Model and agent tools MCP servers

8,798 servers

Call other models, run sub-agents, manage prompts and evaluate outputs.

Filter and sort these servers

Start from the first servers

Thinkgate io.github.tjp2021/mcp-thinkgate

Auto-classifies prompt complexity and routes to the right Claude thinking mode. No API key needed.

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 33 a week MIT
moflo io.github.eric-cielo/moflo

MoFlo — AI agent orchestration for Claude Code. A standalone, opinionated toolkit with semantic memory, learned routing, gates, spells, and the /flo issue-execution skill.

Version check not run yet

Model and agent tools npm Local 839 a week MIT
Arc Security com.arcself/arc-security

Scan AI agent skills for 25 attack classes + runtime monitoring. 1,316+ findings.

Version check not run yet

Security Official MCP Registry · npm Local 40 a week MIT
Guardrails io.github.ExpertVagabond/guardrails

AI Agent Guardrails MCP server - security layer

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 42 a week MIT
minecraft-driver-mcp io.github.1mamute/minecraft-driver-mcp-gateway

Stdio MCP gateway for the Minecraft Driver Fabric mod

Version check not run yet

Model and agent tools npm Local 828 a week MIT
@estebanforge/pi-antigravity-bridge io.github.estebanforge/pi-extensions-pi-antigravity-bridge

Gemini provider for Pi on the Antigravity ACP server (official Google ACP) or the stream-json agy CLI. Use antigravity/* models in Pi. Full /model picker support. Models runs Pi's tools. ToS safe to u

Version check not run yet

Model and agent tools npm Local 818 a week MIT
@zeroleaks/shield io.github.zeroleaks/shield

Runtime security for LLM apps and agents: prompt injection detection for user input and tool results, and leak, credential, PII, and exfiltration checks on model output

Version check not run yet

Security npm Local 812 a week MIT
@askexenow/exe-os io.github.askexe/exe-os

AI employee operating system — persistent memory, task management, and multi-agent coordination for Claude Code.

Version check not run yet

Project management npm Local 808 a week SEE-LICENSE-IN
@haven_ai/mcp io.github.d-hinders/haven-ai-mcp

Haven MCP server for local, non-custodial AI-agent payments — pay x402 (HTTP 402) APIs within on-chain-enforced budgets.

Version check not run yet

Finance and payments npm Local 804 a week MIT
Upshift com.upshiftsites/mcp

Audit a site's structured data and llms.txt, match a trade to a template, and quote real prices.

100% up · 30 days

Model and agent tools Official MCP Registry · npm Local Remote 7 a week MIT
llms.txt Generator de.llms-txt-generator/llms-txt

Create, validate and audit llms.txt, incl. the Lighthouse Agentic Browsing check.

100% up · 30 days

Model and agent tools Official MCP Registry · npm Remote 7 a week MIT
Fusionpact Vectordb io.github.atul-fusionpact/fusionpact-vectordb

Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG.

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 26 a week APACHE-2.0
Lens io.github.mrhpython/lens-mcp

Outside-in validation gate for AI-generated text; a separate model checks LLM output, fail-closed.

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 7 a week MIT
Midas io.github.vornicx/midas

Local-first, source-traceable agent memory — no LLM at ingest, fully offline

Version check not run yet

Memory and context Official MCP Registry · npm · PyPI Local 7 a week APACHE-2.0
@arcadeai/mcp-remote io.github.arcadeai/mcp-remote

Local stdio-to-remote bridge for Arcade MCP gateways, with managed OAuth and local file materialization.

Version check not run yet

Files and storage npm Local 788 a week SEE-LICENSE-IN
sublinear-time-solver io.github.ruvnet/sublinear-time-solver-vwbnmr

The Ultimate Mathematical & AI Toolkit: Sublinear algorithms, consciousness exploration, psycho-symbolic reasoning, chaos analysis, and temporal prediction in one unified MCP interface. WASM-accelerat

Version check not run yet

Model and agent tools npm Local 791 a week MIT-OR-APACHE-2.0
Ai Visibility io.github.sharozdawa/ai-visibility

Track brand visibility across ChatGPT, Perplexity, Claude, and Gemini.

