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.
Acp Protocol
ACP (Agent-Component-Protocol) - lightweight open protocol for AI Agents to invoke remote services, IoT hardware and distributed business components. Bidirectionally compatible wi…
Kervo
Deterministic context for non-deterministic agents — a trust-labeled, git-native memory layer for AI sessions
OpenAgentsGate
One policy, audit, replay, and revocation layer for Codex, Claude Code, MCP tools, CI agents, and custom agent scripts.
LLM Tool Use Patterns
Production-oriented patterns for LLM agents with tool use in Python. Guard rails, state, observability.
AI Companion Chatbot Demo
Voice-first conversational AI demo with layered prompts, safety guardrails, MCP tool-calling, and a from-scratch eval framework.
IrisFlow
开箱即用的 LLM 聊天 + Agent 控制台，支持流式对话、工具调用与 MCP 扩展，适配任意 OpenAI 兼容网关
CyberFortressX
Enterprise Agentic AI SIEM & SOC platform for Palo Alto Firewall analytics, threat intelligence, risk scoring, and automated incident response using FastAPI, IBM Agent Studio and…
Nyoy
State-machine AI agent graphs for local LLMs, MCP, search, and image generation.
Actgate
Local IntentLedger + MCP stdio proxy: propose, approve/deny, hash-chained ledger. Optional HMAC seals.
Resolve Tui
CLI / TUI dual-mode coding agent with three-tier response chain (fastpath + codegen + LLM), Agent Skills, PSE multi-agent orchestration, MCP support, and per-task sandbox isolatio…
Mini Coding Agent
A minimal Python coding agent with tool calling, sandboxed execution, test-driven feedback, verification gates, token budgets, and optional Skill/MCP support.
Jarvis Rag Local
Local-first GraphRAG over a markdown knowledge base: LightRAG, Ollama/Qwen, MCP server, LLM router, scheduled self-maintenance
Kuru
psyche harness
Judgment Labs
Judgment Labs — independent third-party profile of a public API surface, by API Evangelist. Judgment Labs builds the continuous-improvement stack for AI agents: tooling to trace,…
Zhoda
Open-source LLM deliberation and decision-review engine with a Python CLI and MCP server. Includes minority reports and auditable transcripts.
SingleCLI
Unified control plane and coordinator for AI coding-agent CLIs — 24 built-in agents, MCP/LSP/provider sync, multi-account concurrency, a goal-driven task-graph coordinator, a free…
Dewie
Agent-native retrieval over a self-enriching corpus: hybrid search + graph navigation exposed as MCP tools, so small models can punch above their weight.
Aether Agentic Workspace
Full-stack AI assistant with hybrid-retrieval RAG (pgvector + BM25 + cross-encoder rerank), a provider-agnostic LLM backend, MCP and Google Workspace tool use, and a LiveKit voice…
Transcript Bridge
Move agent transcripts between providers without losing data.
Support Ticket Triage Assistant
Portfolio: GitHub-first agentic SDLC case study (v0.1). Demo app: synthetic support-ticket triage. Start: docs/00_project/PORTFOLIO_TOUR.md
Apollo Agi
Ponte self-hosted entre WhatsApp e um agente de IA — Node.js, Uazapi, protocolo MCP, sistema de permissões e transcrição de áudio
AgenticAI Learnings
My hands-on learning journey in Agentic AI covering LangChain, LangGraph, RAG, MCP, Deep Agents, Guardrails, LLM Evaluation, and LLM Gateways.
Nexoraa Tree
Nexoraa — the open AI-workforce SaaS: animated interactive map of 137 AI jobs, gated skill library, pricing, dashboard. Next.js 16 + React 19.
CortexIQ AI
CortexIQ AI is an open platform that make AI more useful, reliable, transparent, and controllable.
Ecosystem Measurements
Reproducible measurements of the MCP registry, the VS Code gallery, Glama, hosted MCP server endpoints and GitHub search. Twelve findings, each with the script, its raw dated outp…
Agent Delivery Gates
Delivery gates for AI coding agents, because green tests are not proof. Breaks your code on purpose and reports the breaks no test noticed. Runs a change's new tests against the c…
Turning Point Proj
AI-powered assistant for Solace Event Portal, enabling Admins and End Users to discover and manage event-driven architectures through natural language using Qwen3-8B, MCP, Solace…
Special War
A jeopardy-style CTF where the competitors are AIs. Play via MCP, no account needed.
Awesome MCP Testing
A curated list of tools for testing, evaluating, validating and debugging MCP (Model Context Protocol) servers: inspectors, conformance suites, eval harnesses, test libraries, sca…
Live Docs MCP
Real-time documentation MCP server for AI engineers - fetch live docs for 45+ libraries (LangChain, OpenAI, Anthropic, CrewAI, Qdrant and more) directly inside Claude. No stale tr…
vishalbanwari26/mnemos
deleted. Real before/after MCP eval: +60% answer accuracy with memory vs. without. `git clone` + `uv sync` (not yet on PyPI).
PackkitLabs/packkit-mcp
mcp`
Mem Forge
Self-evolving, evidence-based memory layer for coding agents and development teams.
Intent DB
A local-first vector database with an extra dimension: intent. The same corpus and query return different results depending on what the asker is doing; built for agent memory
SafeSQL MCP
A LangGraph-powered MCP server for natural language SQL with human-in-the-loop approval for database write operations.
Zerocontext
A local MCP server that serves your AI only the rules matching the file you're editing — just-in-time, per file.
Azure Synapse MCP
Free, open-source MCP server for Azure Synapse Analytics. Full CRUD SQL, Pipelines, Spark & Notebooks. No paid drivers. Works with Claude, Cursor & any MCP client.
Ragnite
Confidence-Aware RAG Memory Engine for LLMs and coding agents - typed memory (facts, decisions, episodes, code), confidence scoring with answer modes, context packing, semantic ca…
Document Assistant
Async RAG backend for PDF Q&A: FastAPI + Postgres/pgvector, streamed answers, swappable LLM providers (Groq, Bedrock, OpenAI, Azure), MCP search tool, Langfuse tracing, 38-questio…
Hallouminate
A per-repo markdown wiki your coding agent writes and searches — persistent memory for Claude Code and any MCP harness, stored as plain markdown
Captainslog
Task and Agenda MCP. Plan your daily work together with copilot
Changelog Hq
Auto-generated changelogs from GitHub PRs via LLM + MCP server
Pdf Rag MCP
PDF-based RAG + MCP system using ChromaDB, DeepSeek and LangChain
Decant Extension
Extract clean Markdown, JSON or MCP from any web page. Chrome Extension + MCP Server.
AgentBudgetMcp
MCP server for @mukundakatta/agentbudget — token + dollar budget caps for AI agents over stdio. Drop into Claude Desktop, Cursor, Cline, Windsurf, Zed.
Persistent Agent Memory
MCP server for persistent agent memory across sessions — semantic search, typed memories, session handoffs, directory indexing
Benchmark Article Resources
An Investigation Across Two MCP Servers, Two Frontier Models, and 20 Controlled Benchmark Runs
Logicahome
Local-first MCP server and CLI for smart home control. Plug any AI into your home.
Storagelens
Diffs and decodes contract storage layouts across proxy upgrades to catch storage-collision and uninitialized-slot bugs.
Promptmirror
Prompt-injection & indirect-injection scanner for any LLM context input