Find agent skills by outcome

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

`server.setRequestHandler(ListToolsRequestSchema

- Examples: `github-mcp-server`

`jira-mcp-server`

Productivity

- The `register*` methods provide better type safety

automatic schema handling

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

- DO use: `server.registerTool()`

`server.registerResource()`

-H

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

- 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>

-e

--env Environment variables in KEY=VALUE format

-u

--url MCP server URL

-a

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

-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)

-t

--transport Transport type: stdio

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

sse

-h

--help Show help message

Productivity

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

After creating your evaluation file

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

Productivity

Remember to parallelize solving tasks to avoid running out of context

then accumulate all answers and make changes to the file at the end.

- The answer will change as issues are created

closed

- LLM might format differently (JSON array

comma-separated

<answer>repo1

repo2

- Requires filtering bugs by date

priority