Deepsleuth MCP server

Deepsleuth — read the fine print

Deepsleuth is a deterministic, no-LLM security scanner for MCP servers. It audits what a server says — and, more importantly, what it does.

Most MCP scanners read only the declared manifest (tools/list names, descriptions, schemas). They never launch the server, never call a tool, never read a response, never read the implementation source, and never reason across calls — so whole classes of attack are structurally invisible to them.

Deepsleuth sees those. It is a single frontend-agnostic detection core with two frontends:

transparent proxy that is an MCP server to the agent and an MCP client to one downstream server. It audits tool descriptions at startup, enforces a gate before every tools/call, and scans every response before returning it. Includes a headless proxy-eval mode for offline scoring.

• Frontend A — inline MCP gateway / proxy (the headline artifact). A

server in a Docker sandbox, actively elicits behavior with synthesized calls + planted canaries, and produces findings. Also the offline scoring harness.

• Frontend B — batch / sandbox scanner. A pre-flight auditor that launches a

Both frontends run the same detectors over the same Context — a detector is written once and works in both.

No LLM. Ever.

Fully deterministic: parsing, static AST + taint/dataflow, normalized regex/token heuristics, unicode/encoding/entropy analysis, structural diffing, and sandboxed dynamic execution with instrumentation. Same input → byte-identical findings. Offline (no network egress except to the Docker daemon). No threat feeds.

Install

Python 3.11+. No required third-party packages — the scanner speaks MCP over stdio itself, so it installs in externally-managed (PEP 668) environments.

pip install security-scanner-deepsleuth-mcp                             # published on PyPI
# or from source:
pip install git+https://github.com/DeepSleuth/deepsleuth-mcp.git   # zero required dependencies
deepsleuth --help
# or straight from the source tree:
python -m deepsleuth --help

The PyPI distribution is named security-scanner-deepsleuth-mcp (what it is, plus the brand); the tool, repo and MCP server are deepsleuth. The package installs the deepsleuth console command — and an alias script under the distribution's own name, so uvx security-scanner-deepsleuth-mcp runs the server for registry clients.

Deepsleuth is itself an MCP server, so agents can scan with it directly:

{"mcpServers": {"deepsleuth": {"command": "python", "args": ["-m", "deepsleuth.mcp_server"]}}}

Tools: listdetectors, checklisting, scan_target.

Install as an agent plugin

The repo is a valid Agent Plugins package (plugin.json + mcp.json, spec 1.0.0): any compatible client can install it directly from the repository and gets the deepsleuth MCP server plus the audit-mcp-server skill. The stdio entry (bin/deepsleuth-mcp) needs only python3.11+ — the scanner has zero third-party requirements:

{"type": "stdio", "command": "./bin/deepsleuth-mcp"}

For the dynamic layer (Frontend B and proxy-eval) you need the Docker CLI + daemon. Without Docker the scanner degrades gracefully: static/manifest detectors still run and the skipped dynamic coverage is reported (never a crash).

Run

# Frontend B — batch/sandbox scanner (also the offline scoring harness)
python -m deepsleuth scan <target> [--no-dynamic] [--json out.json] [--timeout N] [--reference-listing tools.json]

Shortened. The full README is on GitHub.