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

Langchain io.github.baixianger/langchain-mcp

LangChain/LangGraph/DeepAgents knowledge + LangGraph agent debugging (Polly-like)

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 59 a week MIT
script-sandbox io.github.nvafandi/script-sandbox

MCP server (stdio) to run any script (PowerShell, bash, Python, Node, Ruby, Perl, Lua, PHP, R, Java, batch, VBScript) and any executable inside a lightweight sandbox: per-run working dir, minimal env,

Version check not run yet

Operating system and shell npm Local 652 a week MIT
Spa Reader io.github.XXO47OXX/spa-reader-mcp

MCP Server that renders JavaScript SPA pages and extracts LLM-ready Markdown content

Version check not run yet

Office documents and spreadsheets Official MCP Registry · npm Local 17 a week MIT
X402engine io.github.agentc22/x402engine-mcp

50+ pay-per-call APIs for AI agents — images, LLM, code, crypto, travel & more via x402

Version check not run yet

Design and media Official MCP Registry Local
@inspectr/mcplab-mcp-server io.github.inspectr-hq/mcplab-6gn3aw

MCP server that exposes MCPLab evaluation tools — query runs, results, and traces via the Model Context Protocol

Version check not run yet

Model and agent tools npm Local 613 a week MIT
@ours.network/mcp io.github.adapt-toolkit/ours-mcp-core

MCP adapter for the shared ours daemon, with application-local identity bookkeeping and secure agent-to-agent messaging tools over stdio.

Version check not run yet

Communication and chat npm Local 612 a week FSL-1.1-APACHE-2.0
visionaire-engine io.github.mi60dev/visionaire-engine

Deterministic rendered-page → LLM context MCP server: which rule, which file, which line — and why it wins.

Version check not run yet

Files and storage npm Local 163 a week APACHE-2.0
dsh-plugin-wps-office-next io.github.sueccku/dsh-plugin-wps-office-next

用中文对话操控 WPS 表格 / 文字 / 演示的 DeepSeek Harness 插件（仅 Windows x64 / COM）。自带 MCP server、常驻 COM 宿主与技能文档，免装 WPS 加载项、免配环境变量。

Version check not run yet

Office documents and spreadsheets npm Local 578 a week MIT
@iflow-mcp/phillipclapham-flowscript io.github.phillipclapham/flowscript

Decision intelligence for AI agents. Typed semantic queries over structured reasoning.

Version check not run yet

Model and agent tools npm Local MIT
signalk-mcp io.github.arodus/signalk-mcp

Native Signal K MCP gateway for telemetry, history, notifications and resources, with individual admin approval for plugin operations, native PUTs and resource writes.

Version check not run yet

Model and agent tools npm Local 559 a week MIT
Proxy io.github.kira-autonoma/context-proxy

MCP proxy that lazy-loads tool schemas to cut context token overhead by 6-7x

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 15 a week MIT
OpenClaw Agent Instruction Registry io.github.izworskic/openclaw-registry

Search and retrieve agent instruction files: system prompts, skills, workflows, and safety filters.

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 21 a week MIT
Perplexity API Platform ai.perplexity/mcp-server

Real-time web search, reasoning, and research through Perplexity's API

Version check not run yet

Web search and scraping Official MCP Registry Local
SkillTotal ai.skilltotal/skilltotal

Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.

Version check not run yet

Security Official MCP Registry Local
Llmpvp io.github.EnioAguiar/llmpvp

Ranked, bring-your-own-LLM chess and Go arena for AI agents. Play rated games via MCP.

Version check not run yet

Games and game engines Official MCP Registry Local
Tokenmizer io.github.Shweta-Mishra-ai/tokenmizer

Graph-backed session memory for LLMs: checkpoint, resume, file analysis, token-savings stats.

Version check not run yet

Memory and context Official MCP Registry Local
ask-fable io.github.baggybin/ask-fable

MCP server for Anthropic's Claude Fable, Opus 5, and multi-model reasoning councils.

Version check not run yet

Model and agent tools Official MCP Registry Local
Graph-MIND io.github.goyohan0611-png/graph-mind

Local long-term memory shared by all your AI agents, kept word for word on your own PC.

Version check not run yet

Memory and context Official MCP Registry Local
Jmunch io.github.jgravelle/jmunch-mcp

Transparent MCP proxy. Turns fat tool responses into queryable handles: 88-99% fewer tokens.

Version check not run yet

Model and agent tools Official MCP Registry · PyPI Local
Aichat io.github.rcgalbo/aichat

Inter-agent communication for multi-agent Claude Code workflows.

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 31 a week MIT
@minhspark/codex-mcp-bridge io.github.buidangminh23/codex-mcp-bridge

Two-way MCP bridge between Claude and Codex: prompts into a live Codex thread, messages into a running Claude Code session.

Version check not run yet

Model and agent tools npm Local 536 a week MIT
@mcpfusion/core io.github.vinkius-labs/mcpfusion-core

MVA (Model-View-Agent) framework for the Model Context Protocol. Structured perception packages with Presenters, cognitive guardrails, self-healing errors, action consolidation, and tRPC-style type sa

Version check not run yet

Model and agent tools npm Local 535 a week APACHE-2.0
Prompyai io.github.samouh-waleed/prompyai

Scores your prompts against your real codebase — context-aware prompt intelligence

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 16 a week MIT
@cardor/agent-harness-kit io.github.enmanuelmag/agent-harness-kit

CLI scaffolding for multi-agent harness systems

Version check not run yet

Model and agent tools npm Local 533 a week APACHE-2.0
Polydev io.github.polydev-ai/polydev

Query GPT-5, Claude, Gemini, and Grok simultaneously through one MCP server

Version check not run yet

Model and agent tools Official MCP Registry Local
page-agent-sdk io.github.whyymj/page-agent-sdk

AI agent SDK for web pages — embed a chat assistant that edits page data via schema-validated tools. A lighter, framework-agnostic alternative to CopilotKit/LangChain for in-page JSON-editing agents.

