Find agent skills by outcome

description: `Search for users in the Example system by name

.max(200

Query must not exceed 200 characters)

Coding & Debugging

│ └── constants.ts # Shared constants (API_URL

CHARACTER_LIMIT

Use snake_case for tool names (e.g.

search_users

- Explicitly provide `title`

`description`

- Examples: `github-mcp-server`

`jira-mcp-server`

Coding & Debugging

- DO NOT use: Old deprecated APIs such as `server.tool()`

`server.setRequestHandler(ListToolsRequestSchema

- DO use: `server.registerTool()`

`server.registerResource()`

This document provides Node/TypeScript-specific best practices and examples for implementing MCP servers using the MCP TypeScript SDK. It covers project structure

server setup

- Use a more capable model (e.g.

`claude-3-7-sonnet-20250219`)

<question>Among all pull requests merged in Q1 2024

which repository had the highest number? Provide the repository name.</question>

-H

--header HTTP headers in 'Key: Value' format

-a

--args Arguments for the command (e.g.

-u

--url MCP server URL

-e

--env Environment variables in KEY=VALUE format

-c

--command Command to run MCP server (e.g.

-o

--output Output file for report (default: print to stdout)

-m

--model Claude model to use (default: claude-3-7-sonnet-20250219)

-h

--help Show help message

-t

--transport Transport type: stdio

usage: evaluation.py [-h] [-t {stdio

sse

After creating your evaluation file

you can use the provided evaluation harness to test your MCP server.

- LLM might format differently (JSON array

comma-separated

<answer>repo1

repo2