3181 Model Context Protocol servers — searchable, rated, ready to install.
LLM Observability & Orchestration Agent (LangChain Community)
Recovers malformed LLM JSON. MCP build: 218/300 on MALFORMED-300 (library build 282/300).
Run any model on the live WaveSpeed catalog: image, video, audio, 3D.
Local-first, zero-knowledge AI memory across Claude, Cursor, and every MCP client. 0 RTT reads.
Causal root-cause analysis MCP server -- 56 tools across graphs, RCA models, PyRCA.
Fan a goal out to cheap parallel LLM workers on your own key or a free local Ollama. Keep your mind.
Holonovel MCP server: world-model base for tabletop RPG play (rooms, parser, narrative tools).
Search and invoke real AI capabilities on modelmarket.dev. Free trial, then a prepaid key.
Vehicle search on Webmotors, Brazil's largest automotive marketplace. Search listings by make/model,
Free App Store competitive intelligence for Claude — rival downloads, revenue, and ASO keywords.
PostgreSQL MCP server with 15 tools (SQL, EXPLAIN, health, indexes) plus a Gradio UI with LLM chat.
Valem - Deterministic reactive state models. Create your own calculators/forms with AI
Hosted MCP memory: save sessions/decisions once, search from Claude, Cursor, ChatGPT. EU-hosted FTS.
Traced OpenAI LangChain Agent
LLM Orchestration Traced Agent
LLM Orchestration Observability Agent
LLM Orchestration Agent (Langchain Core)
Prepaid inference for agents over hosted MCP. Chat, image, and video.
Shared memory for a team in Claude Code: what one person records, everyone has.
Parse, extract, split, and ask over digital PDFs (text layer, no OCR) from Cursor and Claude.
Tamper-evident memory + governance MCP for Claude Code, Cursor, Codex. Ships the Seatbelt kit.
Consult other LLMs as tools — ask them, compare their answers, synthesize a conclusion.
Checks a claim's numbers, names and file names against your indexed notes. Local; no model.
Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
POST /mcp