daoyuanli2816/mcp-fence

국부적으로 첫번째 안전 스캐너, MCP 의정서 inspector, 동적인 fuzzer, Docker Sandbox 및 ** Model Context Protocol**에 대한 보고서 생성기 서버.

mcp-fence 개발자 도구입니다. mcp.json에서 포인트 (또는 MCP 서버를 실행하여 썼습니다.

1.Statically scan 도구 독에 대한 구성 및 소스, 위험한 시작 명령, 일반 텍스트 비밀, 스키마 간격, 및 unauthenticated HTTP 수송. 2. ** 검사 ** 서버는 stdio에 살고 있습니다 - 실행 initialize, tools/list, schemas/annotations 수집. 3. ** Fuzz ** schema-aware 페이로드가있는 모든 도구 (path traversal, 명령 주입, SSRF, 신속한 주입, oversize 입력, 유형 주입). 기본적으로 안전; 런타임 페이로드를 선택 --toy-mode 또는 --allow-unsafe. 4.Sandbox sensible 프로파일을 가진 Docker에 있는 어떤 stdio 서버 (strict], filesystem-readonly], network-deny], dev). 5.Report 일반 텍스트 테이블, JSON, SARIF 2.1.0 (for GitHub 코드 스캔), 또는 완전히 오프라인 HTML 페이지.

non-destructive, local-first, ** 클라우드 LLM 사용 기본값**. 선택적 로컬 LLM 판단은 로컬 Ollama 또는 OpenAI 호환 엔드포인트.

설치

Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Context Protocol servers.

mcp-fence is a developer tool. Point it at your mcp.json (or any running MCP server you wrote) and it will:

1. Statically scan the config and source for tool poisoning, dangerous startup commands, plaintext secrets, schema gaps, and unauthenticated HTTP transports.
2. Inspect the server live over stdio — runs initialize, tools/list, gathers schemas/annotations.
3. Fuzz every tool with schema-aware payloads (path traversal, command injection, SSRF, prompt injection, oversize input, type confusion). Safe by default; opt in to runtime payloads via --toy-mode or --allow-unsafe.
4. Sandbox any stdio server in Docker with sensible profiles (strict, filesystem-readonly, network-deny, dev).
5. Report findings as a plain-text table, JSON, SARIF 2.1.0 (for GitHub code scanning), or a fully offline HTML page.

It is non-destructive, local-first, and uses no cloud LLM by default. An optional local-LLM judge can talk to a local Ollama or OpenAI-compatible endpoint.

Install

From PyPI:

pip install mcp-fence

From source (for contributors):

git clone https://github.com/DaoyuanLi2816/mcp-fence
cd mcp-fence
python -m venv .venv
source .venv/bin/activate          # Windows: .venv\Scripts\activate
python -m pip install -e ".[dev]"

Requires Python 3.11+.

30-second quickstart

# 1. Bring up the bundled examples in your working directory.
mcp-fence init-example ./mcp-fence-examples

# 2. Static scan the intentionally poisoned metadata server.
mcp-fence scan mcp-fence-examples/vulnerable_metadata_server/mcp.json

# 3. Live-inspect the safe baseline.
mcp-fence inspect mcp-fence-examples/safe_server/mcp.json

# 4. Fuzz the arbitrary-file-read server.
mcp-fence fuzz mcp-fence-examples/vulnerable_filesystem_server/mcp.json

# 5. Generate a `docker run` command that sandboxes any of the above.