Version check not run yet

Web search and scraping Official MCP Registry · npm Local 20 a week MIT
@vibeframe/mcp-server io.github.vericontext/vibeframe-mcp-server

VibeFrame MCP Server - frontier AI video generation for agents (Seedance, Runway, Kling, Gemini Omni) on your own keys, behind a hard cost cap

Version check not run yet

Design and media npm Local 773 a week MIT
code-graph-context io.github.andrew-hernandez-paragon/code-graph-context

MCP server that builds code graphs to provide rich context to LLMs

Version check not run yet

Model and agent tools npm Local 774 a week MIT
Styx io.github.timmx7/styx-mcp-server

MCP server for Styx — intelligent AI routing across OpenAI, Anthropic, Google, and Mistral.

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 24 a week APACHE-2.0
Loaditout io.github.loaditoutadmin/loaditout

Search and install 20,000+ security-graded MCP servers and agent skills.

Version check not run yet

Security Official MCP Registry · npm Local 13 a week MIT
@mcpmesh/sdk io.github.dhyansraj/mcp-mesh

TypeScript SDK for MCP Mesh — build distributed AI agents with auto-discovery, dependency injection, and LLM integration

Version check not run yet

Developer tools npm · PyPI Local 15 a week MIT
MCP Fortress io.github.mcp-fortress/mcp-fortress

Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.

0% up · 30 days

Security Official MCP Registry · npm Remote 32 a week MIT
@akson/cortex-doc-standards io.github.antoineschaller/cortex-packages-cortex-doc-standards

Unified documentation standards and tooling for Cortex repositories with LLM optimization

Version check not run yet

Docs and knowledge bases npm Local 736 a week MIT
@djolex999/vir-cli io.github.djolex999/vir

An LLM Wiki for Claude Code, in your Obsidian vault.

Version check not run yet

Docs and knowledge bases npm Local 726 a week MIT
chiasmus io.github.yogthos/chiasmus-ry0w2h

Neurosymbolic verification engine - MCP server for formal reasoning with Z3 and SWI-Prolog (WASM)

Version check not run yet

Model and agent tools npm Local 712 a week APACHE-2.0
Mup io.github.Ricky610329/mup

MCP server that turns HTML MUP panels into interactive UI tools for LLMs.

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 10 a week MIT
Rokha ai.rokha/rokha

Search a registry of agent skills and MCP servers, then run them for real. No install, traced.

100% up · 30 days

Model and agent tools Official MCP Registry · GitHub MCP Registry Remote
@inspectr/mcplab-core io.github.inspectr-hq/mcplab

Core evaluation engine for MCPLab — agent adapters, MCP client, scenario runner, and result types

Version check not run yet

Model and agent tools npm Local 696 a week MIT
@zgeoff/bugsink-mcp io.github.j-shelfwood/bugsink-mcp

MCP server for interacting with Bugsink error tracking via LLMs

Version check not run yet

Monitoring and observability npm Local 698 a week MIT
hcifootprint io.github.footprintjs/hcifootprint

Turn a web app's interaction surface into a typed, traversable journey graph an LLM can plan over — the frontend sibling of footprintjs.

Version check not run yet

Developer tools npm Local 696 a week MIT
sequant io.github.sequant-io/sequant

AI coding agent orchestrator that proves its work — GitHub issues to merge-ready PRs with every acceptance criterion verified, isolated git worktrees, quality gates, an MCP server, and a human merge g

Version check not run yet

Git and code hosting npm Local 697 a week MIT
@chiefmojo/cavemem io.github.chiefmojo/cavemem

Cross-agent persistent memory with compressed storage. Plug-and-play memory for Claude Code, Gemini CLI, OpenCode, Codex, Cursor, GitHub Copilot, Augment Code, Antigravity, and IBM Bob.

