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.
Python Codemode MCP
A Python adaptation of the Code Mode MCP pattern for local agent stacks — built for macOS + iTerm2.
Data Synth
Seed-to-scale LLM synthetic data engine with auto-detected templates, schema validation & quality-diversity optimization. CLI + MCP ready.
Mini Omega Lock
Measure your LLM judge's noise floor — an A/B improvement smaller than the judge's own noise isn't real. Pre-flight probes for prompt-eval setups; works standalone and with omegap…
Mnemosyne Engine
A production-grade LLM context compression and retrieval engine built entirely on the Python standard library. It solves the single biggest bottleneck in LLM agent effectiveness:…
App Surgeon
☰ FutЯøn ☰ | Reverse-engineer, customize, and add features to any installed app. Patches compiled code, injects custom UI, translates code between 30+ languages. LLM-agnostic — wo…
Behavioral Memory
Behavioral Memory for Tool Orchestration — Validated execution traces as memory for MCP-based agent systems. Based on IEEE paper.
NirmahGTM
AI reasoning engine for Clay: auto-detects 5 GTM buying signals, scores with calibrated LLMs, outputs evidence-backed openers/hooks/CRM sync governed, cached, evaluated.
ConstraintMCP
Hard enforcement for AI coding agents. SPEC.md rules that actually can't be broken.
Ecommerce Operator Playbooks
Evidence-first AI playbooks for ecommerce operators — free to read, one prompt to run.
IntelliRide Spring AI
IntelliRide — Agentic AI ride-Booking backend (Java, Spring Boot, Spring AI, PostgreSQL/pgvector) Built a multi-agent system (supervisor + specialized Rider/Driver/Support agents…
TangleBrain
A local-first, config-driven LLM router across OpenAI-compatible backends you own.
Prx
The agent-run work-unit CLI: capability-scoped agents whose every privileged effect is verified against its signed owner, driving a work unit through one signed pipeline to a merg…
Fugu
Zero-dependency TypeScript client + CLI for the Sakana Fugu OpenAI-compatible API (Responses + Chat Completions).
Tares Cookbooks
Companion cookbooks that take a provider's agent, swap only its read path for one NavFlow query, and measure the difference on a real running system. Includes a self-contained SRE…
Super AI Agent
Build an AI agent platform with Spring Boot, Spring AI, and Vue for chat, RAG search, tool use, and document processing
Noricum
C-to-Rust migration CLI — LLM agents translate C to idiomatic, safe Rust (0 unsafe blocks) with byte-exact differential testing
AI Orchestration MCP Rag N8n
n8n AI orchestration system using MCP, Pinecone RAG, Google Drive ingestion, OpenAI embeddings, and interaction logging.
Awesome Agent Client
A curated list of desktop, IDE, extension, and terminal clients for AI agents.
Uapi Agent Skills
Official UAPI Agent Skills (86 single-endpoint skills for uapis.cn). Install with: npx skills add AxT-Team/uapi-agent-skills
AI Setup Patterns
Where monolithic AI assistants hit their limits in production — and what to build instead.
Building Agent Study
一个系统学习 Agent 工程的中文项目：从理论到实践，由浅入深。
ZeroHuman Agency
Self-hosted AI content team — research, score, draft, multi-agent review, publish. Learns from your social metrics. You approve every post.
Memory Xx
memory-xx 是一套面向 AI Agent 的长期记忆框架，用来让 Codex、Claude Code、OpenClaw 等本地或多 Agent 系统安全地记录、更新和召回长期记忆。
Dong AI Company
Cross-project memory and organizational governance for any AI agent. pip install dong-ai.
