Performs security audits on MCP servers and codebases to identify OWASP MCP Top 10 vulnerabilities and provides A–F grading.
Also known as GuardBee/guardbee-mcp, @guardbee/mcp-owasp-scan
- Stars
- 2
- Tools
- 5
- Downloads, 30 days
- 2,683
- Latest version
- 0.6.0
- Last commit
- Nov 12, 2026
- License
- MIT
What is owasp-scan MCP?
owasp-scan performs security audits on MCP servers and codebases to identify OWASP MCP Top 10 vulnerabilities and provides A–F grading. It exposes 5 tools, such as live, owasp_scan_path, owasp_scan_live.
Summary generated from the project's README
About owasp-scan MCP server
Security auditors can identify vulnerabilities in MCP servers and codebases using this tool to ensure compliance with the OWASP MCP Top 10. It provides an A–F grade based on the severity of findings, ranging from no findings for an A to lethal trifectas for an F. The server supports three distinct modes: scanning local files or directories, performing live audits on running servers via HTTP or stdio, and analyzing offline JSON tool catalogs.
Developers can integrate this into their workflow using the CLI or as an MCP server within environments like Claude Desktop, Cursor, or VS Code. The scanner performs deep analysis on TypeScript, JavaScript, Python, Go, and Rust codebases, while providing pattern-based checks for other languages. It can output results in text, JSON, or SARIF formats for GitHub code scanning integration. Users can opt-in to additional checks for supply chain security and prompt injection via specific flags.
What you can do with it
- 1Audit local source codeRun a static security scan on a repository to find vulnerabilities in tool definitions and handler sinks.
- 2Automate CI security gatesFail a continuous integration build if the security scan detects high or critical vulnerabilities.
Written from the project's README. Every use case is checked against a quote from it.
How to install owasp-scan MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall owasp-scan MCP in Claude Code
$ claude mcp add owasp-scan -- npx -y @guardbee/mcp-owasp-scanInstall owasp-scan MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"owasp-scan": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-owasp-scan"
]
}
}
}Install owasp-scan MCP in VS Code
.vscode/mcp.json
{
"servers": {
"owasp-scan": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-owasp-scan"
]
}
}
}Install owasp-scan MCP in VS Code CLI
$ code --add-mcp '{"name":"owasp-scan","type":"stdio","command":"npx","args":["-y","@guardbee/mcp-owasp-scan"]}'Install owasp-scan MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"owasp-scan": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-owasp-scan"
]
}
}
}Install owasp-scan MCP in Codex
$ codex mcp add owasp-scan -- npx -y @guardbee/mcp-owasp-scanInstall owasp-scan MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.owasp-scan] command = "npx" args = ["-y", "@guardbee/mcp-owasp-scan"]
Install owasp-scan MCP in Gemini CLI
$ gemini mcp add -s user owasp-scan npx -- -y @guardbee/mcp-owasp-scanInstall owasp-scan MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"owasp-scan": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-owasp-scan"
]
}
}
}owasp-scan MCP tools 5
Detected from the READMEliveowasp_scan_pathowasp_scan_liveowasp_scan_cataloglist_owasp_coverage
| live | — | |
| owasp_scan_path | — | |
| owasp_scan_live | — | |
| owasp_scan_catalog | — | |
| list_owasp_coverage | — |
Automated checks
Ran Nov 13, 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 reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHub@guardbee/mcp-owasp-scan
🇬🇧 English | 🇹🇷 Türkçe | 🇨🇳 中文 | 🇯🇵 日本語 | 🇰🇷 한국어 | 🇧🇷 Português | 🇪🇸 Español | 🇩🇪 Deutsch
One CLI and MCP server for a unified OWASP MCP Top 10 check. It runs seven GuardBee auditors over a codebase in one pass, or grades a live MCP server's tool list, and reports every finding under its OWASP id with an A–F grade. Output as text, JSON or SARIF for GitHub code scanning.
Telemetry is off by default. With
GUARDBEE_TELEMETRY=1it sends the server, tool, success, duration and short parameter values such as a file path; longer strings and fields likecontent,tokenorpasswordare replaced with a placeholder. See@guardbee/mcp-telemetry.
Quick start
# Static scan of a repository, fail CI on high or critical findings
npx @guardbee/mcp-owasp-scan scan ./src --format=sarif --fail-on=high > owasp.sarif
# Connect to a running MCP server and grade its tools
npx @guardbee/mcp-owasp-scan live --url=https://mcp.example.com/mcp
npx @guardbee/mcp-owasp-scan live --stdio=npx --arg=-y --arg=@modelcontextprotocol/server-filesystem --arg=.
