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.
Skill Anywhere
Use Claude Skills from any MCP-compatible agent — progressive disclosure of skills via Model Context Protocol
LLM Prices
Zero-dependency Python CLI + MCP server for comparing LLM API costs across 144 models and 22 providers (OpenAI, Anthropic, Google, Mistral, xAI, DeepSeek, Groq...)
Data Forge
Turn any website into a quality-scored LLM fine-tuning dataset: crawl, chunk, generate Q&A, score, export to JSONL/Parquet/HF Hub. CLI plus MCP server.
Jr
A Jira CLI whose output is a versioned contract, built for scripts and agents first. It fails rather than guess: no silent truncation, no approximate answers. Jira Cloud and Data…
Rocky
A blind alien engineer who listens to your terminal, never forgets, and makes sure you still understand your own code.
Jev Compactor
Context compaction and safety gating for AI agents via TypeSafe Jev: keeps messages verbatim, no summarization. OpenAI, Anthropic, LangChain, CLI, MCP.
Crewai MCP Neighborhood Guide Agents
AI agent crew that generates hyper-local neighborhood guides with real estate data, crime stats, and lifestyle insights using CrewAI + 13 MCP servers + Google Gemini.
Linkdigest MCP
Xiaohongshu (RedNote) & Douyin links to text for AI agents: image-note OCR, transcripts + on-screen text, viral breakdown with verbatim-checked quotes. Hosted MCP + API, Python SD…
Remembra
🧠 External memory for AI assistants — facts, decisions, roles and history stored outside the context window. MCP server for OpenCode, Claude Code, Cline, Kimi Code.
Construction MCP
An offline Model Context Protocol server that gives AI assistants construction reference data and calculators. No dependencies, no network access.
Axiom Os
A domain-agnostic platform for building federated, AI-powered operational systems.
Macos Agent Smith
A safety-focused multi-agent workforce for your Mac: an orchestrator, workers with a real shell, a security agent that reviews every tool call, and independent acceptance validati…
Elasticemail Skills
Official agent skills for the Elastic Email REST API v4. Teach Claude and other AI assistants to send transactional and marketing emails and manage contacts, lists, templates, cam…
SsuAgent
자연어 요청을 MCP 도구로 라우팅하고 승인·스트리밍·대화 상태를 관리하는 에이전트 오케스트레이션 서비스
Cogniplane Core
AGPL-licensed multi-tenant agent platform. Self-host or use Cogniplane Cloud.
Agent Chaos
Fault injection toolkit for agent systems. Inject latency spikes, partial failures, 429s, malformed tool outputs, and stale context between agents and their tools. Scenario-driven…
Wigi LLM
Physical control surface for local LLM fleets — WigiDash buttons.json launcher for one-touch llama.cpp model switching, plus experimental C# widgets.
Night Shift
An automated data pipeline that captures user corrections to AI outputs and transforms them into reusable training data — so your AI learns from every edit.
Aura Ctx
One definition. Every AI tool. Yours.
Undercover
Undercover mode for AI agents — strips AI signatures from code and commits before pushing to open-source
Machine Internet
MCP endpoints for APIs that will never have documentation.
Visionagent
Multi-provider AI agent framework with vision capabilities and tool calling. Supports OpenAI, Anthropic, Google. Built-in Figma tools and Google Stitch integration. Type-safe with…
LLM Wiki Skills
Claude Code skills for llm-wiki — ingest, crystallize, research, lint, graph, and content workflows
CareerPilot Agent
Your personal AI CTO: Automates the journey from developer to intern by auditing code, suggesting gap-filling projects, and tracking 'Hirability Scores' through a modular agentic…
Topic Ia Gouvernance
Artefacts de recherche sur la constitution d’un espace de confiance documentaire pour outils conversationnels génératifs, à partir de briques publiques data.gouv.fr et du protocol…
Agentic Cognition
Longitudinal user modeling — living models of human consciousness for AI agents
Jcode Harness
Harness-first fork of jcode with embedded skills, local memory, safety gates, ACP/API orchestration, and multi-agent workflows
Mind Nerve
Intent-classification preselector for agent runtimes — decouples library size from token cost
Epicurus
Self-hosted, modular, local-first personal-assistant platform — an AI agent plus pluggable integration modules.
Clidex
CLI tool discovery for AI agents. Search, compare, and install 5,000+ command-line tools with structured YAML/JSON output.
Claude Code Quant Skills
Claude Code skills, slash commands, and hooks tuned for quant research, backtesting, and crypto trading workflows.
Ragbridge
Self-hosted RAG service with an HTTP API. Add retrieval-augmented search and chat to any existing application.
Delta Harness
Open-source agent harness for knowledge work: long-running AI agents with MCP tools, managed context, subagents and self-improvement in one lean TypeScript-on-Bun binary.
Claude Certified Architect Es
Preparación en español para las certificaciones Claude Certified Architect de Anthropic: Foundations (CCAR-F) y Professional (CCAR-P). 163 preguntas originales, guías de razonamie…
NL2PIPE
Open-source CLI that turns natural language into sandboxed, human-reviewed data pipelines with automated data-quality checks. Provider-agnostic (Anthropic/OpenAI/Gemini/OpenRouter…
Cognitive Os Agent
Cognitive OS Agent Runtime in pure C11 — LLM is the accelerator, not the OS. 认知智能体操作系统：认知内核 · Memory OS · 多智能体编排 · 事务执行 · 内嵌 Web 控制台
Todd
Self-hosted, bring-your-own-model multi-agent operator: describe an outcome, Todd spawns parallel agents with a sandbox, a signed-in browser, APIs and MCP tools, and asks before s…
Alpineagents
Python agent framework where the agent loop is a function you write
AI Connect SDK
The connectivity layer for AI builders: one Application, unlimited users, each with their own connectors and credentials, isolated and never exposed to Vinkius, with thousands of…
Agent Modpack
Download a ready-to-run AI-agent team you own. Works across Claude Code, Cursor, Codex and more, with no lock-in.
Contextcord
Local-first engineering continuity and bounded decision infrastructure for coding agents.
AI Agent Interview Question Bank
持续更新、来源可追溯、答案可协作维护的中文 AI Agent 开发面试题库
SchemaRouter
Typed capability retrieval and execution layer for RAG and LLM agents across OpenAPI, MCP, OPTIMADE, and Python tools.
Grandpa
Grandpa makes AI coding agents work smarter, not harder. Zero-bloat architecture, 8 skills, CLI scanner, and benchmark harness for 25+ AI agents.
AI Kubernetes Helm Chart Security
Evidence and data for the Sorami technical report on security defaults of 15 AI serving, vector database and MCP Helm charts on Kubernetes.
Enlil
Source-available control and audit plane for AI agent actions. Enforce what your agents may do, and prove what they did.
AI Agent Firewall
Local-first security firewall for autonomous AI coding agents — intercepts, risk-scores, and human-approves every tool call (Claude Code / Codex / Cursor / Cline). Apache-2.0.
AI Security Labs
Hands-on AI security labs. Build, break, understand.
Localcode
A coding agent that runs on your machine, on any model — and lets a second model check the first. Bedrock, Anthropic, and local LLMs; daemon with TUI, Web UI and desktop clients.
Agent Customer Service
基于LangGraph的智能客服Agent系统