Explore
Find agent skills by outcome
17,107 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
- The `register*` methods provide better type safety
automatic schema handling
2. **Load each task instruction** and in parallel using the MCP server and tools
identify the correct answer by attempting to solve the task YOURSELF
Remember to parallelize solving tasks to avoid running out of context
then accumulate all answers and make changes to the file at the end.