ab-platform-mcp-local
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ab-platform-mcp-localStart agent analysis for experiment exp-456 on user retention."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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。
Related MCP server: local-skills-mcp
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
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
AlicenseAqualityAmaintenanceMCP server that gives AI coding agents direct access to evaluation tools.2322 PyPIApache 2.0- AlicenseAqualityAmaintenanceA universal MCP server that enables any LLM or AI agent to access expert skills from your local filesystem.388 npm40MIT
- FlicenseNot gradedqualityDmaintenanceLocal MCP server that exposes fixed tools for GPT, Claude, and Gemini while routing to any OpenAI-compatible chat completions backend with independent configuration per target.1-
- AlicenseNot gradedqualityCmaintenanceAn MCP server that lets AI agents search, view, install, and validate skills from the skillhub registry through tool calls.MIT