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.
Sc Prism Releases
Run many AIs on one board and keep control of all of it. Deterministic code decides who acts — never a model. A privacy floor keeps sensitive work on your machine, your own tests…
Factor
The AI agent with a memory that lives on your machine and answers the phone.
Claude Agents Cookbook
Copy-paste Claude Code agent recipes for real businesses — WhatsApp, sales, support, bookings. Real CLAUDE.md, skills & MCP configs. EN/ES.
Zelatix V2
Zelatix v2: Agent-Native Context Database
Dagsmith
Agentic scaffolding for data engineering — turns natural-language source specs into tested Snowflake pipelines (dbt + Airflow + GE) via an LLM tool-use loop over an MCP metadata s…
Ash4d.com
Private AI platform on k3s — Ollama/Qwen3 + Milvus RAG + MCP agentic tooling + Fleet multi-cluster management
Embedmind
Persistent memory for AI agents — one local file, fast, no server. Vector + full-text + graph, via MCP + CLI. Built in Rust.
Vicky
AI 研究报告知识平台：Agent 报告入库 → 门禁校验 → 书风格渲染 → L0-L3 知识蒸馏 → 可查询知识服务
Xomni
XOMNI - one agent, every feature, every free model. Seven open-source coding agents composed on one host with 35 plugins, 25 verified free models, and a 1,251-test suite.
Legacy Erp Agent Lab
A deliberately messy legacy ERP database, and a .NET 9 / Microsoft Agent Framework agent that answers questions about it correctly — including the parts the database gets wrong.
Contextbrief
A token-efficient change log AI tools read once instead of re-scanning your whole codebase or losing context in long chats.
Claudeos
⚡ Open-source agent operating system — Claude as the kernel, every AI tool as a process, one shared memory
Cortex Agent
企业级多智能体 + RAG 知识库问答平台 | Enterprise multi-agent + RAG knowledge assistant: 多模型网关 / 混合检索 / ReAct Agent / 多Agent编排 / MCP，零 API Key 离线可跑，克隆即演示。Runs fully offline out of the box.
Kibborg AI Assistant
KIBBORG AI Assistant — a modular layered AI agent for coding, algorithmic trading, automation, vision, voice, and local LLM workflows.
Chatbi Stock Assistant
面向证券行业的对话式商业智能（ChatBI）助手，支持自然语言转 SQL、行情分析、自动可视化、ARIMA 预测、BOLL 异常检测与 Tavily 实时新闻检索。
Hermes Local
Local-first Hermes Agent workspace with desktop UI, relay profiles, model health checks, and run tracing.
Archive Org API Knowledge Base
Internet Archive (archive.org) developer API as a queryable knowledge base for AI agents — Items, Metadata read/write, IA-S3 upload, Search & Scrape, Tasks/Changes/Views/Reviews,…
Stubborn
Stubborn — deterministic code context from SCIP symbol graphs
Lelouch
⚡ Absolute command over your AI agent's token budget — local-first compression of noisy tool output before it reaches the model. Claude Code / OpenCode / Codex / Gemini.
Agentcard
AgentCard — standardized identity & capability schema for AI agents. Rust reference implementation: github.com/kwailapt/aevum/tree/main/crates/agent-card
Tokenloom
Weave the live web into your context window — a fast, safe, token-efficient Rust CLI for LLM web search & page fetching
Mdingest
Ingest blog/article/newsletter pages (Medium, Dev.to, Substack) to clean Markdown for LLMs. HTTP API, CLI, and MCP server.
Wikiprompt Dataset
Open access to the wikiprompt.org catalog of 55,000+ AI prompts: dataset, API, MCP server and Claude skill. Build with it.
Orbyntiq
Local-first multi-agent AI platform with LangGraph, RAG, MCP, FastAPI, Angular, Ollama, Qdrant, Redis, MongoDB, and production observability.