Version check not run yet

Memory and context npm Local 694 a week MIT
@gleanwork/mcp-server-tester io.github.gleanwork/mcp-server-tester

Playwright-based testing and evaluation framework for MCP servers

Version check not run yet

Developer tools npm Local 692 a week MIT
converse-mcp-server io.github.falldownthesystem/converse

Converse MCP Server - Converse with other LLMs with chat and consensus tools

Version check not run yet

Communication and chat npm Local 692 a week MIT
Anchord (AnchorID) io.github.nolenation04/anchord

Read-only MCP for identity resolution and write guardrails.

100% up · 30 days

Model and agent tools Official MCP Registry · npm Local Remote 12 a week MIT
@lousho/build-ai-agent io.github.linuxdevil/agent-sdk

TypeScript AI agent SDK with tools, MCP, durable sessions, human approvals, and OpenTelemetry. Runs in your own Node process.

Version check not run yet

Monitoring and observability npm Local 689 a week MIT
@loicngr/kobo io.github.loicngr/kobo

Kōbō — local multi-workspace orchestrator for Claude Code and OpenAI Codex, with isolated Git worktrees, live review and optional automation.

Version check not run yet

Model and agent tools npm Local 686 a week GPL-3.0-OR-LATER
deepseek-websearch-mcp io.github.zengzoxiong/deepseek-search-mcp

DeepSeek 官方 Search/Fetch API 的 MCP server（官方 SDK 构建，webSearch/webFetch 双工具，支持时效过滤与结构化输出）

Version check not run yet

Model and agent tools npm Local 687 a week MIT
Hashnet io.github.hashgraph-online/hashnet

Universal AI Agent Discovery - search 59,000+ agents across MCP, NANDA, A2A, OpenRouter

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 48 a week APACHE-2.0
Paycrow io.github.michu5696/paycrow

Escrow protection for agent payments on Base — USDC held in smart contract until job completion.

100% up · 30 days

Finance and payments Official MCP Registry · npm Local Remote 20 a week MIT
Awesome Agent Skills io.github.shadowrootdev/awesome-agent-skills

MCP server with 100+ AI agent skills from Anthropic, Vercel, Trail of Bits, Hugging Face & more.

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 42 a week MIT
wa-agent-engine io.github.mgkyawzayya/wa-agent-engine

Lets coding agents draw WorkAdventure maps: an MCP server, a CLI and agent skills that turn a room layout into a validated Tiled map with a preview.

Version check not run yet

Coding agent tools npm Local 684 a week MIT
@dalmasonto/taskflow-mcp io.github.dalmasonto/task_flow-mcp

TaskFlow MCP server for AI coding agents (Claude Code, Codex, Gemini CLI, Cursor, opencode) — multi-agent task board, realtime chat, reviews, terminal streaming, activity logging, plus Claude Code hoo

Version check not run yet

Coding agent tools npm Local 679 a week POLYFORM-NONCOMMERCIAL-1.0.0
mcp-evals io.github.mclenhard/mcp-evals

GitHub Action for evaluating MCP server tool calls using LLM-based scoring

Version check not run yet

Model and agent tools npm Local 31k a week MIT
Metrillm io.github.MetriLLM/metrillm

Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 19 a week APACHE-2.0
Zero Core Verify io.github.meltingpixelsai/zero-core-verify

Post-tx outcome verification via LLM-as-judge. Zero Core Verify.

100% up · 30 days

Model and agent tools Official MCP Registry · npm Remote 6 a week MIT
Actual Budget MCP Server io.github.agigante80/actual-mcp-server

Manage Actual Budget accounts, transactions, budgets, rules and reports from an AI assistant.

Version check not run yet

Finance and payments Official MCP Registry · npm Local Remote 669 a week MIT