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.
Claude Code Analysis Report
Analysis report of Claude code
Universal Dev MCP
A MCP server which gives any AI tool live access to your dev environment. Connects Claude Desktop, Cursor, Windsurf, Zed, Gemini and ChatGPT to your localhost app via MCP — inspec…
AI Hot Source
AI Hot Sauce — Spice up your AI workflow
The Gate
Multi-AI thesis auditor — submit any idea, decision, or argument and Claude, GPT-4o, Gemini, and Grok debate it across three structured rounds to stress-test your reasoning before…
Wssch
Takes care of you while you code for them 🫰🎇. Planned migration to Rust or C++23 soon.
Agentcast
Structured output for any LLM call — validate, retry with feedback, return typed data or throw. Zero deps. Sibling to agentsnap + agentguard.
Agentsnap Action
GitHub Action for AI agent tool-call snapshot tests. Diffs current traces against baselines, posts PR comments on drift. Wraps @mukundakatta/agentsnap.
Runpod Cowork Plugin
RunPod MCP plugin for Claude and Cowork. Manage GPU pods, Jupyter environments, AI jobs, and cloud inference workloads through natural language.
AI Protect
AI-application security assurance pipeline: tier-aware SAST · DAST · AI red-team scanning with a findings dashboard, CVE intel feeds & auto-remediation. For AppSec & platform team…
MDAN
MDAN — Framework de développement multi-agents IA. 28 agents, 17 wizards, 2,014 composants écosystème. Serveur MCP, Context Graph, Débat/Consensus. Made in Morocco.
Agenttrace React
Headless React primitives for AI agent execution traces, approval gates, and human-in-the-loop UI. Works with LangGraph, AG-UI, and the Vercel AI SDK.
AI Agents Research
Field research and feature analysis for AI coding agents — sandboxing, orchestration, plugins, community tooling, SDLC patterns.
Graphrag Rs
GraphRAG: Turn any folder of documents into a knowledge graph, then query it from Claude, Cursor, or any MCP-compatible AI assistant. Powered by Samyama.
Tken Openai Compatible Examples
OpenAI-compatible gateway examples, endpoint tester, SDK migration guides, and tool configs for TKEN developers.
Claw Code Java
Java 21 / Spring Boot implementation of a Claude Code-like coding-agent runtime with CLI, MCP, tools, skills, replay, and PostgreSQL persistence.
LLM Memory
Persistent, cross-model memory for LLM assistants — MCP server in .NET 10 over Postgres + pgvector + Apache AGE. Hybrid retrieval (vector + BM25 + graph PPR + LLM rerank), bi-temp…
Aurekai
Aurekai is the operating fabric for intelligent work: Akai runtime, model memory, proof, semantic cache, and integrations for AI-native operations.
Agent Engineering Kit
A reusable, production-grade .cursor/ engineering package for Cursor / Claude Code / Agent IDEs. Rules, skills, commands, and deterministic safety hooks extracted from a real Agen…
Openclaw Brain
Engineering knowledge-graph + memory served over MCP — ingests semiconductor PDFs into a typed, grounded, citable Neo4j graph for an AI circuit-design mentor.
Modelradar MCP
MCP server for ModelRadar — AI model discovery + a router between OpenRouter and your CLI
Freepalp
Multi-agent AI orchestrator that runs on free models — self-improving, MCP, token streaming, DAG, WebUI
Claude Agent SDK Cookbook
基于 Claude Agent SDK (Python) 的写作智能体实战 —— FastAPI + Vue3 + WebSocket 流式 + 自定义 MCP 工具 + RAG 向量检索 + 多子 Agent 编排
Qwen Memory Agent
Host-agnostic, self-correcting library/API memory for coding agents — harvests mistakes at compaction, verifies against the installed package, auto-injects the fix into future ses…
AI Companion
Drive Claude Code from Telegram — run multiple coding sessions at once and switch between them from a chat keyboard. Runs locally, uses your Claude login.
Openclaw Unison
Long-term memory & recall for OpenClaw — powered by Unison.
Agency.NET
A .NET 10 toolkit for building RAG pipelines and AI agents in idiomatic C#—featuring pluggable vector/KV stores, native MCP integration, and OpenTelemetry throughout.
Pulsa
File-watching automation platform that chains audio conversion, speech-to-text, and LLM processing into document pipelines, with MCP server integration for semantic search.
Pipelain
Powerful utility to build and execute type-safe AI pipelines with structured outputs and tool integration
Agent Utils
One API key. Agent-native utilities for AI agents. File hosting, PII redaction, dead letter queues, and more.
AI Deployment Project
LLM application engineering projects: RAG, LangGraph Agents, MCP, evaluation, FastAPI, Redis, and deployment.
Circuit Breaker Agents
Circuit breaker library designed for agent-to-tool and agent-to-agent communication. Per-tool breakers, confidence-aware tripping, cost-aware tripping, gradual HALF_OPEN recovery,…
Klarova
The trust layer between AI agents and your company's data — correct, cited, access-scoped answers, served to any agent over MCP.
Agentcrdt
CRDTs for distributed AI agent state and conflict-free belief merging
Extract
Agent-facing content extraction infrastructure for autonomous workflows and tool-using systems.
Stabbur
stabbur — the Norwegian storehouse for your models: build a local LLM library, then run, chat and serve it with MCP tools. Source-available, proprietary.
Linux Server Skill
Manage Linux servers with AI over SSH for deploys, SSL, databases, Docker, firewall, monitoring, logs, and files
Claude Code Map
Map Claude Code projects with a clear MCP-driven view of files, paths, and structure
Semantic Runtime
Semantic infrastructure layer for AI Agents: semantic understanding, context resolution, evidence, and safe execution between models and tools.
Spidey
Production-oriented autonomous coding agent: multi-agent workflows, sandboxed execution, code intelligence, and human approval gates.
Claridae
A portable, testable home for everything you've taught your AI
Palimpsest
Local-first, battle-tested, memory that never disappears. Hybrid vector search + knowledge graph + full-text retrieval for AI agents.
Benn
极简 AI Agent 运行时。~4700 行 Python，3 个外部依赖。认知自由，执行有界——家长行为设限兜底，模型自主决策。
Kakeibo
A personal finance agent built from scratch on the raw Gemini API: hand-written tool-calling loop, double-entry PostgreSQL ledger, context caching, MCP server, 46-task eval harnes…
Liteagent
A native, single-user, local-model-first AI agent. Works with any OpenAI-compatible endpoint (Ollama, vLLM, LM Studio) — full tool-calling loop, MCP client, memory, scheduler, and…
Forge Agent
TypeScript agent runtime with tracing, a scripted model for CI, and OpenAI-compatible providers.
Graph Engineering Course
Hands-on course in agentic graph engineering: temporal knowledge-graph memory for AI agents, driven with Hermes Agent and GitHub Copilot CLI
Evelynn Lite
Watch an agent's memory being built, recalled and forgotten. One page, your own local model, and every memory shows where it came from.
Arxiv Agent Research Skill Brightdata
Agent skill: a ranked, summarized roundup of the latest arXiv research on AI agents (default: harness optimization) with 'read these first' picks and a saved report. Fetches via t…
Alpaca Hack
Autonomous paper-trading agent for Alpaca. Trades options and equities on its own: scores news and price signals, sizes by volatility, enforces hard risk limits and flattens intra…
VouqisVerify
Vouqis Verify (VouqisVerify) generates AI Change Evidence Packs from merged GitHub pull requests, with AI change classifications, CI checks, and reviewer evidence exported to Exce…