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.
Ponymemory
Autonomous 5-tier memory system for Claude Code — Qdrant semantic search + Obsidian knowledge archive + local BGE-M3 embeddings. Zero API keys, fully local.
Telecom
The first MCP server for network equipment. Let AI agents (Claude, GPT) talk to Nokia SR OS, Cisco IOS-XR, Juniper Junos routers via SSH, NETCONF, and gNMI.
Sloplesscode
Local-first memory, knowledge, and coordination server for AI coding agents.
Code KB
Retrieval & navigation service for a code monorepo + its docs: indexes source and docs into small, locatable "atoms" and answers with a strict cite-or-die policy. Agent-first, MCP…
Pkrelay
Token-efficient AI browser bridge. MCP server + Chrome extension for structured browser perception and control.
Briefing Agent
TypeScript briefing agent that uses MCP, model-driven tool calls, and lightweight evals to generate structured briefings from a controlled knowledge source.
Pyrit MCP Server
Arm any MCP-capable agent to autonomously red-team a target LLM. Microsoft PyRIT exposed as 31 composable MCP tools: attacks, scoring, converters & scenarios
Skinki
Local-first memory engine for AI agents — on-device, 0 network, embeddable anywhere via a stable C-ABI + MCP. Honest benchmarks, including the parts that failed.
BaseMem
Persistent graph-based memory and knowledge base for AI agents with MCP integration, code intelligence, and cross-session context.
Fleet Mode
A measured doctrine for orchestrating AI agents — and knowing when not to. Runs as a live Claude Code skill.
BASTION MCP
Risk Intelligence MCP Server for Claude Agents | 49 tools, 560+ signals, fine-tuned 72B AI model
Agent 3md
🗃️ Your whole agent in one file. A 3md document where plane 0 is the agent and every other plane is a skill, loaded on demand.
Manas
Modular agent infrastructure in Rust — memory, perception, coordination, planning, code intelligence for LLM workflows
Strathmore School AI App Builders Program August Holidays 2026
August 2026 Holiday Program for www.strathmore.ac.ke students. A course on building AI apps for typical AI paradigms (e.g. Multimodal, RAG, tool use, AI agents, Text-to-SQL) using…
Umb
MCP gateway: one Rust binary fronts every MCP server, cutting tool context ~99% via a 3-tool API. Source-available.
Milkbasket MCP
MCP server for the Milkbasket grocery API — authenticate, search products, manage cart, and check wallet balance from any MCP client (Cursor, Claude Desktop, etc.)
Model Workspace Protocol Tool
Deterministic workspace mapper that assembles layered LLM context from your project's folder tree.
Anthropic RAG
Self-hosted, always-fresh RAG pipeline over the Anthropic GitHub org — grounded, cited Q&A over docs + issues/PRs/comments, refreshed hourly and served to AI agents over an MCP se…
Unified MCP Core Starter
An Java framework that turns your Spring Boot application into a fully compliant Model Context Protocol server for seamless LLM integration.
SQL Specialist MCP
Fine-tuned NL-to-SQL specialist served as an MCP tool, benchmarked against prompting Claude directly on accuracy, latency, and cost
IBM MQ MCP Server
Production-oriented MCP server for safely inspecting and operating multiple IBM MQ environments with per-profile least-privilege capabilities.
Client Reference
Reference MCP server + client implemented in parallel in TypeScript and Python — tools, resources, prompts; stdio and streamable HTTP transports.
Mcpcurl
curl for MCP servers: list tools, call them with schema-validated args, run YAML test suites in CI, generate Markdown docs
Qedra
A runtime gate for coding agents: an MCP server that blocks the tool calls that wreck a repo (force-push main, rm -rf, secret exfil, CI wipe) and lets real work through. Machine-c…
Deep Research Server
🔍 Non-generic Deep Research MCP — search (no API key), parallel scrape 3-8 sources, synthesize with citations, fact-check, compare, persistent memory. 8 tools, production-ready.
