Policy MCP Server

[该MCP服务提供全面的政策相关信息查询功能,包括政府补贴、政策优惠、政策支持等信息,帮助用户了解企业的政策扶持情况。](https://www.handaas.com/)

Remote serverstreamable-httpPython

What is the Policy MCP server?

If you want an AI assistant working directly with Policy, the policy mcp server is the bridge. 该MCP服务提供全面的政策相关信息查询功能,包括政府补贴、政策优惠、政策支持等信息,帮助用户了解企业的政策扶持情况。.

What Policy does

该MCP服务提供全面的政策相关信息查询功能,包括政府补贴、政策优惠、政策支持等信息,帮助用户了解企业的政策扶持情况。

Tools it exposes

Once connected, the assistant can call these 14 tools directly:

  • total — 总数
  • resultList — 结果列表,包含企业基本信息
  • count — 总项目数量
  • ppeLevelStat — 项目级别分布
  • nationalProjectCount — 国家级项目数量
  • provincialProjectCount — 省级项目数量
  • municipalProjectCount — 市级项目数量
  • districtProjectCount — 区级项目数量
  • ppeAgencyStat — 项目归口分布
  • agency — 主管机构
  • ppeYearProjectStat — 获批项目趋势
  • year — 年份
  • ppeYearAmountStat — 补贴金额趋势
  • amount — 补贴金额

Installing the policy mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Configuration

Before the server will start you need to supply 4 environment variables: PYTHONPATH, INTEGRATOR_ID, SECRET_ID, SECRET_KEY. Keep credentials in your client's env block or a secrets manager rather than committing them.

Where it fits

Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Policy sits in that group, and the shape of its toolset — total, resultList, count among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This is a hosted server — you point your client at an endpoint rather than running a local process, so there is nothing to keep updated on your machine.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • With 14 tools exposed, expect a noticeable bump in prompt size — disable it in projects that never use Policy.
  • Maintained by handaas, written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the policy mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
total总数
resultList结果列表,包含企业基本信息
count总项目数量
ppeLevelStat项目级别分布
nationalProjectCount国家级项目数量
provincialProjectCount省级项目数量
municipalProjectCount市级项目数量
districtProjectCount区级项目数量
ppeAgencyStat项目归口分布
agency主管机构
ppeYearProjectStat获批项目趋势
year年份
ppeYearAmountStat补贴金额趋势
amount补贴金额

Configuration

VariableDescriptionRequired
PYTHONPATHFilesystem location the server is allowed to use.Optional
INTEGRATOR_IDConfiguration value read at startup.Optional
SECRET_IDCredential the server authenticates with.Yes
SECRET_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Policy to total.
  • Use Policy to resultList.
  • Use Policy to count.

Frequently asked questions

It connects Policy to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (total, resultList, count, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Policy directly.