Crossband
A group chat with several AI models at once. One shared transcript, shared tools, Claude Code as a summonable guest, and cost accounting that never sums metered and subscription s…
Trilha Engenharia Ia Aplicada
Currículo autoral e teoria-primeiro de Engenharia de IA Aplicada — 104 lições em 17 módulos, do zero (álgebra linear, ML) até LLMs, RAG, agentes e MCP, com exercícios e soluções…
Munch Food Agent
A food-ordering agent that can't order food you didn't approve. Guardrails between the LLM and the world: hard dietary/allergen blocks, spend caps, and a mandatory human confirmat…
XOne
XOne - The Open Agentic Studio
Factgate
The deterministic verification gate for AI research agents — fake CVEs 404, quotes must be on the page, a verified=yes it can't confirm is a FAIL.
Neurobase
Multi-DB conversational engine. Natural language → verified SQL on Postgres / MySQL / SQLite / MongoDB. Multi-agent pipeline, permission ladder, cost tracking. No .env required.
Oatda Skills
Claude Code plugin: 9 skills for OATDA unified LLM API gateway - text, vision, image, video, audio (TTS/STT/translation). 10+ providers, 1 API key.
Aindy Runtime
Self-hosted runtime for AI agents and workflows. Durable execution, capability-gated tools, human approval gates, and a memory system that accumulates. Runs survive restarts and r…
Agent Spine
Deterministic workflow engine for AI coding agents — declarative YAML pipelines.
Autonomous Research Agent
Autonomous AI Research Agent using LangGraph, MCP, Groq & Streamlit with cyclic research, tool calling, and self-critique.
Inferwatch
Real-time and historical metrics for locally served LLMs (Ollama and vLLM) — dashboard, HTTP API and MCP server. One process, one SQLite file, never in the request path.
Clau Browser Control
Chrome extension that drives your browser like a human — no CDP, no automation banner, passes bot detection. In-extension AI agent (bring your own key), record & replay Procedures…
Memento Gaia
GAIA benchmark result reproduction of Implementation of Memento (AgentFly)
Guardrailed AI Prospector
Automate sales prospecting with guarded AI agents for lead research, email drafting, scoring, and outreach workflows
Agentweld
Turn any MCP server into a curated, composable, A2A-ready agent.
Claude Code Quickstart
Claude Code in 12 minutes – terminal setup, install, project structure, copy-paste examples. Markdown + auto-built PDF.
Withallo
Read-only MCP server for the Allo API — query calls, transcripts, SMS & analytics from Claude, Cursor & any MCP client
Project Hawkeye
AI-powered pre-deployment testing platform. Autonomous agents execute visual QA tests against web applications inside observable Docker sandbox containers — no brittle recorded sc…
Beholder
The foundational SDK for algorithmic AI orchestration. The central nervous system powering the Enchanter ecosystem with native MCP support.
3 Distributed System MCP AI Incident Ethics Governance
🕸️ 3- Distributed MCP-based platform for AI incident analysis, with structured communication and traceability to support AI governance, Responsible AI and ethics-by-design.
Amira MCP Server
Read-only MCP server for AMIRA, the Africa Multiple Cluster of Excellence research-data platform on Omeka S — 26 tools over ~4,000 research items, 93 projects, 1,600+ people, publ…
Pentool MCP Server
MCP (stdio JSON-RPC) server for Pentool AI — local LLM assistant for pentest: pick checks, bypass WAF, find endpoints. Made for DrXOps/pentool.
Geospatial MCP
Open geospatial MCP standard for analyst, map, and app-builder workflows
Pager
Token-aware response paging for MCP servers. One line of code — large tool responses chunked and delivered page by page.
Iot Cloud MCP
MCP gateway that connects Claude/ChatGPT to Rogo IoT Cloud — 15 tools, OAuth 2.1, multi-tenant, Redis sessions
Tally MCP Read And Write
AI-powered natural language interface for Tally Prime ERP using Gemma 4 and Model Context Protocol.