mcp-builder

A guide for building MCP servers. MCP, or Model Context Protocol, is a standard way for AI agents to use tools and data from APIs, databases, and other services.

In plain words
What is it for?
Use it when creating an MCP server, exposing an API or database to an AI agent, or designing the tools, schemas, and documentation the agent will call.
Why use it?
It helps avoid unclear tool definitions, missing operations, and weak error handling when connecting an AI agent to another service.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/code-saurabh/openskills/mcp-builder
Any agent
npx skills add CODE-SAURABH/OpenSkills --skill mcp-builder
Clone the repo
git clone --depth 1 https://github.com/CODE-SAURABH/OpenSkills

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,507 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00079 $0.03507
Opus 5 $0.00039 $0.01754
Sonnet 5 $0.00016 $0.00701
Haiku 4.5 $0.00008 $0.00351

Measured 2d ago against content hash 203a548fe63f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate_tool_contract.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

mcp-builder/SKILL.md · 424 lines

How it starts

The opening of the file, as written. The whole thing — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Development

MCP (Model Context Protocol) is the standard for connecting AI agents to external tools and services. An MCP server exposes tools, resources, and prompts that any compatible AI agent can call — Claude, GPT-4, Gemini, or any other model that speaks the protocol.

Build MCP servers like you build APIs: with clear contracts, proper error handling, and the caller (the AI agent) as your user. A badly designed MCP tool confuses the model. A well-designed one makes the model dramatically more capable.


MCP Builder Principles

  • The AI agent is the caller — design for it. Tool names, descriptions, and schemas must be clear enough that an LLM picks the right tool without being told. If a tool name is ambiguous, the agent will misuse it.
  • Tool descriptions are prompt engineering. The description field in your tool schema is what the model reads to decide when and how to call it. Write it like a senior engineer explaining an API to a junior — concrete, precise, with examples.
  • Comprehensive beats clever. Cover the API's core operations completely before adding workflow shortcuts. Agents can compose basic tools; they cannot invent missing operations.
  • Actionable errors are non-negotiable. When a tool fails, the error message must tell the agent exactly what went wrong and exactly what to try next. "An error occurred" is useless. "Authentication failed: API key missing. Set the X-API-KEY header with your key from https://example.com/settings/api" is useful.
  • Stateless by default. Design tools to be stateless and idempotent where possible. Stateful MCP servers are harder to debug, scale, and reason about.
  • Security is not optional. MCP servers run with the credentials of the human user. Never log secrets. Validate every input. Scope permissions to the minimum required.

Step 0: Plan Before You Build

Answer these before writing a line of code:

  1. What service are you wrapping? Name it. What does it do?
  2. What are the 5 most common operations a user needs? Start here — not with full API coverage.
  3. What is the authentication mechanism? API key, OAuth, bearer token, mTLS?
  4. What transport? stdio for local tools (runs on user's machine), streamable HTTP for remote servers (deployed, shareable).
  5. What language? TypeScript recommended (best SDK support, type safety, broad compatibility). Python (FastMCP) for data/ML workflows.
  6. What are the failure modes? API rate limits, network timeouts, auth expiry — plan the error messages now.

Read the full file on GitHub · 424 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 424 lines · 79 tokens per session scan A 203a548fe63f

Subscribe to this mod's changes

mcp-builder is a skill published in the GitHub repository CODE-SAURABH/OpenSkills (2 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 3,507 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

looper

Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council. Use when the user wants to design, build, or set up an agent loop, iterative agent workflow, self-review loop, LLM-as-judge loop, multi-model council, reviewer/judge gate, or /goal-style looping process. Start from a…

ksimback/looper · 157 tokens

context-mode

Mandatory routing rules for Antigravity CLI. Invoke when exploring a codebase, reading files for analysis, listing context-mode tools, searching, parsing, counting, comparing, summarizing, fetching web content, or running data-heavy commands.

mksglu/context-mode · 50 tokens

skill-supply-chain-audit

Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk. Use when evaluating a third-party skill before installing, enabling, updating, publishing, or distributing it; reviewing an…

seb1n/awesome-ai-agent-skills · 106 tokens

espalier-init

Analyze any existing codebase, discover its patterns and best practices, and generate an Espalier structure (rules, skills, wiki, pipeline) so AI coders produce code matching that project's language and conventions. Greenfield repos take the two-pass Decide-Then-Bind path (/espalier-map charts the conventions, init…

Junhanliu-dev/espalier-engineering · 118 tokens

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

EliasOulkadi/shokunin · 63 tokens

skill-maintainer

Track upstream drift and sync adapted skill libraries.

moonlight-lupin/agent-skills · 12 tokens