Schema | mcp-repo-search

mcp-repo-search

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_REPO_SEARCH_TEMP_DIR`	No	Base directory for clones (default: os.tmpdir()/mcp-repo-search)
`MCP_REPO_SEARCH_TTL_SECONDS`	No	Idle timeout in seconds before the clone is deleted (default: 300)

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
ensure_repoA	Clone a Git repo to a temp directory (or reuse existing clone). Call this first before search_repo, read_file, or list_directory. Returns the clone path and status. Resets the 5-minute idle timer.
get_repo_statusA	Returns whether a repo is currently cloned, its path, repo URL, and seconds until expiry. Does not clone; call ensure_repo first if needed.
read_fileA	Read a file from the cloned repo. Path is relative to repo root. Call ensure_repo first. Resets idle timer.
list_directoryA	List files and directories in the cloned repo. Path is relative to repo root (default "."). Call ensure_repo first. Resets idle timer.
search_repoA	Search for text or regex in the cloned repo. Optional path (subdir) and fileGlob (e.g. *.ts). Call ensure_repo first. Resets idle timer.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ParitoshMaurya/mcp-repo-search'

If you have feedback or need assistance with the MCP directory API, please join our Discord server