Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
MCP server for llamator: automate LLM red teaming workflows
PythonCC-BY-SA-4.0★ 4Few starsNo key
MCP server for Harbor Registry — projects, repositories, artifacts, storage reports, cleanup candidates. Works with any Harbor 2.x instance.
PythonMIT★ 1Few starsNeeds a key
A Model Context Protocol (MCP) server for Tuleap. Enables AI assistants (Claude, OpenCode, Cursor, Gemini) to read Agile projects, query artifacts, fetch Epics and User Stories, and search Git reposit
PythonMIT★ 4Few starsNo key
Skills ecosystem for autonomous software development
SkillApache-2.0★ 3Few starsNo key
SkillFabric: Weaving Task-Specific Wikis for Agentic Skill Routing
SkillMIT★ 10No key
Static security review for AI agent configs (LangGraph, CrewAI, OpenAI Agents, MCP): maps source-to-tool flows and flags untrusted input that can reach privileged actions. Runs locally, no network, no
PythonApache-2.0★ 17No key
Sentinel DV is an **open-source Model Context Protocol (MCP) server** that provides large language models and AI agents with **safe, structured, read-only access** to verification artifacts—enabling d
PythonApache-2.0★ 5No key
Universal AI skill compiler + MCP bridge. Write once, run across ChatGPT/Codex, Claude, Gemini, DeepSeek, Meta/Llama and browsers.
PythonMIT★ 1Few starsNo key
Optees is an open-source desktop toolkit for optimization: LP (SciPy/HiGHS), MILP (OR-Tools CP-SAT), and 0/1 knapsack. Clean Architecture, TDD, dataset adapters (LPnetlib, MIPLIB, Burkardt). Minimal A
PythonApache-2.0★ 13No key
Persistent code knowledge graph + MCP server for AI coding agents, with confidence-tagged edges and 5 durable markdown artifacts. Apache-2.0.
PythonApache-2.0★ 2Few starsNo key
Automatically bridge your local Claude Code setup into Codex so both stay equally effective.
SkillMIT★ 10No key
Self-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams
PythonApache-2.0★ 6Needs a key
Governed AI-ops for self-managed GitLab + Gitea CI/CD: pipelines, jobs, runners, artifacts, repo hyg
PythonMITFew starsNo key
面向 agent 长任务的本地 MCP,自动保存截图、短录屏、打码副本和可复盘证据。
PythonMIT★ 4Few starsNo key
A runtime-portable 5-agent adjudicator council for universal quality gating of text artifacts.
PythonMIT★ 11No key
Evidence-grounded AI research workflow for traceable claims, explicit uncertainty, causal-language checks, and reviewable JSON, Markdown, and Excel exports.
SkillMIT★ 11No key
🔌 Lets an MCP client analyze images, videos, and audio for deepfake manipulation artifacts. Checks metadata, provenance chains, and synthesis indicators.
PythonMITFew starsNo key
Governed state engine for AI agents: typed, executable knowledge artifacts with a code-like lifecycle
PythonApache-2.0★ 17No key
Turn any company URL into a strategic intelligence brief. Adaptive scraping + AI-powered research and synthesis.
PythonApache-2.0★ 3Few starsNo key
Local deterministic MCP evidence and release gates with portable Agent Skills
PythonApache-2.0Few starsNo key
Auditable MCP + cross-agent harness for autonomous and human-guided academic writing—from verified evidence to reviewed DOCX/PDF.
PythonApache-2.0★ 12No key
Daily, plain-language GTFS quality scorecards for small transit agencies: the grade, the three fixes that matter most, and why. 2,600+ curated Schedule and Realtime feed records (US, Canada, reviewed
PythonApache-2.0★ 1Few starsNo key
Independent verifier for AI agent completion claims: VERIFIED, FAILED, FALSE_DONE or UNVERIFIABLE. Stdlib CLI + optional LangChain tool.
PythonMITFew starsNo key
MCP server that compresses OCR-heavy PDFs into dense packed images so AI agents can handle long visual documents
PythonMIT★ 1Few starsNo key
Who stands behind it