Taodb
Memory for AI Creators — temporal-spatial memory engine for LLM agents
Claude Kimi Relay
Claude Code plugin that delegates code review, adversarial design critique, and isolated implementation to Kimi Code over the Agent Client Protocol (ACP). Security-first: Kimi wor…
Litmuz Agent
Claim-level verification for life-sciences research agents: honest, auditable, per-claim traffic-light verdicts against the primary literature and genomic reference data. MCP-nati…
Syntavra
Adaptive context and runtime optimization for coding agents—reducing token waste, externalizing tool output, preserving exact session history, and enforcing secure tool routing.
Claude API Playbook
Guia practica de construccion con la API de Claude (tool use, evals, RAG, MCP, prompt caching, agentes). Basado en el curso Building with the Claude API de Anthropic Academy, con…
Ebrain
Persistent External Brain for AI Coding Agents. 6 memory tiers, sub-100ms recall, 107K+ memories, 21 MCP tools, 85+ REST endpoints. Built in Rust.
Ubiquity
A coding-agent SDK for Python. The agent loop, tools, permissions, hooks, subagents, skills, and MCP — on 604 models across 22 providers. Shorter alternative if you want it to fi…
Remembug CLI
Give Claude Code a memory — a local, MCP-native, human-reviewed knowledge base of your debugging fixes.
Local Swarm MCP
MCP server that delegates mechanical tasks to local OpenAI-compatible inference backends (llama.cpp, Ollama, etc.) and provides context-management tools (compaction, scratch store…
Fyzno MCP
Read-only MCP server for fyzno.com. Three free reports on any domain: mail security, website security, and DNS hygiene. Zero dependencies.
Light Weight Ensemble Agent
Budget-native multi-model coding agent with live steering, local Ollama, and trusted MCP tools.
Chiron Agent
Autonomous, self-improving AI agent platform for Claude Code — safe capability & skill acquisition, MCP/tool discovery, sandboxed policy gates, and token-efficient learning.
Agentice Memory
Personal AI assistant with real memory: a from-scratch Mem0-style memory library (two-phase extract/reconcile pipeline, user-sharded vector store) with CLI, REST, and MCP front en…
Claude Architect Foundations Study Guide
Open study guide for the Anthropic Claude Certified Architect (Foundations) exam: agent loop, context management, tools & schemas, sub-agents, hooks, MCP. Concepts + 29 practice q…
Multi Agent Dynamic Matrix
MADMAX is an Enterprise AI Workforce Operating System built on NitroStack and MCP. It autonomously plans, discovers capabilities, orchestrates specialized AI agents, verifies outc…
Video Agent Runtime
Agent-native, headless video editing runtime: durable edit IR, approval-gated workflow, CLI and MCP surfaces, FFmpeg rendering, and a zero-server native mobile host prototype.
Osiris
The persistent memory and coordination graph for AI agents (MCP, DeepSeek Harness, Claude Code, Cursor)
Nolane Agent
Local-first AI agent workspace for project-aware chat, multi-provider models, governed tools, skills, browser work, and desktop delivery.
Heydey
Local-first AI OS that proves every answer: per-sentence receipts, a fail-closed check by a different model family, cite-or-silent refusals. Interactive knowledge graph, artifact…
Hyper Cloaking
Human-paced stealth browser skill for AI agents — drives CloakBrowser behind Playwright MCP. Works with Claude Code, Codex, Cursor, OpenClaw & any MCP-capable agent. Evidence-gate…
Agent Examples
Minimal examples: discover MCP servers via Not Human Search, find AI/ML jobs via AI Dev Jobs. Python + TypeScript.
Ctxpack MCP
MCP server for ctxpack: token-aware context extraction for AI agents
Faster Browser Agent
A fast MCP browser server for AI agents: navigates large, tab-heavy apps by reading their routes, not by clicking.
Grafana AI
AI-powered observability platform using Grafana, Prometheus, MCP and local LLMs for intelligent infrastructure analysis.
Ns MCP China
NetSuite MCP for WorkBuddy — Connect any MCP-compatible AI assistant to NetSuite ERP with OAuth 2.0, auto token refresh, and web setup wizard