MCP Catalog
Browse 410 Model Context Protocol servers · AI & Machine Learning · PythonClear
+9 more
MCP server for the Codabench REST API — drives a full ML-benchmark participant workflow.
Social-choice voting rules (Borda, Copeland, Condorcet, STV, opinion pool) as MCP tools.
Goose-first MCP server for Workbench-owned acceptance evidence, validation gates, and analytics.
Spacecraft ephemeris made easy — auto-managed SPICE kernels for heliophysics
Action-level governance for AI agents -- control what they DO, not what they SAY
Ten formal algebra for machine intelligence — encode, decode, compose, and verify
Local Fusion MCP: panel->judge->synthesis on the Claude CLI subscription, no OpenRouter.
AI agent trust engine — preflight checks, KYA due diligence, search 204K+ agents. Free.
Tracks conversation health in real time — drift, desync, and causal collapse — for any AI agent.
Multi-model AI gateway — 8 providers plus local models, no system prompt injection.
Real-time threat intel for AI agents: 890K+ IOCs incl. prompt-injection & AI-skill threats
Hacker News signal extraction for technology trend monitoring
MCP server for the CZ CELLxGENE Census. Single-cell, ontology-aware. Community, unaffiliated.
Model-tiered content pipeline — cheap models seed, expensive models verify
9-LLM consensus + disagreement scoring + cheapest-route picks to fight hallucinations.
An MCP server that fuses LLM contextual intelligence with procedural code reliability.
Decentralized AI inference on Base: OpenAI-compatible chat via community GPUs, paid in MYAI
Version-controlled golden datasets and RAG evaluation, no API key needed.
Usage-adaptive Obsidian vault search: Hebbian + PageRank + BM25 hybrid ranking.
Drug interactions (FDA), dose range check, allergy cross-reactivity. No PHI processed.
LLM-native optimization solver: LP, MIP, portfolio & scheduling via HiGHS/OR-Tools.
PDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.
QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
Authority-weighted memory graph for AI agents with conflict detection and semantic search.