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.
Llama Gradio Ui
Local-first Gradio 6 chat UI for llama.cpp with MCP tool-calling and an optional Presidio-based privacy shield.
Agentfit
Fit your messages into the LLM context window. Token-aware truncation with multiple strategies, pluggable tokenizers, zero deps.
Archaeologist
MCP server that excavates project history from commits, PRs, markdown, and AI-agent breadcrumbs — returns structured timelines and periodic reports for team updates and stakeh…
Cricket Intelligence
Just applying my learnings about Text2SQL, VectorDB, Knowledge Graph, MCP!
Beachead
Desktop app for managing AI agents in isolated Docker Sandbox microVMs
Agentic Rag Assistant
Production-grade RAG over arXiv AI/ML papers — LangGraph, hybrid retrieval + cross-encoder re-rank, RAGAS eval, Langfuse observability.
Proov
The coding agent that edits a sliver, not the whole file — a fast, low-cost terminal CLI. Anchor-edit engine never re-sends whole files (65–89% cheaper on large files). Any model…
LUCY CHENGJU
澄矩 · ChengJu（工坊·一法）— 工业智能质量控制工作站：IQS-DSL · AI 推理 · MCP 渲染 · 14 类 QC 图 | 鹿溪联合创新实验室出品
AI Coding Assistant
Provider-agnostic Python CLI coding agent with ReAct tool use, Plan Mode, MCP, Safe Mode, and on-demand RAG.
Env2llm
Generate environment maps (services, artifacts, env vars) for LLM decision-making
Mokai Brain Kit
On-premises AI knowledge kit — shared brain gateway, LLM wiki synthesis, evolving relation graph. MIT.
AI Sdlc Prompts
AI-SDLC Pro — Biblioteca de Prompts de Ingeniería de Software
VortoCode
Self-hosted AI coding agent: one agent runtime behind Desktop, TUI, Web and headless CLI. Delegated dev tasks run in isolated git worktrees with verification and PR handoff; human…
Nutricoach AI
iOS AI diet-coach powered by MiniMax-M3 — HealthKit integration, persistent memory and specialised MCPs. App Store soon.
Algitex
Progressive algorithmization toolchain — from LLM to deterministic code, from proxy to tickets
AI Codebase Vectorizer
RepoMap AI 2026: Map Codebases for AI Assistants Beyond Window Limits
Local AI Stack
🔍 Build local AI infrastructure on M2 MacBook Air with zero cloud dependencies, ensuring unlimited usage and complete privacy.
SpanLedger
An out-of-band auditor that proves whether your OpenTelemetry pipeline actually delivered what it claims to.
RogueAgent Testbed
Georgia Tech master's in cybersecurity research on cascading indirect prompt injection attacks. Author: Fahid Ahmed
Anomaly AI Agent
Anomaly - a desktop AI agent built with Electron, React, Vite and TypeScript. ChatGPT-style web search with citations and a Sources panel, sub-agents, skills, 15+ tools, MCP suppo…
Retail Investor Agent
A LLM agent that gives beginner investors a broad, honest second opinion — plain-language explanations, precise numbers computed by built-in tools, citations, and a built-in bear…
Graphscout
Cached, incremental code-graph maps so AI agents query code structure instead of reading whole files. CLI + MCP, wires into Claude Code, Codex, Gemini CLI, Cursor. Auto-sync watch…
Data Analysis Agent Backend
Local-first AI data analysis agent backend with multi-source data access, statistical modeling, RAG, visualization, and report generation.
AI Restaurant Food Planner
AI-powered restaurant search and recommendation platform with pgvector semantic search, multi-factor scoring, and LLM review Q&A — Flask + Databricks Lakebase.
Okft
okft — lint and MCP-serve Open Knowledge Format (OKF) bundles. Spec validator + agent server for Google's OKF v0.1.
Durable Agent Runtime
Durable execution runtime for AI agents. Checkpointed state, idempotent tool calls, compensation instead of naive retries, human-in-the-loop escalation, MCP tool boundary, and Ope…
Research Papers
MCP research assistant for discovering arXiv papers through FastMCP, Groq and structured tool calling.
Pgvector Search
Hybrid RAG over pgvector, exposed as MCP tools — semantic and keyword search fused with Reciprocal Rank Fusion
Cdp MCP Gateway
CDP-to-MCP Gateway: Connect active Chrome instances to Model Context Protocol (MCP) servers for LLM browser control.
Joomla AI Autoposter
One-command Joomla autoposting pipeline: LLM article → validation → Playwright publishing → Yandex.Webmaster re-crawl
Khwan Chat
Reference chat app built on the Khwan loop — prepare → your model → record, with the answer-gate wired in
LocalFleet
LocalFleet - a local-first team of AI bots in a chat app: LM Studio + GitHub Copilot engines, per-bot desktop containers on a shared filesystem, routines, and an Electron tray. In…
Foral
Foral runner — typed, governed MCP capabilities for systems without public APIs. Apache-2.0.
Furlpay Bot
Persistent AI teammates with a computer, memory, and voice — web, desktop, and mobile. Self-hostable, bring your own model and sandbox.
Tracefrugal
Measure Claude Code and Codex usage. Try reversible local Claude optimizations with version checks, hourly comparisons and quality history. Go, EN/KO.
Mml Composemusic MCP
レトロチップ音源（2A03 APU）風のMMLをLLMに作曲させるためのMCPサーバです
CallLens
Open-source conversation intelligence and evidence-backed call scoring powered by LangGraph.
Skillexec
A binary container for agent skills: SKILL.md compiled into a signed, tiered, content-addressed graph — with capability-gated wasm segments and an organization compiler.
PyStreamMCP
Intelligence layer for AI agents. Query planning, context discovery, cost optimization. 60-75% token reduction while maintaining quality.
AI Agent Template
Production-grade LangGraph + Claude Agent SDK + MCP starter. Multi-agent orchestration, Ragas evaluation, observability. Used in production at Haleon.
Reconmind
Multi-agent, RAG-powered copilot that investigates data pipeline incidents (key drift, duplicate submissions, schema drift, volume anomalies) and writes the incident report.
DataOps Investigator
Evidence driven AI agent for investigating data system incidents using LLM planning, MCP-based evidence collection, and deterministic root-cause analysis.
Jichi
自治（じち） jichi means autonomy / self-government, and a rarer, literary homophone 自知（じち） reads as self-knowledge. jichi is a complete AI coding agent in C, conforming to the C89 (ANS…
Job Copilot Backend
FastAPI backend that scores a resume against a job description using Claude. Agentic RAG over Qdrant (Voyage embeddings + reranking), tool calling, MCP logging, prompt caching, SS…
Jupiter Autonomous Agent
Always-on personal Claude Code agent: shared usage budget, memory bus, script-first pulses, phone access, self-review. Install and go.
Cordy
A cross-platform TUI coding agent in Rust — hot-swap any model/provider mid-conversation, MCP, skills, sub-agents, background jobs, and an OpenCode-inspired interface.
AgentGym
A verifiable Kubernetes incident gym for post-training and serving tool-using agents. Real control plane, deterministic workload simulator, executable rewards.
Ferrule
A portable, single-binary agent runtime with per-model harness profiles, structured context compaction, and hybrid memory — written in Rust.
Ungrounded
Measure how often your LLM agent reaches for the wrong tool when it can't ground an entity in a request.
DevAgent
AI coding agent that reproduces a GitHub issue with a failing test, fixes it in a no-network Docker sandbox, and opens a draft PR only after human approval. FastAPI + Next.js, MCP…