D | 0 | 0 | 2 | state-changing tools (MCP02) |
@modelcontextprotocol/server-slack |
8 | C | 0 | 1 | 0 | reads + posts = data + exfil (MCP10) |
@modelcontextprotocol/server-everything |
13 | A | 0 | 0 | 0 | clean ✓ |
@kazuph/mcp-fetch |
1 | A | 0 | 0 | 0 | clean ✓ |
9 of 12 flagged, 3 clean, every row audited finding-by-finding, false positives stripped rather than padded. Reproduce any row yourself:
npx owasp-mcp-scan --stdio "npx -y firecrawl-mcp" # F: lethal trifecta + code exec
npx owasp-mcp-scan --stdio "npx -y @modelcontextprotocol/server-everything" # A: clean
Use it
CLI
npx owasp-mcp-scan --stdio "<command>" # local stdio server
npx owasp-mcp-scan --url https://host/mcp --header "Authorization: Bearer $TOKEN"
npx owasp-mcp-scan --config ~/.cursor/mcp.json --format sarif --output mcp.sarif
As an MCP server, let your agent scan servers on demand ("scan this MCP server before I add it"). Add to any client; this mcpServers shape works in Claude Code, Claude Desktop, Cursor, Windsurf, VS Code, and Gemini CLI:
{ "mcpServers": { "mcp-scan": { "command": "npx", "args": ["-y", "owasp-mcp-scan", "--serve"] } } }
OpenAI Codex (~/.codex/config.toml):
[mcp_servers.mcp-scan]
command = "npx"
args = ["-y", "owasp-mcp-scan", "--serve"]
Exposes two tools: scan_mcp_server (audit a stdio/HTTP target) and list_checks.
Claude Code plugin
/plugin marketplace add CodingSelim/mcp-scan
/plugin install mcp-scan@mcp-scan
Also on the official MCP registry as io.github.CodingSelim/mcp-scan. Publishing steps: PUBLISHING.md.
What it checks
Full OWASP MCP Top 10 (2025) coverage, 12 checks:
| Check | OWASP | Catches |
|---|---|---|
secret-exposure |
MCP01 | AWS / OpenAI / Anthropic / GitHub / GitLab / Stripe / SendGrid / npm / HF / DB URIs / JWT / private keys in advertised text |
transport |
MCP01 | Plaintext http:// to a non-loopback host |
path-traversal |
MCP01 | file:///{path} templates and unconstrained path params |
excessive-scope |
MCP02 | Destructive tools (delete, drop, transfer) with no confirmation |
tool-poisoning |
MCP03 | Instruction overrides, hidden exfiltration directives, zero-width / Unicode-tag smuggling |
tool-shadowing |
MCP03 / MCP09 | Duplicate tool-name collisions and "call me first" precedence injection |
supply-chain |
MCP04 / MCP09 | Unpinned/placeholder versions and homoglyph server names |
command-injection |
MCP05 | Unconstrained command / shell / code params, raw SQL, advertised execution |
ssrf |
MCP05 | Arbitrary url / host params with no allowlist |
tool-poisoning (dynamic) |
MCP06 | Injection in resource contents and server instructions |
authn |
MCP07 | HTTP servers that complete an unauthenticated handshake |
telemetry |
MCP08 | High-impact tools with no audit trail (advisory, unscored) |
toxic-flow |
MCP10 | Lethal trifecta: one server that reads private data, ingests untrusted content, and can exfiltrate |
toxic-flow is the standout, it reasons across the whole toolset, catching the GitHub-MCP / email-agent injection shape that per-tool checks miss.
Output & CI
console (default) · json · sarif (GitHub Code Scanning). Exit code is non-zero at/above --fail-on (default high), so it gates CI:
- run: npx owasp-mcp-scan --url ${{ secrets.MCP_URL }} --format sarif --output mcp.sarif
- uses: github/codeql-action/upload-sarif@v3
with: { sarif_file: mcp.sarif }
Limitations (read these)
- Static analysis can't see runtime sandboxing, a server that safely confines paths still flags them. Verify against actual enforcement.
- Auth and transport checks apply to HTTP targets only.
- Heuristics favor recall, so triage findings in context. When a rule is tightened to kill a false positive, a test pins the intended behavior.
- Scanning a stdio target spawns that command, so run it only on servers you trust.
Develop
npm install && npm run build && npm test # 48 tests, incl. live end-to-end fixture scans
Checks are pure and isolated (src/checks/), reusing detectors in src/detectors/. See CONTRIBUTING.md.
References
OWASP MCP Top 10 · MCP Security Cheat Sheet · Vulnerable MCP Project · MCPTox
MIT © CodingSelim
scan MCP questions
How do I add scan MCP to Claude Code?
Run claude mcp add mcp-scan -- npx -y owasp-mcp-scan in your terminal. Add --scope user to make it available in every project.
How do I add scan MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Is it safe to run against production servers?
Yes, it is a passive, read-only scanner that analyzes advertised capabilities without invoking tools.
What does the scanner check for?
It performs 12 static checks including secret exposure, injection, SSRF, path traversal, and the 'toxic-flow' trifecta.