3230 Model Context Protocol servers — searchable, rated, ready to install.
Private memory layer for AI assistants. Local-first: remember, recall, forget, expand.
Code changes and unit tests by local MLX models, behind a gate a machine can run.
Run 3D CAD operations, pipelines, parametric models and STEP conversions on CAD Cloud with a key
Chinese frontier AI models as MCP tools via one OpenAI-compatible endpoint, zero platform fee.
OpenAI-compatible multi-model inference via ComputeFlux (Polkadot testnet, TEE-verifiable). stdio.
MCP server for Matrix42: explore the API and data model, search the service desk, act on tickets
Secret scanning for AI agents: rules and entropy find candidates, a model decides which are real.
Outlook / Microsoft 365 for Claude — triage mail, reply, answer invites and book meetings, confirmed
Spanish autónomo bookkeeping and AEAT tax forms 303, 130, 390, 100: your model reads the documents
Encrypted long-term memory shared across your AI assistants (Claude, ChatGPT, Perplexity).
Discover verified AI inference nodes, get the best node+model per task, pre-price chains.
Simulate farms, validate GardenScript and compare policies with Rust. No outbound LLM calls.
Build and publish full-stack apps from your coding agent: models, rules, pages, auth, per-app MCP.
Guardrails for LLM answers: exact checks against sources, PASS/REVIEW/FAIL, signed records.
Ask your AI assistant to sketch or change a Neo4j graph data model, then open it in toro4n.
Deploy what Claude builds to a live link: previews, who-opened-it links, stats, forms, domains.
Read, measure and explain LLM eval runs of a digline suite. Cannot promote a baseline.
Claude steers live music by writing Strudel code played in a browser page
Unofficial SAP Concur MCP for Claude — expense reports, expenses, receipts and trips
Model Context Protocol server for the VectorMethods VideoVector media intelligence API.
Generate AI video, images and music. Browse models and prices; OAuth and one prepaid balance.
Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.
Can GPTBot, ClaudeBot and PerplexityBot reach a site? Real fetch per crawler, firewall/CDN blocks.
Shared knowledge base + task queue so Claude, ChatGPT and other agents can work together safely.
POST /mcp