generate-mcp-config

generate-mcp-config is an agent for Claude Code from shuchitajain/awesome-ai-setup. It costs 19 tokens per session (1,382 once invoked), scanned A, original, MIT.

An agent instruction for detecting a project's connected services and creating Model Context Protocol configuration files. MCP lets AI tools access live project data and services.

In plain words
What is it for?
Use it to inspect the project's stack, AI-tool setup, environment keys, and documentation, then generate suitable MCP configurations.
Why use it?
It reduces configuration mistakes and prevents existing integrations from being overwritten.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions CLAUDE.md; mentions Claude Code.

Good fit Use it to inspect the project's stack, AI-tool setup, environment keys, and documentation, then generate suitable MCP configurations.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/shuchitajain/awesome-ai-setup/generate-mcp-config
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.

Clone the repo
git clone --depth 1 https://github.com/shuchitajain/awesome-ai-setup

Made for: Claude Code.

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 generate-mcp-config

README.md
[![agentmods](https://agentmods.dev/badge/agents/shuchitajain/awesome-ai-setup/generate-mcp-config/github.svg)](https://agentmods.dev/agents/shuchitajain/awesome-ai-setup/generate-mcp-config)
Your own site
<a href="https://agentmods.dev/agents/shuchitajain/awesome-ai-setup/generate-mcp-config"><img src="https://agentmods.dev/badge/agents/shuchitajain/awesome-ai-setup/generate-mcp-config/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 generate-mcp-config

Your own site · 80×15
<a href="https://agentmods.dev/agents/shuchitajain/awesome-ai-setup/generate-mcp-config"><img src="https://agentmods.dev/badge/agents/shuchitajain/awesome-ai-setup/generate-mcp-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,382 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 $0.00019 $0.01382
Opus 5 $0.00010 $0.00691
Sonnet 5 $0.00004 $0.00276
Haiku 4.5 $0.00002 $0.00138

Measured 10d ago against content hash a0be212735b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

generate-mcp-config 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 10d 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.

agents/generate-mcp-config.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Generate MCP Configuration

You are generating MCP (Model Context Protocol) configuration files for this repository.

MCP connects AI tools to live data sources - your database schema, GitHub issues, filesystem, and external APIs - so they work with real state instead of documented state. This agent detects which integrations are relevant for this project and generates the correct config file for each AI tool in use.


Step 1 - Detect the Stack and Existing Setup

Read these sources:

  1. Dependency manifest (pubspec.yaml, package.json, Cargo.toml, etc.) - identify the tech stack and any backend services in use (Supabase, Firebase, PostgreSQL, etc.)
  2. Existing MCP configs - check for .mcp.json, .cursor/mcp.json, .vscode/mcp.json. Read them if present - don't overwrite entries that already exist.
  3. Environment files - check .env.example or .env (keys only, never values) to understand what external services are configured
  4. README or docs - may name backend services explicitly

Identify which AI tools are in use by checking for:

  • CLAUDE.md → Claude Code → config goes in .mcp.json
  • .cursor/ or .cursorrules → Cursor → config goes in .cursor/mcp.json
  • .github/copilot-instructions.md → GitHub Copilot → config goes in .vscode/mcp.json

If none are detected, generate all three.


Step 2 - Select Relevant MCP Servers

Based on what you found, select from these servers. Only include servers with a clear reason to exist in this project.

Universal (include for any project):

Server npm package When to include
GitHub @modelcontextprotocol/server-github Any project with a GitHub remote
Filesystem @modelcontextprotocol/server-filesystem Always - lets AI read actual files

Database / backend:

Server npm package When to include
PostgreSQL @modelcontextprotocol/server-postgres If pg, postgres, drizzle-orm, or prisma detected
Supabase @supabase/mcp-server-supabase If @supabase/supabase-js detected
Firebase mcp-server-firebase If firebase or firebase-admin detected
SQLite @modelcontextprotocol/server-sqlite If sqlite3, better-sqlite3, or sqflite detected

Read the full file on GitHub · 156 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. 10d ago First seen · 156 lines · 19 tokens per session scan A a0be212735b3

Subscribe to this mod's changes

generate-mcp-config is an agent published in the GitHub repository shuchitajain/awesome-ai-setup (5 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 1,382 once invoked, about $0.0001 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.