UFN TOOLS

7 tools from the Ufn MCP Server, categorised by risk level.

// ALL 7 UFN TOOLS

READ 6 tools

Read deep-research-query-task 查询深度研究任务状态和结果 Read deep-search-create-task 创建深度搜索异步任务，立即返回task_id Read deep-search-query-task 查询深度搜索异步任务状态和结果 Read deep-search-sync 深度搜索同步接口，实时返回搜索结果 Read web-reader 抓取指定页面URL的详细内容 Read web-search 通过关键词检索互联网上的信息列表

WRITE 1 tools

Write deep-research-create-task 创建深度研究任务，进行深度的网络信息研究和分析

// RUNNING THIS SERVER

The managed route: connect Ufn through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @unifuncs/ufn-mcp-server

// FAQ

How many tools does the Ufn MCP server have? +

The Ufn MCP server exposes 7 tools across 2 categories: Read, Write.

How do I enforce policies on Ufn tools? +

Route the Ufn server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Ufn tools fall into? +

Ufn tools are categorised as Read (6), Write (1). Each category has a recommended default policy.

Enforce policy on every Ufn tool call.

Start from Ufn, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Instant setup, no code required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.