Agentic Agile
Claude Code plugin for agentic agile + autonomous TDD: hook-enforced AI coding agents that plan sprints, then write code RED→GREEN with deterministic gates. Agentic workflow for L…
Devmemory Agent
AI agent with persistent memory across dev sessions — built on Qwen Cloud
Yatra Multi Agent AI Travel Assistant
Production-grade multi-agent AI travel assistant — 5 agents, MCP, RAG, Kafka, Supabase, Pinecone
Memkeeper Harness
Memkeeper: Harness — a local-first task ledger, dispatcher, and runner for coordinating AI agent workforces. Goals, tasks, and dependencies under TTL leases, with evidence and an…
Cachly Rust
Official Rust SDK for cachly — persistent AI memory and managed Valkey/Redis with semantic caching. Free tier, EU-hosted.
Go Toolbroker
In-process Go library for intent-aware MCP tool selection: keyword intent detection, priority-ordered selection rules, token-budget pruning, and a per-tool enrichment pipeline.
Zk Agent
AI agent that classifies conversation insights into Zettelkasten notes and saves to Heptabase or Obsidian
Claf
CLAF — Closed-Loop Agent Framework. Anthropic's skin, your brain. Off-grid by default; cloud convenience optional.
Prompt Gate
Control plane for safely exposing LLM providers to your teams
Tokencompress
🔐 Local, zero-cloud token & text compression for LLM prompts and logs. Offline rules + optional local Ollama semantic + lossless gzip. MCP / HTTP / CLI / library. 中文友好。
Top Industrial AI Agents
Curated list of LLM-agent projects, tools, benchmarks for industrial OT — SCADA, MES, historians, industrial protocols
Web Agent
Local-first web & desktop automation toolkit: browser automation, video transcription, local OCR & VLM vision, desktop control — 数据全部本地处理，零上传
Talk August 19
Live demos and write-up for "How to Cut API Costs Without Compromising Agent Reliability" — prompt caching and MCP tool search, measured against real providers.
Loop Studio
Loop Studio - A Loop Engineering Engine with Verify-Separation and Quality Gates for Multi-Agent Software Delivery
Remora
🐟 Wireshark for AI agents — a local, zero-config proxy that taps LLM + MCP traffic and renders it on a live timeline. See what your agent is actually doing.
Sandbase Docs
Official SandBase developer documentation: one API for LLMs, image, video, audio, embeddings, real-world APIs, and reusable Agents.
Chief
Your agents plan, you approve, Chief keeps the record. A local tracker for agentic workflows: plans arrive as drafts, mid-run changes pause for your decision, everything lands in…
Concord
An open-source AI-native platform that connects your existing DevSecOps tools through intelligent MCP agents — turning fragmented signals into instant root cause, fixes, and compl…
AI Agent Architecture 2026
Reference architecture for enterprise AI agent systems in 2026. MCP-first, framework-agnostic, built for regulated industries.
Thetacog MCP
npx thetacog-mcp — a decidable, on-chip, LLM-free placement receipt a stranger recomputes byte-for-byte. Free for builders; patent-licensed for production & financial use (US Pate…
Makmolga
마인크래프트 완전몰입형 가상현실을 향한 LLM 동료 — Fabric 26.2 · Mineflayer · MCP
DevWit
Lean-context AI-native desktop IDE: multi-agent orchestration, authorization gate, transparent context & MCP. 747 unit tests, 3 platforms.
SoAI
An OpenAI and Anthropic-compatible API in front of llama.cpp, Ollama, vLLM and remote providers, with on-demand backends, queuing, failover and load balancing. Also includes a mul…
Lawclaw
面向中国执业律师的桌面 AI 智能体（Tauri + Vue 3 + Python/Hermes）：案件台账·文书校对·法条引用验证·期限与日程·值守提醒
Skilltest
SkillTest: test framework and CI gate for AI agent skills (SKILL.md) — the engine behind skillemall.ai
KBase
私有化交付的 B 端知识库系统：单租户，Docker Compose 一键部署，纯 CPU 可离线跑。RAG 全链路开箱即用——混合检索+重排，引用溯源到页码/章节/表格/插图；扫描件 OCR 与满血 VLM 深度解析、表格原子分块、飞书 wiki 整树导入（含画板）。Embedding/向量库/LLM/OCR/分块器全插槽；RBAC+库级 ACL+SSO…