Turn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP.
Scored across 6 tools
Each tool has a distinct purpose: get_file for a single file, list_files for repo layout, pack_repo for full repo context, search_context for targeted repo queries, and similarly pack_docs/search_docs for documentation. There is no overlap or ambiguity between tools.
All tool names follow a verb_noun pattern (get_file, list_files, pack_docs, pack_repo, search_context, search_docs). The only minor inconsistency is 'search_context' versus 'search_docs'; 'context' is slightly less clear than would be 'search_repo', but the pattern is otherwise consistent.
With 6 tools, the server is well-scoped. Each tool covers a core operation (file access, listing, packing, searching) for two domains (repo and docs). The count feels right for the server's purpose.
The tool surface fully covers the domain of context retrieval: you can list files, get a file, pack a repo or docs site, and search for specific passages. There are no obvious missing operations for the stated purpose of packing and searching code and documentation.
Return the full text of a single file in a repository, by path. Use after list_files or search_context to drill in.
Inputs: path (required), repo (required), ref.
List the text files ctx would include for a repository (after stripping binaries, lockfiles and build dirs), with their byte sizes. Cheap way for an agent to see the layout before packing.
Inputs: repo (required), ref, exclude, include.
Crawl a documentation site from a start URL and return it as one agent-ready context blob: each page extracted to clean Markdown, concatenated with its URL. Stays within the same site section; bounded by depth and page count. Use max_tokens to fit a budget.
Inputs: url (required), depth, max_pages, max_tokens.
Fetch a GitHub repository and return it as one agent-ready context blob: text files concatenated with clear "==== path ====" headers, binaries/lockfiles/build dirs stripped, with a token estimate. Use include/exclude globs to focus, and max_tokens to fit a budget.
Inputs: repo (required), ref, exclude, include, +1 more.
Search a GitHub repository and return only the passages that match a query — each with its file path, line number and a relevance score. Far more token-efficient than pack_repo when you need a specific detail (e.g. "where is auth handled?").
Inputs: repo (required), query (required), ref, exclude, +3 more.
Crawl a documentation site and return only the passages that match a query — each with its page URL, line and a relevance score. Token-efficient way to answer a question from docs without packing the whole site.
Inputs: url (required), query (required), depth, max_pages, +2 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Query any docs site via MCP. Submit a URL, ask questions, get cited answers.
Scrape, crawl and search the web for AI agents via MCP.
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
Agent-driven search: build, import, tune, search, and score result quality — all over MCP.
Add one secure layer between your agents and this server.
