UniFuncs MCP Server
@UniFuncs
About UniFuncs MCP Server
MCP Server for the UniFuncs API
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"unifuncs": {
"command": "npx",
"args": [
"-y",
"@unifuncs/ufn-mcp-server"
],
"env": {
"UNIFUNCS_API_KEY": "<YOUR UNIFUNCS API KEY>"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is UniFuncs MCP Server?
UniFuncs MCP Server provides access to the UniFuncs API through the Model Context Protocol (MCP), offering web search, web reader, deep search (sync and async), and deep research capabilities. It is designed for developers building AI applications that need real-time or in-depth research from the web.
How to use UniFuncs MCP Server?
Install and configure via NPX (STDIO) using the @unifuncs/ufn-mcp-server package, setting the UNIFUNCS_API_KEY environment variable. Alternatively, build from source or run as an SSE server with the --sse flag or UNIFUNCS_SSE_SERVER=true. Tools are invoked by sending JSON-formatted requests to the MCP client.
Key features of UniFuncs MCP Server
- Real-time web search with freshness and pagination.
- Clean content extraction from web pages.
- Synchronous and asynchronous deep search.
- Comprehensive deep research with custom parameters.
- Multiple output formats: JSON, Markdown, Text.
Use cases of UniFuncs MCP Server
- Perform real-time web searches with filtered results.
- Extract clean, structured content from any URL.
- Run synchronous or asynchronous deep searches on complex queries.
- Execute detailed deep research tasks with customizable depth and domain scoping.
- Integrate web search and research into AI agent workflows via MCP.
FAQ from UniFuncs MCP Server
What is the difference between Deep Search and Deep Research?
Deep Search provides both synchronous (immediate) and asynchronous (task-based) search, while Deep Research offers more comprehensive, async-only research with customizable parameters like depth, domain scoping, and output prompts.
What are the runtime requirements for UniFuncs MCP Server?
Node.js is required to run the server via NPX or source build. A UniFuncs API key is mandatory and must be set as the environment variable UNIFUNCS_API_KEY.
What transports does UniFuncs MCP Server support?
It supports STDIO (default) and SSE transports. SSE can be enabled with the --sse flag or by setting UNIFUNCS_SSE_SERVER=true.
How is pricing structured for UniFuncs MCP Server?
Web Search and Web Reader are pay-per-request. Deep Search uses pay-per-token. Deep Research uses M Tokens for U3 and U3 Pro models.
Where can I find support or documentation?
Documentation is at https://unifuncs.com/api, GitHub at https://github.com/UniFuncs/ufn-mcp-server, and support by email at [email protected].
Frequently asked questions
What is the difference between Deep Search and Deep Research?
Deep Search provides both synchronous (immediate) and asynchronous (task-based) search, while Deep Research offers more comprehensive, async-only research with customizable parameters like depth, domain scoping, and output prompts.
What are the runtime requirements for UniFuncs MCP Server?
Node.js is required to run the server via NPX or source build. A UniFuncs API key is mandatory and must be set as the environment variable `UNIFUNCS_API_KEY`.
What transports does UniFuncs MCP Server support?
It supports STDIO (default) and SSE transports. SSE can be enabled with the `--sse` flag or by setting `UNIFUNCS_SSE_SERVER=true`.
How is pricing structured for UniFuncs MCP Server?
Web Search and Web Reader are pay-per-request. Deep Search uses pay-per-token. Deep Research uses M Tokens for U3 and U3 Pro models.
Where can I find support or documentation?
Documentation is at https://unifuncs.com/api, GitHub at https://github.com/UniFuncs/ufn-mcp-server, and support by email at [email protected].
Basic information
More Other MCP servers
Blender
ahujasidOpen-source MCP to use Blender with any LLM
Codelf
unbugA search tool helps dev to solve the naming things problem.

Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

EverArt
modelcontextprotocolModel Context Protocol Servers
Comments