MCP servers tagged llm
10K live MCP servers tagged "llm", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with llm.
Pcli2 MCP
MCP server exposing Physna 3D geometry search as tools for LLM clients
Semesh
Official SettleMesh client-integration layer: MCP server, Claude Code plugin, Cursor rules, agent docs, and starter templates. The platform and CLI binary are proprietary.
Cycles Client Python
Python SDK for Cycles — reserve, commit, release budget and risk for AI agents
CRT GroundCheck SSE
CORE/Aether — epistemic governance for AI agents. Belief substrate with trust math, contradiction detection, and a measured belief/speech gap. The model is the mouth; the substrat…
Agent Circuit Breaker
Stop runaway agents before they stop your wallet.
LLM Hub
Self-hosted hub for local & cloud LLMs. Unifies Ollama, Anthropic, Google & OpenAI behind one OpenAI-compatible gateway. Features an MCP server generator, Anthropic skills manager…
Dr Claw App
Native Android client for the Ironjaw gateway: Kotlin and Compose, streaming chat, encrypted local history and agentic tool cards over one authenticated WebSocket.
Warehouseops AI
Multi-agent warehouse operations assistant — LangGraph planner, MCP tools, forecasting and document extraction, running on free open-source infrastructure
Context Brief
Context template for Claude Code, Cursor, ChatGPT, and coding agents — schema-backed context engineering briefs.
Aegis Advisory Assistant
Agentic wealth advisory assistant. Five agents, a deterministic compliance rules engine, and a trace of every step
MPCP
MPCP — an open, transport-agnostic protocol for governed, auditable coordination among mixed parties: humans and AI agents as first-class, symmetric participants (P2P/P2A/A2A). Si…
Vacancy Radar
A local-first job application tracker. A markdown vault is the source of truth; a derived LanceDB index provides hybrid BM25 + vector search; an MCP server exposes read/write tool…
Agent Systems Course
25-lesson Chinese textbook on modern Agent systems, harnesses, tools, memory, orchestration, evaluation and production engineering
Docqa Server
MCP server for document Q&A — the retrieval half of RAG as reusable infrastructure: semantic search over pgvector/SQLite, OpenAI or keyless embeddings, PubMed ingestion, recall-ga…
Nmem
Spreading-activation memory for agents. Graph brain, not a vector DB. Rust, MCP, weak-hardware friendly.
Rho
Pi-style hot-reloadable coding agent written in Rhombus. Minimal kernel; MCP, tools, dashboard, and sandbox load as extensions.
Epa
A confined generation tool: runs an LLM over a local directory read-only and emits the output as a product that is always labeled untrusted. CLI + stdio MCP server on the myelin s…
Onprem Agent Kit
Reference kit for running an agent stack inside a customer VPC with zero egress — Helm chart, MCP gateway allowlist, deny-all NetworkPolicy. Early scaffold.
Telegram AI
Talk to Claude Code and Codex from Telegram — Bot-API bridges and userbot modules
Free
[Live] The verified $0 stack for shipping an AI side-project — exact free-tier limits for 37 dev services, each checked on the official pricing page with a date. JSON + MCP + week…
Enterprise AI Platform V2
Production-architecture RAG + AI agent platform on a free local stack — PySpark, DuckDB, FAISS, LangGraph, Ollama, FastMCP
PRVerdict
PR readiness gate that scores pull requests against six criteria using live GitHub and PagerDuty data via MCP
Aie3672
A 28-lesson LLM application engineering course: Transformer internals to agent systems. English slide decks.
Reversible Context Memory
Reversible selective compression of AI chat history — concept article in Russian and English
Psw Code
An open-source, local-first AI coding agent powered by Ollama — and the provider-agnostic TypeScript agent runtime underneath it.
GoPilotKit
Enterprise intelligence runtime in a single Go binary. Implements AG-UI, MCP, and A2A protocols with autonomous self-improvement, persistent threads, guardrails, analytics, and mu…
Atomic Memory Kit
Bidirectional atomic memory for agents: compile Markdown knowledge atoms into one context bundle, decompile back, and spotlight what's missing. Zero deps, no embeddings.
AI Code Assistant Showcase
基于 Spring AI、Agent、RAG 与 PGVector 的智能编程学习助手
Agent Harness Experience
A minimal, traceable Agent Harness experiment covering tool calling, context management, memory, persistence, retry, MCP, and reviewer subagents.
Provtrail
Append-only, hash-chained ledger for recording the sources used in LLM-assisted research
Acsac ANCHOR
ACSAC artifact for ANCHOR: schema-agnostic CTI knowledge graph construction via hybrid ontology discovery (UCO / STIX / MALOnt). Requested badges: Available, Functional.
LLM Engineering Portfolio
Thirteen measured experiments on one RAG pipeline: retrieval evaluation, hallucination defense, prompt injection, MCP, and stateful agents. Every number produced by code in this r…
Frog To Toad Agent
Frog-to-Toad Agent — public recipes for forging governed living agents
AI Engineer Course
Курс «AI-инженер: от устройства LLM до мультиагентных систем»: устройство LLM, промпты, RAG, LangChain, LangGraph, MCP, агенты
Pdverify
Render Pure Data patches headless and verify what they actually sound like — the audio-verification piece missing from Pd LLM harnesses.
AI Collab MCP Notes
CHIEF — decision-audit infrastructure for trustworthy AI-assisted review, revision, and human adjudication
Mu Client
The Memory Universe local daemon and agent host integrations — capture, context injection and local stores. Apache-2.0.
Curricle
A personalized-learning platform for one person: compile a course from markdown, serve it with real progress tracking, and let an LLM build its interactive layer under a budget.
AI Act Evidence Desk
Agentic RAG assistant that turns an AI use case into a source-grounded EU AI Act evidence map. Hybrid BM25/TF-IDF retrieval with rank fusion, three-pass self-consistency synthesis…
Fetch Html To Md
Convert remote or local HTML resources to Markdown via CLI or Node.js API.
Autonomous Code Agent
Autonomous coding agent: clones a repo, fixes bugs, opens PRs. LangGraph + MCP + RAG
OKTS
OKT — open knowledge tools; OKTS — tool search and discovery for any agent.
Blastdoor
Blast radius control for autonomous agents: capability boundaries, dry-run by default, verifiable kill switches, and an audit trail for every mutation.
Multi Agent Rag MCP
Production-style multi-agent AI system with LangGraph, hybrid RAG, MCP, self-correction, human approval, observability, and RAGAS evaluation
Veriplane
Evidence-backed project state for humans and AI agents. Open-source, local-first control plane across models, agents, and tools.
Simplex
Fast, evidence-first open-source research search with SearXNG, LLM Judge, Crawl4AI, and citation streaming.
Agentic Patterns
Reference implementations of 12 agentic AI patterns (ReAct, RAG, MCP, guardrails, multi-agent, and more) from canonical form to 2025-2026 research. Runs offline with no API key.
Turnscope
Local observability TUI for Codex sessions: timelines, tool I/O, Skills, MCP, tokens, and critical-path latency.
Review Rubric
What code review enforces, mined from 2,899 comments across 9 repos, and how to feed it back to an LLM reviewer
Bindagt
AGT-9303 — the agent identity standard. Verify that an AI agent belongs to the domain it claims.