MCPHARDEN — MCP server hardening linter — capability declarations, transport, tool descriptions

Part of the Cognis Neural Suite by Cognis Digital Cognis Open Collaboration License (COCL) v1.0 · domain: ai-security

MCP server hardening linter — capability declarations, transport, tool descriptions.

AI Security & Governance — securing LLMs, agents, and the MCP supply chain.

Usage — step by step

1. Install the linter:

   pip install cognis-mcpharden

2. Audit a single MCP server manifest — audit takes a manifest path and prints a findings table:

   mcpharden audit path/to/mcp-server.json

3. Scan a directory of manifests and gate on severity. scan walks a file or directory; --min-severity filters the report and --fail-on controls the exit code:

   mcpharden scan demos/ --min-severity low --fail-on high

4. Read the output in a machine format. --format accepts table (default), json, sarif, or html; --out writes to a file instead of stdout:

   mcpharden scan demos/ --format sarif --out mcpharden.sarif
   # exit code is non-zero when a finding >= --fail-on is present
   echo $?

   List the detection rules behind those findings with mcpharden rules.
5. Automate in CI — fail the build on high-severity findings and upload SARIF to code scanning:

   - run: pip install cognis-mcpharden
   - run: mcpharden scan . --format sarif --out mcpharden.sarif --fail-on high
   - uses: github/codeql-action/upload-sarif@v3
     with: { sarif_file: mcpharden.sarif }

   To expose it to agents instead, run mcpharden mcp (stdio JSON-RPC MCP server).

Why

Security and intelligence teams need MCP server hardening linter — capability declarations, transport, tool descriptions without standing up heavyweight infrastructure. mcpharden is single-purpose, scriptable, CI-friendly, and self-hostable: point it at a target, get prioritized findings in the format your workflow already speaks (table, JSON, SARIF, HTML), and wire it into agents over MCP when you want it autonomous.

Install

pip install cognis-mcpharden
# or, from this repo:
pip install -e ".[dev]"

Quick start

mcpharden --version
mcpharden scan demos/                      # run against the bundled demo
mcpharden scan demos/ --format sarif --out r.sarif --fail-on high
mcpharden scan demos/ --format html --out report.html
mcpharden mcp                              # expose as an MCP server (Cognis.Studio / Claude Desktop / Cursor)

Built-in demo scenarios

Each scenario folder includes a SCENARIO.md describing the situation and the findings to expect.

• demos/01-basic/
• demos/01-public-mcp-no-auth/
• demos/02-internal-stdio/
• demos/03-shared-multi-server/

Output formats

• Table (default) — human-readable terminal summary
• JSON — machine-readable findings for pipelines
• SARIF — drops into GitHub code-scanning / IDE problem panes
• HTML — shareable report with severity rollups

Credits / Built on

Cognis composes and credits the best of open source. This tool builds on / interoperates with:

• ModelContextProtocol-Security/mcpserver-audit — fork base
• slowmist/MCP-Security-Checklist — checklist source

Missing a credit? Open a PR — see CONTRIBUTING.md.

How it fits the Cognis Neural Suite

mcpharden is one of 52 tools in the Cognis Neural Suite. Every tool ships an MCP server, so Cognis.Studio agents can call them as scoped capabilities.

Sibling tools in ai-security: aegis, promptmirror, ledgermind, adversa, guardpost, hallumark, aicard, biascope, agentlog, ragshield

Architecture & roadmap

• Design notes: docs/ARCHITECTURE.md
• Planned work: ROADMAP.md

Contributing

PRs, new detections, and demo scenarios are welcome under the collaboration-pull model. See CONTRIBUTING.md and SECURITY.md.

Interoperability

mcpharden composes with the 300+ tool Cognis suite — JSON in/out and a shared OpenAI-compatible /v1 backbone. See INTEROP.md for the suite map, composition patterns, and reference stacks.

Integrations

Forward mcpharden's findings to STIX/MISP/Sigma/Splunk/Elastic/Slack/webhooks via cognis-connect. See INTEGRATIONS.md.

License

Source-available under the Cognis Open Collaboration License (COCL) v1.0 — free for personal, internal-evaluation, research, and educational use; commercial / production use requires a license (licensing@cognis.digital). See LICENSE.

Responsible use

This is dual-use security software. Use it only against systems, data, and identities you own or are explicitly authorized in writing to test, and in compliance with applicable law.

About

Cognis Digital — Wyoming, USA · Making Tomorrow Better Today: Advanced Cybersecurity, AI Innovation, and Blockchain Expertise.