Fetching latest headlines…
I Built 3 MCP Servers for AI Agents — Here's How They Work
NORTH AMERICA
🇺🇸 United StatesJune 28, 2026

I Built 3 MCP Servers for AI Agents — Here's How They Work

0 views0 likes0 comments
Originally published byDev.to

What are MCP Servers?

The Model Context Protocol (MCP) is an open standard that lets AI agents use external tools through a unified interface. Think of it as USB-C for AI — one protocol connects any AI client (Claude Desktop, Cursor, VS Code with Cline) to any tool or data source.

I built three production-ready MCP servers and published them to PyPI and GitHub. Here's what they do and how to use them.

1. Web Search MCP Server

uvx crewai-web-search-mcp

Two tools:

  • web_search(query) — Searches Google/SerpAPI and returns ranked results with snippets
  • extract_content(url) — Fetches and extracts readable content from any web page

Use cases: Ask your AI about current events, research competitors, pull documentation, verify facts in real time.

{
  "mcpServers": {
    "web-search": {
      "command": "uvx",
      "args": ["crewai-web-search-mcp"]
    }
  }
}

2. Code Review Automation MCP

uvx code-review-automation

Three tools:

  • review_code(diff) — Analyzes code changes for bugs, security issues, anti-patterns, style violations
  • check_quality(path) — Runs static analysis and returns a quality report
  • analyze_pr(diff) — Produces a structured review: what changed, what's risky, suggestions

Use cases: Paste a PR diff and get an instant review. Catch issues before they reach production.

3. Document Intelligence Server

uvx document-intelligence-server

Three tools:

  • extract_document(path) — OCR and text extraction from PDFs, scanned docs, images
  • classify_document(path) — Identifies document type (invoice, report, contract, article)
  • summarize_document(path) — Generates a structured summary from extracted content

Use cases: Process uploaded PDFs, extract data from scanned forms, summarize long reports.

Pricing

All three servers use a shared credit system:

Tier Price Credits
Free $0 50 calls/day
Starter $20 2,000 calls
Pro $100 12,000 calls

Buy credits once, use them across any server. Credits never expire.

How it works:

  1. Install with uvx crewai-web-search-mcp
  2. Use 50 free calls per day — no key needed
  3. For unlimited use: buy credits on Gumroad → set MCP_LICENSE_KEY → all limits removed

The Stack

  • Servers: Python + FastMCP
  • Billing: FastAPI + PostgreSQL (self-hosted, open source)
  • Auth: Gumroad license key verification
  • Distribution: PyPI, GitHub, HuggingFace, Gumroad, MCP registries

The billing backend is open source too: github.com/KennyWayn3/mcp-billing-api

Links

What MCP servers would you like to see built next? I'm curious what the community actually needs.

Comments (0)

Sign in to join the discussion

Be the first to comment!