MCP
Your coding agent reads the codebase through the same index: search, symbols, code, traces, the graph, impact and answers, over MCP.
- Sign in once with OAuth from the editor, or run it locally with an API key.
- Every tool only reads, and only the repositories you can read.
- What it returns from the code is marked as the repository's, not instructions to follow.
- The sensei command line does the same from a terminal.
Connect it: the setup for each editor
Claude Code
.mcp.json
{ "mcpServers": { "repo-sensei": { "type": "http", "url": "https://reposensei.com/mcp" } } }claude mcp add --transport http repo-sensei https://reposensei.com/mcp
In Claude Code, run /mcp and choose repo-sensei to sign in.
VS Code
.vscode/mcp.json
{ "servers": { "repo-sensei": { "type": "http", "url": "https://reposensei.com/mcp" } } }code --add-mcp '{"name":"repo-sensei","type":"http","url":"https://reposensei.com/mcp"}'Start the server from the MCP view and sign in when VS Code asks.
Cursor
.cursor/mcp.json
{ "mcpServers": { "repo-sensei": { "url": "https://reposensei.com/mcp" } } }In Cursor's MCP settings, sign in to repo-sensei when it asks.
Its tools
- sensei_list_repos
- The repositories you can read.
- sensei_search
- Exact, keyword and meaning search.
- sensei_find_symbol
- Where a symbol is defined.
- sensei_read_code
- A file's lines, numbered.
- sensei_trace
- A feature, hop by hop across layers.
- sensei_graph_neighbors
- What a symbol calls and what calls it.
- sensei_impact
- What a change to a symbol reaches.
- sensei_ask
- An answer with its citations.