windtools-mcp

ZahidGalea/windtools-mcp

3.3

If you are the rightful owner of windtools-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

WindTools MCP Server provides document embedding and retrieval capabilities using ChromaDB and sentence transformers.

Tools

Functions exposed to the LLM to take actions

list_dir

List the contents of a directory.

Directory path must be an absolute path to a directory that exists.
For each child in the directory, output will have:
- relative path to the directory
- whether it is a directory or file
- size in bytes if file
- number of children (recursive) if directory

Args:
    directory_path: Path to list contents of, should be absolute path to a directory

Returns:
    JSON string containing directory information

get_initialization_status

Get the status of background initialization process.
The background initialization process includes initializing ChromaDB and embedding model.

Returns:
    JSON string with initialization status

index_repository

Index code files from the specified directories into ChromaDB for later search.

This tool scans the specified directories for code files, indexes their content
in ChromaDB, and updates existing entries if they have changed. This enables
high-quality semantic search over the codebase.

Args:
    target_directories: List of absolute paths to directories to index
    force_reindex: If true, will reindex all files even if they already exist in the index

Returns:
    JSON string containing indexing statistics and results

codebase_search

Find snippets of code from the indexed codebase most relevant to the search query.

This performs semantic search over previously indexed code files.
Results are ranked by relevance to the query. For best results, index your
repositories first using the index_repository tool.

Args:
    query: Search query describing what you're looking for
    limit: Maximum number of results to return (default: 10)
    min_relevance: Minimum relevance score threshold (0.0 to 1.0)

Returns:
    JSON string containing search results with relevant code snippets

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources