Poco MCP Service
Independent MCP service module for Poco, providing analytics and management tools such as daily usage analysis and service introspection.
README
Poco MCP Service
独立 MCP 服务模块(目录内自洽),用于承载 Poco 的多类型 MCP 工具。
目录结构
app/core:配置与基础设施app/clients:后端 API 客户端app/schemas:结构化输出模型app/services:工具编排与分析逻辑app/tools:MCP tools(按领域拆分)app/main.py:MCP 入口,挂载多子服务skills:面向 AI 的调用与分析技能文档
快速启动
cd mcp_service
uv sync
uv run python -m app.main
默认使用 http 传输(0.0.0.0:8090)。如需 stdio:
MCP_TRANSPORT=stdio uv run python -m app.main
认证建议:
- 推荐通过 MCP headers 透传用户自己的 API Key(可同时传 admin/global)。
BACKEND_ADMIN_API_KEY作为无 HTTP 请求上下文时的可选回退(例如本地直连测试)。- 可选配置
BACKEND_GLOBAL_API_KEY(global-scope 工具或回退场景使用)。
可用工具(当前)
analysis_get_company_daily_usageanalysis_get_user_daily_usageanalysis_get_usage_scenariosanalysis_get_daily_analysis_briefanalysis_get_daily_content_taxonomyanalysis_get_daily_user_proficiencyanalysis_get_daily_user_personasanalysis_get_daily_report_datasetmanagement_pingmanagement_describe_service
MCP 服务配置示例
{
"mcpServers": {
"poco_analytics": {
"type": "http",
"url": "${MCP_ANALYTICS_HTTP_URL:-http://host.docker.internal:8090/mcp}",
"headers": {
"BACKEND_ADMIN_API_KEY": "${MCP_ANALYTICS_ADMIN_API_KEY}",
"BACKEND_GLOBAL_API_KEY": "${MCP_ANALYTICS_GLOBAL_API_KEY:-}"
}
}
}
}
说明:
"/workspace/mcp_service"是 容器内路径,仅在stdio + command启动模式需要。- 当前推荐
http方式接入,不再需要在 MCP Server 配置里写command/args。 MCP_ANALYTICS_ADMIN_API_KEY/MCP_ANALYTICS_GLOBAL_API_KEY建议配置为用户级环境变量。mcp_service会优先读取来路 headers 中的BACKEND_ADMIN_API_KEY、BACKEND_GLOBAL_API_KEY;同时兼容Authorization。- 仅在无 HTTP 请求上下文时,才回退
BACKEND_ADMIN_API_KEY/BACKEND_GLOBAL_API_KEY(便于本地直连测试)。
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.