MCP servers & tool integrations
MCP SDKs & server frameworks
859 agents · most starred first
MCP SDKs & server frameworks, page 9 of 9
Project typed Python operations as agent-friendly CLIs, MCP tools, and schemas
MCP server for SpecForge - AI agent integration
分层长期记忆 MCP 服务器:本地 MiniLM 或 OpenAI 兼容嵌入 API,供 LLM Agent(DeepSeek Harness / Claude Code)做可语义检索的长期记忆
MCP server for persistent AI agent memory
WebRTC MCP Server — peer-to-peer multi-agent communication, room-based signaling, and video stream bridging via low-latency DataChannels.
MCP server serving agentic-context standards, playbooks, and conventions on demand, fetched over HTTPS with in-memory caching
Stop paying for out-of-order MCP tool calls. Author-side job-graph enforcement.
MCP server that calls a local Ollama or vLLM model for language work, with schema-validated JSON output checked by a dependency-free validator.
Cross-platform local MCP server and CLI for bitemporal long-term memory for AI agents
MCP server exposing Crispex, Perturbio and Bindigo as agent tools
Let Agents Chat — MCP server for AI agent communication
LCDD MCP Server — AI agent integration via Model Context Protocol
Model Context Protocol (MCP) Server and AI Agent Skill Suite for OpenRP.ai
LoomWeaver: open-source plugin platform for Angular workbenches. The MCP server: scaffolding and validation as tools, so an AI assistant in any product repo can build weavers without a checkout.
Lightweight MCP server for agentic knowledge guidance
A Model Context Protocol server for agentic knowledge guidance with web-based documentation loading and intelligent search instructions
An mcp
Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Vertex AI).
MCP facade and audited tools for HarborRAG.
pydantic-ai tool integration for Algenta: a governed-execution-aware toolset wrapping a self-hosted Algenta engine's MCP tool surface
Universal Web Standards MCP server hosting for ai-agent-sdk
Node stdio and HTTP MCP server hosting for ai-agent-sdk
Model Context Protocol adapter for ai-agent-context. Exposes the repository knowledge graph to MCP clients over stdio. Contains no business logic of its own.
Mio Agent Runtime installer and MCP intelligence layer
Enhanced MCP server for GraphQL with dynamic headers and robust variables parsing — a drop-in replacement for mcp-graphql.
Model Context Protocol (MCP) server providing the universal autonomous agent runtime interface, execution lifecycle state machine, and resource budgeting.
Read-only native CrewAI tools for the AgentDomain MCP server
Integração opcional do Atlas Agent Framework com MCP
MCP server for ragfaith: live faithfulness checks for RAG answers
SOFTURE AI agent-ready module: everything an AI agent uses to discover and connect to an app, from configuration plus its MCP server: API catalog, OpenAPI, Link header, OAuth discovery additions and auth.md, MCP server and A2A cards, Agent Skills, AI cata
Headless core SDK for AI Agent Skills and MCP server configurations
CLI tool to bundle, sanitize, and share AI Agent Skills and MCP server configurations
Reference implementation of the KYA-OS protocol for Model Context Protocol servers: identity, delegation, proofs, sessions, and verifiable audit trails
OpenAI extensions for MCP servers and apps.
Exposes MCP tools to an agentic run loop, and consumes remote MCP servers as agentic tools
Agentic MCP Server with advanced AI capabilities including web search, summarization, database querying, and customer support. Built by the Agentics Foundation to enhance AI agents with powerful tools for research, content generation, and data analysis.
Unified modular Model Context Protocol (MCP) server for the Agentic Engineering Suite
A true MCP server where the agent is the model and the API key.
MCP server for Django sites: tools generated from django-agent-content, including file and image uploads, for Claude Code, Claude Desktop, Cursor and other MCP clients.
Offline, read-only MCP server that verifies agent evidence claims and replays the agent-evidence conformance vectors
Shared MCP server infrastructure for exposing insurance pricing tools and agents.
Make your FastAPI services agent-ready with owner-approved MCP tools.
Django app that lets AI agents and MCP clients (Claude Code, Cursor and others) edit your site's content safely: API keys, permissions, drafts, file and image uploads, no deletes.
LangChain integration for RecruitMCP: load RecruitMCP's MCP tools as LangChain tools.
Living Agents Protocol (LAP) Python reference implementation and MCP server middleware: LIP-1 Passport, LIP-3 Scope Algebra, LIP-4 Micro-Core verification and receipts.
Production-ready MCP server scaffold with stateless MCP 2026-07-28, A2A Agent Card, and Agent Skill packaging
模联 ModLink 的 Agent 工具包——把平台模型封装为 CLI 与 MCP 工具,供 AI Agent 调用
MCP server engine and indexing library for OneTick LLM assistants — semantic document search and reference-data tools; configured and launched by a wrapper package (e.g. onetick-mcp).
OpenAI extensions for MCP Python servers.
Model Context Protocol server exposing openstax-llm pedagogical textbook chunking
Local-first GraphRAG system exposed as an MCP server
Seqoria Agentic Assistant Framework - MCP-native tool orchestration for AI applications
WebAgent Protocol: an MCP extension that lets AI agents discover, verify and safely use tools published by any website.
AgentArts 自研示例 MCP:服务器时间查询 + 文本统计
Make a small business readable for AI assistants: write and check an A2A agent card or MCP server card. Offline, standard library only. Built by the makers of Open Door for AI Assistants, where an AI assistant will be able to leave an inquiry for the business (inquiry service coming soon).
Curated, governed connectors for Algen Agent Runtime agents
FinzData MCP server configs for CrewAI, AutoGen and OpenAI Agents SDK.
Publish and consume the official MCP Skills extension (https://agentskills.io)
Free, open-source MCP servers for public data: research integrity, US federal funding, B2B leads and web/agent security. Four focused Python servers with pay-per-result Apify backends and hard spend caps.