mcp-server-builder

mcp-server-builder is a skill for Claude Code, Codex from Jignesh-Ponamwar/skills-mcp. It costs 98 tokens per session (2,239 once invoked), scanned A, original, Apache-2.0.

A guide for building Model Context Protocol (MCP) servers, which let AI agents use defined tools, read data, and follow reusable prompts. It covers Python and TypeScript implementations.

In plain words
What is it for?
Use it to expose functions, API calls, files, database records, configuration, or guided workflows to AI agents over local or web connections.
Why use it?
It removes the need to work out how to structure an MCP server, connect it to an AI client, handle requests safely, and deploy it.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it to expose functions, API calls, files, database records, configuration, or guided workflows to AI agents over local or web connections.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jignesh-ponamwar/skills-mcp/mcp-server-builder
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.

Any agent
npx skills add Jignesh-Ponamwar/skills-mcp --skill mcp-server-builder
Clone the repo
git clone --depth 1 https://github.com/Jignesh-Ponamwar/skills-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-server-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/jignesh-ponamwar/skills-mcp/mcp-server-builder/github.svg)](https://agentmods.dev/skills/jignesh-ponamwar/skills-mcp/mcp-server-builder)
Your own site
<a href="https://agentmods.dev/skills/jignesh-ponamwar/skills-mcp/mcp-server-builder"><img src="https://agentmods.dev/badge/skills/jignesh-ponamwar/skills-mcp/mcp-server-builder/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-server-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/jignesh-ponamwar/skills-mcp/mcp-server-builder"><img src="https://agentmods.dev/badge/skills/jignesh-ponamwar/skills-mcp/mcp-server-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,239 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00098 $0.02239
Opus 5 $0.00049 $0.01120
Sonnet 5 $0.00020 $0.00448
Haiku 4.5 $0.00010 $0.00224

Measured 12d ago against content hash 1ba8b6cf1e4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mcp-server-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 12d ago.

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.

skill_mcp/skills_data/mcp-server-builder/SKILL.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Builder Skill

MCP Architecture

An MCP server exposes three primitives to AI clients:

Primitive Purpose When to Use
Tools Callable functions the agent invokes (tools/call) Actions, API calls, computations
Resources Read-only data the agent fetches (resources/read) Files, database records, configuration
Prompts Reusable prompt templates (prompts/get) Guided workflows, structured interactions

pip install fastmcp

Minimal Server

# server.py
from fastmcp import FastMCP

mcp = FastMCP("My Tools Server", version="1.0.0")

@mcp.tool(description="Add two numbers together")
def add(a: float, b: float) -> float:
    """Add two numbers and return the result."""
    return a + b

@mcp.tool(description="Fetch the current weather for a city")
async def get_weather(city: str, unit: str = "celsius") -> dict:
    """Get current weather. unit: 'celsius' or 'fahrenheit'"""
    import httpx
    async with httpx.AsyncClient() as client:
        resp = await client.get(f"https://wttr.in/{city}?format=j1")
        resp.raise_for_status()
        data = resp.json()
    return {
        "city": city,
        "temperature": data["current_condition"][0]["temp_C" if unit == "celsius" else "temp_F"],
        "condition": data["current_condition"][0]["weatherDesc"][0]["value"],
    }

if __name__ == "__main__":
    mcp.run()  # stdio mode (default)

Run Modes

# stdio (for Claude Code, Cursor - recommended for local tools)
python server.py

# SSE (for browser clients and remote access)
MCP_TRANSPORT=sse python server.py           # http://localhost:8000/sse

# Streamable HTTP (modern, bidirectional)
MCP_TRANSPORT=streamable-http python server.py

Resources

@mcp.resource("config://app-settings")
def get_app_settings() -> str:
    """Return current application settings."""
    import json
    return json.dumps({
        "version": "1.0.0",
        "features": ["auth", "analytics"],
        "max_users": 1000,
    })

@mcp.resource("file://{path}")  # template URI with parameter
def read_file(path: str) -> str:
    """Read a file by path."""
    import pathlib
    # IMPORTANT: validate path to prevent traversal
    base = pathlib.Path("./allowed_dir").resolve()
    target = (base / path).resolve()
    if base not in target.parents and base != target:
        raise ValueError("Path outside allowed directory")
    return target.read_text()

Read the full file on GitHub · 297 lines

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. 12d ago First seen · 297 lines · 98 tokens per session scan A 1ba8b6cf1e4c

Subscribe to this mod's changes

mcp-server-builder is a skill published in the GitHub repository Jignesh-Ponamwar/skills-mcp (8 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 98 tokens to every session and 2,239 once invoked, about $0.0005 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.