Fetch Agents
@SoftwareValete
About Fetch Agents
AI-powered code analysis and context optimization tools. Slim large code files to relevant sections (save 60-80% tokens), compress text, analyze conversations for noise, and search past chat knowledge bases. Supports x402 micropayments on Base.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"fetch-agents": {
"command": "python",
"args": [
"mcp_server.py"
],
"cwd": "/path/to/fetch-agents-mcp"
}
}
}Tools
7Reduce a code file to only sections relevant to your task
List all LAYER sections in a code file
Extract one specific named LAYER section
Compress long text while preserving key information
Find noise and wasted tokens in conversations
Index a chat export into searchable knowledge base
Search indexed knowledge bases
Overview
What is Fetch Agents?
Fetch Agents is an MCP server that provides AI-powered code analysis, context compression, and knowledge search tools for Claude Code, Cline, and other MCP-compatible AI assistants. It connects to cloud-hosted agents via HTTPS and processes code server-side using LLM pipelines.
How to use Fetch Agents?
Obtain a free API key by registering via curl (50 free requests/day included). Add the server to your MCP config with the python command, the script mcp_server.py, and the API key in environment variables. Install dependencies with pip install mcp httpx. Optionally use x402 micropayments to pay per request without registration.
Key features of Fetch Agents
- Reduce code files to only relevant sections with
slim_code - List and extract LAYER sections from code files
- Compress long text while preserving key information
- Analyze conversations for noise and wasted tokens
- Index chat exports into a searchable knowledge base
- Search indexed knowledge bases for past discussion insights
- Pay-per-use via x402 micropayments on Base
Use cases of Fetch Agents
- Reading large code files while saving token usage
- Exploring unfamiliar code structure quickly
- Summarizing long documentation or verbose logs
- Reusing insights from past conversations in new chats
- Identifying wasted tokens in long conversations hitting context limits
FAQ from Fetch Agents
How does Fetch Agents process my code?
Your code is sent via HTTPS to cloud agents at agentslab.duckdns.org where LLM-powered analysis pipelines run. No local GPU is needed.
What are the runtime requirements?
Python 3.10+, the mcp and httpx packages, and an internet connection are required.
How much does Fetch Agents cost?
A free tier includes 50 requests per day. Pay-per-use costs $0.10–$1.00 per request via USDC on Base (x402). Prepaid balances and a $15/month Pro subscription (300 requests/month) are also available.
How do I authenticate with the server?
You can either use a free API key obtained from the registration endpoint or use x402 micropayments by signing a USDC transfer on Base per request (no API key needed).
Where is my data processed?
Data is processed on cloud servers. The README does not specify long-term storage or deletion policies.
More Browser Automation MCP servers
Browserbase MCP Server
browserbaseAllow LLMs to control a browser with Browserbase and Stagehand
MCP Browser Kit
ndthanhdevAn MCP Server that enables AI assistants to interact with your local browsers.
Puppeteer Vision Mcp Server
djannot
Apify Model Context Protocol (MCP) Server
apifyThe Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.
fetch-mcp
egoistAn MCP server for fetching URLs / Youtube video transcript.
Comments