This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
An MCP server that lets a coding agent search the source code of the public web. Ask it which sites embed a script, what a domain is built with, or which domains share an analytics id, and it answers from searchcode.ai instead of guessing.
Works with Claude Code, Claude Desktop, Cursor, VS Code, and any other MCP client.
npx -y @searchcode/mcpRelated MCP server: fossick-mcp
Add it to your MCP client's config. For Claude Code:
claude mcp add searchcode --env SEARCHCODE_API_KEY=your-key -- npx -y @searchcode/mcpOr by hand, in any client that takes the standard config shape:
{
"mcpServers": {
"searchcode": {
"command": "npx",
"args": ["-y", "@searchcode/mcp"],
"env": { "SEARCHCODE_API_KEY": "your-key" }
}
}
}Get a key. The free plan needs no card.
Tool | Credits | Plan | What it does |
| 5 | Free | Search the raw source (HTML, inline JavaScript and CSS) of websites across the public web for a substring or regular expression. |
| 1 | Free | Get the exact number of sites carrying one signal, answering "how many sites use X". |
| 3 | Free | List every site detected using a given technology, rank-ordered, with an exact site count. |
| 3 | Pro | Get the full technology and statistics profile for one domain: detected technologies by category, page and byte counts, and sample pages. |
| 5 | Pro | Read the retained source of one page from a search hit, by its blob hash and content type. |
| 5 | Pro | Find every domain sharing one analytics, advertising, or tracker identifier, revealing sites run by the same operator. |
| 1 | Free | Browse the ranked domain index, optionally narrowed by a name fragment, top-level domain, technology, or country. |
| 1 | Enterprise | Browse captured e-commerce storefronts by catalog size, optionally filtered by domain fragment or country. |
| 1 | Enterprise | Aggregate statistics over the shop catalog: stores and products per platform, top vendors, product types, and price bands. |
| 2 | Enterprise | Read captured product records: one store's catalog, or products across stores by title fragment, vendor, or country. |
Each tool reports its own credit cost and plan requirement in its description, so the agent knows what a call will cost before it makes one.
Once it is connected, questions like these work:
"Which sites embed the Stripe checkout script?"
"What is shopify.com built with?"
"How many sites use React?"
"Find every domain sharing this Google Analytics id."
"Show me the source of that match so I can see the surrounding code."
Variable | Meaning |
| your API key, required |
| gateway base URL, defaults to |
Every file here is generated from the searchcode.ai customer API contract. When the API changes, the contract changes, these packages are regenerated, their tests run, and a new version is published. That is why the commands, tools, credit costs and plan requirements documented here can never drift from what the API actually does.
Found a problem? Open an issue — please don't send a pull request against generated files, they are overwritten on the next contract change.
MIT
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
On-page crawl, tech-stack detection, DNS, SSL and WHOIS as agent tools.
Web data for agents. Extract web pages, crawl websites, discover URLs, and search the web.
Search websites by source code, technology stack, analyze domains, and download lead lists.
