"Hugging Face" matching MCP servers:

Automated MCP server that listens for Hugging Face discussion comments, extracts ML tags, and creates pull requests to update model metadata.

Biometric authorization for AI agent actions via Face ID on iPhone, enabling secure approval of sensitive actions and credential-safe API calls through vault execution.

Stdio MCP Server wrapping custom Python runtime (LocalPythonExecutor) from Hugging Faces' smolagents framework. The runtime combines the ease of setup (compared to docker, VM, cloud runtimes) while providing safeguards and limiting operations/imports that are allowed inside the runtime.

Provides access to over 100 curated AI agent skills from organizations like Anthropic, Vercel, and Hugging Face. It enables AI assistants to perform specialized tasks including document processing, security analysis, and web development through a standardized interface.

An MCP server that enables agents to automate refusal direction removal from open-weight LLMs via Optuna-driven search, producing standard Hugging Face models with no inference overhead.

A local daemon for macOS that gives any MCP-capable AI client eyes, hands, and a face — screen capture, accessibility tree, mouse/keyboard actions, and an overlay — with a built-in security ceiling.

Lets any MCP-compatible agent connect to a simulated pool table to observe the layout, take shots with angle, power and spin while human-like hand noise is injected, and review its own shot history and score for self-calibration. It runs as a headless, deterministic and replayable hall where agents can play solo calibration trials or face each other in live matches.

Non-AI deterministic Japanese parser that extracts intents, constraints, references, and execution order into structured Task Packets for safe downstream processing.

Enables autonomous agents to cross-reference factual claims against multiple source documents, detect ungrounded or hallucinated statements, and return normalized confidence scores via the verify_claim tool.

Enables AI-powered racing coaching and telemetry analysis for iRacing, providing real-time racing advice, car spotting, lap analysis, and conversational interaction with racing data through live telemetry streaming.

Enables autonomous agents to cross-reference factual claims against multiple source documents, detect ungrounded statements, and compute normalized confidence scores. It supports multi-source corroboration and claim verification through a single MCP tool.

Implements Agentic Context Engineering to create self-improving AI coding assistants that learn from execution feedback and build persistent knowledge playbooks. Reduces token usage by 86.9% while improving code accuracy by 10.6% through incremental context updates.

Enables autonomous agents and MCP clients to decompose text into atomic claims and verify them against reference knowledge, detecting ungrounded claims, numerical contradictions, and hallucinated entities.

Enables AI agents and MCP clients to decompose text into atomic claims and cross-verify them against reference knowledge to flag ungrounded claims, numerical contradictions, and hallucinated entities. Runs deterministically with zero dependencies over JSON-RPC stdio, avoiding LLM round-trips for routine verification tasks.