# Grade a saved tools/list response
npx @guardbee/mcp-owasp-scan catalog ./tools.json --format=json
As an MCP server (Claude Desktop, Cursor, VS Code):
{
"mcpServers": {
"guardbee-owasp-scan": {
"command": "npx",
"args": ["-y", "@guardbee/mcp-owasp-scan"]
}
}
}
Modes
| Mode | Input | What runs |
|---|---|---|
scan <path> |
A file or directory | secret-scanner, mcp-server-auditor, oauth-auditor, audit-gap-auditor, context-oversharing-auditor, toxic-flow-auditor, tool-poisoning-scanner |
live |
--url=<streamable HTTP URL> or --stdio=<command> with --arg=… |
Connects, calls tools/list, then toxic-flow-auditor and tool-poisoning-scanner |
catalog <tools.json> |
A tools/list dump ({ "tools": [...] } or a bare array) |
Same checks as live, offline |
scan reads TypeScript/JavaScript, Python (FastMCP, official SDK, low-level server), Go (official go-sdk, mark3labs/mcp-go) and Rust (rmcp #[tool] / #[tool_router]) MCP servers in full: tool definitions, handler sinks and OAuth rules. Other languages (Java, Kotlin, C#, Ruby, PHP, Swift) get the language-neutral rules only (secrets, URLs, config). The report's coverage lists every source file with its language, that depth (full or patterns) and the number of tool definitions found, plus a per-language summary (languages: in text output), so a file the scan could not read deeply is visible rather than silently passing.
--discover-shadow adds an MCP09 check to scan: it inventories the MCP servers configured on this machine (Cursor, Claude Desktop, Windsurf, VS Code) through mcp-config-auditor, and --allowlist=<path> marks the approved ones.
OWASP MCP Top 10 coverage
| ID | Risk | Covered by |
|---|---|---|
| MCP01 | Token / credential exposure | secret-scanner, mcp-server-auditor |
| MCP02 | Privilege / excessive agency | mcp-server-auditor |
| MCP03 | Tool poisoning / rug pull surface | tool-poisoning-scanner (scan, live, catalog) |
| MCP04 | Supply chain | Opt-in: --with-supply-chain / withSupplyChain runs mcp-dependency-auditor (OSV) and mcp-slopsquat-scanner (needs the network). Listed in notRun when off |
| MCP05 | Command / code injection via tools | mcp-server-auditor |
| MCP06 | Prompt / context injection | Opt-in: --with-content / withContent runs mcp-prompt-injection-scanner on content under the path. Listed in notRun when off |
| MCP07 | Auth / OAuth misconfiguration | oauth-auditor |
| MCP08 | Lack of audit and telemetry | audit-gap-auditor |
| MCP09 | Shadow MCP servers | mcp-config-auditor (--discover-shadow) |
| MCP10 | Toxic flows / context oversharing | toxic-flow-auditor, context-oversharing-auditor (scan, live, catalog) |
Grade
| Grade | When |
|---|---|
| F | A lethal trifecta: one agent can read untrusted content, reach sensitive data and send data out |
| D | Any critical finding |
| C | Any high finding |
| B | Only medium or low findings |
| A | No findings |
CLI options
| Option | Default | Meaning |
|---|---|---|
--format=text|json|sarif |
text |
Report format. SARIF uploads to GitHub code scanning |
--fail-on=any|critical|high|medium|none |
any |
Exit 1 when a finding at or above this severity exists |
--max-files=<n> |
5000 |
Stop a path scan after this many files |
--discover-shadow |
off | Add the MCP09 host inventory to scan |
--with-supply-chain |
off | Add MCP04 (OSV dependency audit + slopsquat; needs network) |
--with-content |
off | Add MCP06 (prompt injection on docs/content under the path) |
--allowlist=<path> |
– | Approved servers for --discover-shadow |
Exit codes: 0 clean (or below --fail-on), 1 findings at or above --fail-on, 2 usage error.
MCP tools
| Tool | What it does |
|---|---|
owasp_scan_path |
The scan mode over a path (path, maxFiles, discoverShadow, allowlistPath) |
owasp_scan_live |
The live mode (url, or command with args) |
owasp_scan_catalog |
The catalog mode on a JSON string |
list_owasp_coverage |
The coverage table above |
GitHub Actions
- run: npx -y @guardbee/mcp-owasp-scan scan . --format=sarif --fail-on=high > owasp.sarif
- uses: github/codeql-action/upload-sarif@v3
if: always()
with:
sarif_file: owasp.sarif
Related packages
Each auditor is also its own package with more options: mcp-secret-scanner, mcp-server-auditor, mcp-oauth-auditor, mcp-audit-gap-auditor, mcp-context-oversharing-auditor, mcp-toxic-flow-auditor, mcp-tool-poisoning-scanner, mcp-config-auditor. To enforce these rules at runtime instead of finding them in code, put mcp-security-proxy in front of your MCP servers.
Feedback
Questions, ideas, or a false positive? Start a thread in GitHub Discussions or open an issue. If GuardBee is useful to you, a ⭐ on the repository helps others find it.
owasp-scan MCP questions
How do I add owasp-scan MCP to Claude Code?
Run claude mcp add owasp-scan -- npx -y @guardbee/mcp-owasp-scan in your terminal. Add --scope user to make it available in every project.
How do I add owasp-scan MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does owasp-scan MCP provide?
It exposes 5 tools, including live, owasp_scan_path, owasp_scan_live, owasp_scan_catalog, list_owasp_coverage.
What formats can the scan report be exported in?
The scan results can be output as text, JSON, or SARIF, which is compatible with GitHub code scanning.
Can I scan a live MCP server?
Yes, you can connect to a running MCP server via a streamable HTTP URL or a stdio command to grade its tools.
How is the security grade determined?
The server provides an A–F grade where A means no findings and F represents a lethal trifecta of risks.
Does the tool collect telemetry data?
Telemetry is disabled by default, but can be enabled using the GUARDBEE_TELEMETRY=1 environment variable.