Find agent skills by outcome

await ctx.report_progress(0.25

Starting search...)

FastMCP can automatically inject a `Context` parameter into tools for advanced capabilities like logging

progress reporting

async def _make_api_request(endpoint: str

method: str = GET

This server provides tools to interact with Example API

including user search

async def _make_api_request(endpoint: str

method: str = GET

data = await api_request(limit=params.limit

offset=params.offset)

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

* This server provides tools to interact with Example API

including user search

const data = await apiRequest(params.limit

params.offset);

textContent = JSON.stringify(output

null

content: [{ type: text

text: textContent }]

Creative

This tool searches across all user profiles in the Example platform

supporting partial matches and various search filters. It does NOT create or modify users

│ └── 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

content: [{ type: text

text: JSON.stringify(output) }]

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.

<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 inspecting the content

create 10 human-readable questions:

- Goal: identify specific content (e.g.

users

After understanding the API and tools

USE the MCP server tools: