ab-platform-mcp-local
A local MCP server that forwards tools from an upstream experiment platform and adds AI Agent tools for experiment analysis and skill debugging.
README
ab-platform-mcp-local
一个本地 MCP(Model Context Protocol)server,作为上游实验平台 MCP 的本地扩展层:透传上游已有的工具,并在其上新增几个面向「用 AI Agent 做实验分析、并调试分析 skill」的工具。纯接口调用,可在 Claude Code 等 MCP 客户端中使用。
本仓库为脱敏公开版:所有服务地址、账号、密钥都通过环境变量注入(见
.env.example),代码本身不含任何内部地址或凭据。
能力
启动后对客户端暴露两类工具:
- 透传工具:把上游 MCP(通过 SSE transport 连接)的工具原样转发,客户端可直接调用。
- 本地新增工具:
start_agent_analysis(message, experiment_id, ...)— 向后端 Agent 发起一次分析对话(异步),返回thread_id/chat_url。get_run_details(thread_id, diagnose?)— 读取某次对话的完整执行详情(执行统计、思考过程、最终报告;diagnose=true给每个工具的入参/结果/报错)。数据从 Agent 的 checkpoint 读,运行中和完成后都能用。list_exp_conversations(experiment_id?)— 列对话历史,拿thread_id。sync_skill(skill_name, skill_md_path?/content?)— 上传/覆盖一个个人 skill(幂等)。list_skills()— 列出当前账号的个人 skill。
结构
server.py # MCP server 入口(低层 Server API:动态合并远端清单 + 本地工具,分发调用)
relay.py # 透传层:sse_client 连上游 MCP,拉清单 / 转发 tools/call
agent_http.py # Agent 服务的共享 HTTP 客户端(按 X-Username 认证)
agent_chat.py # 对话流(SSE 解析 + 异常处理)
tools/ # 本地新增工具实现
agent_analysis.py、run_details.py、sync_skill.py、conversations.py
run_one.py # 单任务执行器:上传 skill → 发起 → 体检/重发 → 轮询 → 分类(供批量/并行调用)
使用
- Python 3.10+,装依赖:
python -m venv .venv && ./.venv/bin/pip install -r requirements.txt - 复制
.env.example为.env,填上你自己的服务地址 / 账号 / 密钥。 - 在 MCP 客户端(如 Claude Code)的配置里注册:
{ "ab-platform-local": { "type": "stdio", "command": "/abs/path/.venv/bin/python", "args": ["/abs/path/server.py"] } }
说明
.env含真实凭据,已被.gitignore忽略,不要提交。- 工具的服务地址、鉴权全部来自环境变量;本仓库代码不含任何内部信息。
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.