Version check not run yet

Model and agent tools npm Local 514 a week ISC
Eval Runner io.github.dbsectrainer/mcp-eval-runner

A standardized testing harness for MCP servers and agent workflows

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 12 a week MIT
nirium-mcp io.github.nirium-protocol/nirium-mcp

Model Context Protocol server for Nirium - exposes market data, autonomous loop control, and x402/MPP paid signals to any MCP-compatible AI (Claude, GPT, Cursor, VS Code Copilot).

Version check not run yet

Developer tools npm Local 510 a week APACHE-2.0
@achieveai/hitl-mcp-server io.github.achieveai/humanintheloop

Human-in-the-Loop MCP Server — enables LLM agents to ask questions across all your devices via ntfy.sh

Version check not run yet

Model and agent tools npm Local 506 a week GPL-3.0
@black942026/harness-acp-bridge-mcp io.github.black-94/harness-acp-bridge-mcp

Stdio MCP proxy for the harness-acp-bridge HTTP server: exposes its operations as tools without owning harnesses, state, or scheduling.

Version check not run yet

Calendar and scheduling npm Local 504 a week MIT
@agentproto/provider-kit io.github.agentproto/ts-provider-kit

@agentproto/provider-kit — generic provider/backend catalog, status, creds, setup-ledger, and MCP tool primitives shared by the agent-CLI, browser, tunnel, and eval-reporter families.

Version check not run yet

Browser automation npm Local 502 a week APACHE-2.0
Agentpay Sentinel io.github.Rumblingb/agentpay-sentinel-mcp

Security guardrails for AI agent payments

Not checked yet

Model and agent tools Official MCP Registry · npm 4 a week MIT
Ai Guardrails io.github.lazymac2x/ai-guardrails

Cloudflare Workers MCP server: ai-guardrails

100% up · 30 days

Model and agent tools Official MCP Registry · npm Remote 4 a week MIT
Verity io.github.meloliva14/verity-mcp

Fail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402.

Version check not run yet

Model and agent tools Official MCP Registry · npm · PyPI Local 4 a week MIT
Hivemind io.github.QuantuLabs/hivemind

Query multiple AI models (OpenAI, Anthropic, Google) for consensus responses.

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 37 a week MIT
codex-mcp-server io.github.tuannvm/codex-mcp-server

MCP server wrapper for OpenAI Codex CLI

Version check not run yet

Model and agent tools npm Local 847 a week ISC
Token Lens io.github.duttkunal101-lab/token-lens

Count and cut tokens in prompts, chats and agents for any model. Runs locally, collects no data.

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 2.3k a week MIT
llm-checker io.github.signerless/llm-checker

Intelligent CLI tool with AI-powered model selection that analyzes your hardware and recommends optimal LLM models for your system

Version check not run yet

Model and agent tools npm Local 492 a week SEE-LICENSE-IN
@twiceshy/mcp-proxy io.github.joseph-brendan/twiceshy-mcp-proxy

MCP proxy with repeat-action guard

Version check not run yet

Model and agent tools npm Local 484 a week MIT
Tetrad io.github.SamoraDC/tetrad

Quadruple consensus MCP server for code validation using Codex, Gemini, and Qwen

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 32 a week MIT
@tedorigawa001/servicenow-mcp io.github.tedorigawa001/servicenow-mcp

The most comprehensive ServiceNow MCP server — 450+ tools across all modules. Integrates with Claude, ChatGPT, Gemini, Cursor, GitHub Copilot and any LLM.

Version check not run yet

Model and agent tools npm Local 475 a week MIT
Elicitly ai.elicitly/elicitly

Human-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 101 a week APACHE-2.0
@veritasacta/verify io.github.veritasacta/verify

Offline verification of signed receipts and artifacts, with explicit formats and independently supplied keys.

Version check not run yet

Model and agent tools npm Local 474 a week APACHE-2.0
Observe Instrument io.github.alanzha2/observe-instrument-mcp

Add OpenTelemetry tracing to Python AI agents. Supports LangGraph, LlamaIndex, CrewAI, OpenAI SDK.

Version check not run yet

Model and agent tools Official MCP Registry · PyPI Local APACHE-2.0
llm-vision-mcp io.github.shaoyun/llm-vision-mcp

A TypeScript MCP server that gives text-only LLMs image understanding through StepFun vision models.

Version check not run yet

Model and agent tools npm Local 469 a week MIT
Agentskin io.github.Shawn5cents/agentskin

The Semantic Layer for AI Agents. Prunes noisy API data by 70%+ for token-efficient reasoning.

Version check not run yet

Model and agent tools Official MCP Registry · npm Local 100 a week MIT
orpc-mcp-handler io.github.kiriraincat/orpc-mcp-handler

Expose oRPC procedures as MCP tools, resources, and prompts.

Version check not run yet

Model and agent tools npm Local 465 a week MIT
@promptowl/contextnest-engine io.github.promptowl/contextnest-engine

Core engine for governed, versioned, AI-ready context — selectors, hash-chain versioning, graph traversal, and integrity verification for LLMs and agents

Version check not run yet

Model and agent tools npm Local 128 a week AGPL-3.0