Explore
Find agent skills by outcome
4,510 skills indexed with the new KISS metadata standard.
return {id: data[id]
name: data[name]}
async def _make_api_request(endpoint: str
method: str = GET
data = await api_request(limit=params.limit
offset=params.offset)
- Return complete
structured data suitable for programmatic processing
- Omit verbose metadata (e.g.
show only one profile image URL
def validate_email(cls
v: str) -> str:
email: str = Field(...
description=User's email address
The official MCP Python SDK provides FastMCP
a high-level framework for building MCP servers. It provides:
This document provides Python-specific best practices and examples for implementing MCP servers using the MCP Python SDK. It covers server setup
tool registration patterns
- [ ] Tools enable complete workflows
not just API endpoint wrappers
Expose data as resources for efficient
URI-based access:
* This server provides tools to interact with Example API
including user search
* project management
and data export capabilities.
const truncatedData = data.slice(0
Math.max(1
const data = await apiRequest(params.limit
params.offset);
- Return complete
structured data suitable for programmatic processing
email: string
// Email address
description: `Search for users in the Example system by name
│ └── constants.ts # Shared constants (API_URL
CHARACTER_LIMIT
- **DO NOT use**: Old deprecated APIs such as `server.tool()`
`server.setRequestHandler(ListToolsRequestSchema
<question>Look for pull requests that modified files in the /api directory and were merged between January 1 and January 31
2024. How many different contributors worked on these PRs?</question>
After understanding the API and tools
USE the MCP server tools:
- Example: if finding a paper name
be SPECIFIC enough so answer is not confused with papers published later