Open behavioral litmus for MCP servers — grades A–F across tool-output injection, egress, sensitive-data, and adversarial-input, with reproducible, content-addressed evidence. Tools: run_litmus, verify_attestation.
4
228 npm
8
Apache 2.0
Why this server?
Provides hooks for contract-driven test enforcement as a pre-commit step.
Structural graph map of any codebase. Scans entities, relationships, and feature flows across 13 languages so LLMs navigate by structure instead of
reading everything.
6
458 PyPI
87
MIT
Why this server?
Provides a pre-commit hook configuration to run OKF lint on commits; the hook is lint-only.
An MCP server and CLI that checks, maintains, imports, and upgrades Open Knowledge Format bundles — directories of Markdown concepts with YAML frontmatter — reporting findings and applying mechanical repairs locally. It runs one contract for agents, CI, and terminals, with no network access and no writes to git.
30
Apache 2.0
Why this server?
Integrates with pre-commit hooks to refuse commits that introduce duplicate code or documentation, or exceed file size budgets, via `ce precommit` and `ce commitmsg`.
Read-only reports on a codebase's LLM-induced entropy: exact and near-miss clone blocks, duplicated documentation, dead code with a liveness verdict, size and complexity metrics, architecture and structure axes, merge suggestions and an erase plan. 21 tools over the local ce and ce-core binaries; no model, no network.
21
20
Apache 2.0
Why this server?
Enforces policy-as-code checks as a pre-commit hook layer, including secret patterns, doc coverage, and deploy verification.
Enables AI coding agents to access live operational context like processes, containers, and git state, while providing a tamper-evident audit log and policy-as-code compliance hooks locally.
22
301 npm
Business Source 1.1
Why this server?
Configures the Governed Agent verification gate as a pre-commit hook for running fail-closed checks on staged files.
Adaptive Epistemic Triage & Recall Engine (AETRE) — Bayesian Value-of-Information (VOI) and queueing operations engine for academic peer review, grant study sections, and venture capital dealflow.
