repo_read_file

MCP tool from Kubesearch MCP by perfectra1n

Read a text file from a clone (binary refused, large files truncated).

How to use it

repo_read_file is exposed by the Kubesearch MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the repo_read_file tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Kubesearch MCP

$node /absolute/path/to/kubesearch-mcp/dist/index.js

FULL KUBESEARCH MCP LISTING

Other tools in Kubesearch MCP (9)

kubesearch_get_release

/hr/<id>

kubesearch_grep_values

/grep#grep cert-manager.io

kubesearch_search_images

/image#image cert-manager

kubesearch_search_releases

/#cert-manager

kubesearch_status

—

repo_cleanup

Delete a clone early (clones also auto-expire).

repo_clone

Temporarily clone a repo (indexed owner/repo or an https Git URL) and return a handle + a curated file tree.

repo_grep

Substring-search a clone's text files; returns path:line matches. Takes limit and casesensitive.

repo_list_files

List files in a clone (optional sub-path + glob).