MCPStore

███ ███ ██████ ███████ ██████ ████████ ██████ ██████ ███████ ████ ████ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ████ ██ ██ ███████ ██████ ██ ██ ██ ██████ █████ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██████ ██ ██████ ██ ██████ ██ ██ ███████

mcpstore 是一个基于 Rust 构建的 MCP 管理平台，覆盖 MCP 服务的配置、运行、调用与生命周期管理，并提供可复用的 SDK、命令行工具（CLI）以及 App/Web 应用等多种使用方式。

pip install mcpstore # 或：uv add mcpstore

# macOS / Linux curl -fsSL https://raw.githubusercontent.com/ip2a/mcpstore/main/install.sh | bash # 或使用 npm（macOS / Linux / Windows） npm install -g mcpstore

截图：docs/assets/images/app-session-transfer.png

通过 CLI 管理 MCP 服务、查看运行状态，并为 Agent 提供命令行工作流。

通过 Python SDK 或 Rust Lib 将 mcpstore 集成到自己的应用中。

from mcpstore import MCPStore store = MCPStore.setup_store()

通过store.for_store()管理全局作用域内的 MCP 服务和工具。

store.for_store().add_service({ "mcpServers": { "mcpstore_wiki": { "url": "https://example.com/mcp" } } }).wait_service("mcpstore_wiki")

add_service接受 MCP 服务配置；wait_service等待指定服务就绪。

tools = store.for_store().for_langchain().list_tools() print("loaded langchain tools:", len(tools))

适配器从store.for_store()读取工具，并转换为对应框架使用的对象。

from langchain.agents import create_agent from langchain_openai import ChatOpenAI llm = ChatOpenAI( temperature=0, model="your-model", api_key="sk-*", base_url="https://api.xxx.com", ) agent = create_agent(model=llm, tools=tools, system_prompt="你是一个助手") events = agent.invoke({ "messages": [{"role": "user", "content": "mcpstore 怎么添加服务？"}] }) print(events)

使用for_agent(agent_id)为不同 Agent 建立独立作用域：

store.for_agent("agent1").add_service({ "name": "mcpstore_wiki", "url": "https://example.com/mcp", }) store.for_agent("agent2").add_service({ "name": "gitodo", "command": "uvx", "args": ["gitodo"], }) agent1_tools = store.for_agent("agent1").list_tools() agent2_tools = store.for_agent("agent2").list_tools()

store.for_agent(agent_id)与store.for_store()提供相同的操作，服务和工具按 Agent 作用域隔离。

当前推荐直接使用 Rust CLI 暴露服务，而不是再依赖历史 Python hub 接口：

# 启动 Rust HTTP API mcpstore api --config-path ./mcp.json --host 127.0.0.1 --port 1820 # 以 stdio 启动 Rust MCP Server mcpstore mcp --config-path ./mcp.json # 以 streamable-http 启动 Rust MCP Server mcpstore mcp --config-path ./mcp.json --transport streamable-http --host 127.0.0.1 --port 1830 --path /mcp

Python SDK 不再启动嵌入式 API server；需要对外提供服务时，请使用 Rust CLI。

from mcpstore import MCPStore from mcpstore.config import RedisConfig redis_config = RedisConfig( host="127.0.0.1", port=6379, password=None, namespace="demo_namespace", ) store = MCPStore.setup_store(source=redis_config)

使用相同后端和namespace的实例可以共享数据。若当前进程只使用共享数据源、不维护本地服务实例，可设置mode="data_plane"：

from mcpstore import MCPStore from mcpstore.config import RedisConfig redis_config = RedisConfig( host="127.0.0.1", port=6379, password=None, namespace="demo_namespace", ) store = MCPStore.setup_store(source=redis_config, mode="data_plane") services = store.for_store().list_services()

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

What Shopify did for ecommerce, Chipp does for AI agents. Build, deploy, and monetize AI agents for your business — no engineering team required.

CodeVF MCP lets AI hand off problems to real engineers instantly, so your workflows don’t stall when models hit their limits.

Client implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.

Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.

On-demand access to 150+ specialist AI agent templates — search, browse, and spawn agents. 150x reduction in context usage vs loading agents locally.

AgentChatBus is a persistent AI communication bus that lets multiple independent AI Agents chat, collaborate, and delegate tasks — across terminals, across IDEs, and across frameworks.

Remote MCP server (Streamable HTTP) at https://mcp.agenticrail.nz/ — deterministic step-order enforcement for AI agents. evaluate_step returns ALLOW or DENY before a step runs; verify_receipt proves a sequence's Ed25519-signed, hash-chained receipt chain is intact. No auth required: omit the bearer token and calls run on the public demo key. That first clause matters — the form has no "remote/hosted" field, and putting the endpoint in the description is the convention on that list ("Fully REMOTE! Just use…"). The rest mirrors your own server card verbatim, so the listing and the card can't drift.

An AI Agent with optional Human-in-the-Loop Safety and Model Context Protocol (MCP) integration.

Agent Mail Rooms is a paid remote MCP endpoint for OpenAI Codex agent coordination MCP. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit-

MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) — purpose-built tools, model routing with fallback, session continuity, and output truncation to save Claude's context and tokens.