Build Mcp
Design and implement MCP servers in Python (FastMCP) or TypeScript so your agent gets workflow-shaped tools, not raw API passthrough.
Overview
Build-mcp is an agent skill most often used in Build (also Ship security review, Operate infra) that guides creation of high-quality MCP servers in Python or TypeScript.
Install
npx skills add https://github.com/neolabhq/context-engineering-kit --skill build-mcpWhat is this skill?
- Four-phase workflow: deep research and planning, implementation, evaluation, and iteration
- Agent-centric design: workflow tools that consolidate operations, not one-tool-per-REST-endpoint
- Context-window guidance—optimize tool descriptions and payloads for limited agent context
- Covers Python FastMCP and Node/TypeScript MCP SDK paths
- Explicit trigger: use when building MCP servers to integrate external APIs or services
- 4 main development phases named in the workflow (research/planning through iteration)
Adoption & trust: 511 installs on skills.sh; 1.1k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You exposed every REST endpoint as an MCP tool and your agent still cannot complete realistic workflows within context limits.
Who is it for?
Indie builders adding a focused MCP layer on top of an API they own or a key integration (calendar, billing, deployment) for daily agent use.
Skip if: Consumers who only need to install an existing MCP from a marketplace without writing server code.
When should I use this skill?
When building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
What do I get? / Deliverables
You ship an MCP server whose tools map to agent workflows, with clearer schemas and descriptions so LLMs can reliably call external services.
- Implemented MCP server
- Workflow-oriented tool definitions with agent-friendly descriptions
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Build is the primary shelf because the skill is an end-to-end MCP server development guide from research through implementation. Agent-tooling is the best fit: MCP is the standard surface for extending LLM agents with external tools and services.
Where it fits
Replace five granular GitHub tools with one `open_pr_for_issue` workflow tool before wiring Cursor.
Wrap a Stripe + internal ledger flow into a single MCP tool for billing support agents.
Review OAuth scopes and input validation on new MCP tools before exposing them to production agents.
Extend an existing MCP deployment with a consolidated monitoring or incident tool.
How it compares
This is a server authoring playbook, not a prebuilt MCP catalog entry—pair with official SDK docs for transport details.
Common Questions / FAQ
Who is build-mcp for?
Developers building custom MCP servers with FastMCP or the MCP SDK who want agent-first tool design rather than API wrappers.
When should I use build-mcp?
In Build while designing agent-tooling and integrations; in Ship when hardening tool auth and scopes; in Operate when extending production MCP surfaces—whenever you are integrating external services via MCP.
Is build-mcp safe to install?
The skill is documentation and process guidance; your server code still needs normal secret handling and network policy—check the Security Audits panel on this page for the package source.
SKILL.md
READMESKILL.md - Build Mcp
# MCP Server Development Guide ## Overview To create high-quality MCP (Model Context Protocol) servers that enable LLMs to effectively interact with external services, use this skill. An MCP server provides tools that allow LLMs to access external services and APIs. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks using the tools provided. --- # Process ## 🚀 High-Level Workflow Creating a high-quality MCP server involves four main phases: ### Phase 1: Deep Research and Planning #### 1.1 Understand Agent-Centric Design Principles Before diving into implementation, understand how to design tools for AI agents by reviewing these principles: **Build for Workflows, Not Just API Endpoints:** - Don't simply wrap existing API endpoints - build thoughtful, high-impact workflow tools - Consolidate related operations (e.g., `schedule_event` that both checks availability and creates event) - Focus on tools that enable complete tasks, not just individual API calls - Consider what workflows agents actually need to accomplish **Optimize for Limited Context:** - Agents have constrained context windows - make every token count - Return high-signal information, not exhaustive data dumps - Provide "concise" vs "detailed" response format options - Default to human-readable identifiers over technical codes (names over IDs) - Consider the agent's context budget as a scarce resource **Design Actionable Error Messages:** - Error messages should guide agents toward correct usage patterns - Suggest specific next steps: "Try using filter='active_only' to reduce results" - Make errors educational, not just diagnostic - Help agents learn proper tool usage through clear feedback **Follow Natural Task Subdivisions:** - Tool names should reflect how humans think about tasks - Group related tools with consistent prefixes for discoverability - Design tools around natural workflows, not just API structure **Use Evaluation-Driven Development:** - Create realistic evaluation scenarios early - Let agent feedback drive tool improvements - Prototype quickly and iterate based on actual agent performance #### 1.3 Study MCP Protocol Documentation **Fetch the latest MCP protocol documentation:** Use WebFetch to load: `https://modelcontextprotocol.io/llms-full.txt` This comprehensive document contains the complete MCP specification and guidelines. #### 1.4 Study Framework Documentation **Load and read the following reference files:** - **MCP Best Practices**: [📋 View Best Practices](./reference/mcp_best_practices.md) - Core guidelines for all MCP servers **For Python implementations, also load:** - **Python SDK Documentation**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` - [🐍 Python Implementation Guide](./reference/python_mcp_server.md) - Python-specific best practices and examples **For Node/TypeScript implementations, also load:** - **TypeScript SDK Documentation**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md` - [⚡ TypeScript Implementation Guide](./reference/node_mcp_server.md) - Node/TypeScript-specific best practices and examples #### 1.5 Exhaustively Study API Documentation To integrate a service, read through **ALL** available API documentation: - Official API reference documentation - Authentication and authorization requirements - Rate limiting and pagination patterns - Error responses and status codes - Available endpoints and their parameters - Data models and schemas **To gather comprehensive information, use web search and the WebFetch tool