Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by jurasofish • Documentation & Docs
A lightweight MCP server that lets LLM agents search, chunk, and navigate codebases without embeddings to enable conversational code exploration and review.
Explore and answer questions about a local codebase by searching logically chunked code (functions, classes, sections) without using embeddings.
Perform repository-aware tasks such as generating diffs against a reference branch or listing recently checked-out branches to support PR review workflows.
Iteratively narrow context and fetch exact code chunks (e.g., for code explanation, debugging guidance, or targeted code review) with clear auditability of what was searched.
MCPunk breaks a project's files into logical chunks (functions, classes, markdown sections, etc.) and exposes tools for agents to search files by chunk content, list chunks, and fetch chunk details. It supports multiple built-in chunkers (Python, Markdown, Vue, fallback whole-file) and can produce git diffs and recent-branch information for repository-aware workflows. The design emphasizes auditable, exact-match searching (no embeddings) so an LLM can drill down into relevant code with human-in-the-loop control.
Get a really funny joke! For testing :)
Configure a new project containing files. Each file in the project is split into 'chunks' - logical sections like functions, classes, markdown sections, and import blocks. After configuring, a common workflow is: 1. list_all_files_in_project to get an overview of the project (with an initial limit on the depth of the search) 2. Find files by function/class definition: find_files_by_chunk_content(... ["def my_funk"]) 3. Find files by function/class usage: find_files_by_chunk_content(... ["my_funk"]) 4. Determine which chunks in the found files are relevant: find_matching_chunks_in_file(...) 5. Get details about the chunks: chunk_details(...) Use ~ (tilde) literally if the user specifies it in paths.
List all files in a project, returning a file tree. This is useful for getting an overview of the project, or specific subdirectories of the project. A project may have many files, so you are suggested to start with a depth limit to get an overview, and then continue increasing the depth limit with a filter to look at specific subdirectories.
Step 1: Find files containing chunks with matching text. Returns file tree only showing which files contain matches. You must use find_matching_chunks_in_file on each relevant file to see the actual matches. Example workflow: 1. Find files: files = find_files_by_chunk_content(project, ["MyClass"]) 2. For each file, find actual matches: matches = find_matching_chunks_in_file(file, ["MyClass"]) 3. Get content: content = chunk_details(file, match_id)
Step 2: Find the actual matching chunks in a specific file. Required after find_files_by_chunk_content or list_all_files_in_project to see matches, as those tools only show files, not their contents. This can be used for things like: - Finding all chunks in a file that make reference to a specific function (e.g. find_matching_chunks_in_file(..., ["my_funk"]) - Finding a chunk where a specific function is defined (e.g. find_matching_chunks_in_file(..., ["def my_funk"]) Some chunks are split into multiple parts, because they are too large. This will look like 'chunkx_part1', 'chunkx_part2', ...
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.