compute_similarity — embedding search MCP Tool
compute_similarity
(compute similarity) is one of 3 tools on the
embedding search
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call compute_similarity from your client
- Claude Code embedding search compute_similarity run in your project directory
- Claude Desktop embedding search compute_similarity ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor embedding search compute_similarity ~/.cursor/mcp.json
- VS Code embedding search compute_similarity .vscode/mcp.json
- Zed embedding search compute_similarity ~/.config/zed/settings.json
- Windsurf embedding search compute_similarity ~/.codeium/windsurf/mcp_config.json
- Cline embedding search compute_similarity ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI embedding search compute_similarity ~/.gemini/settings.json
- Grok embedding search compute_similarity .mcp.json (in your project root)
- ChatGPT embedding search compute_similarity Settings → Connectors → Advanced → Developer mode
- Claude.ai embedding search compute_similarity Settings → Connectors → Add custom connector
- LangChain embedding search compute_similarity pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http embedding-search https://api.lazy-mac.com/embedding-search/mcpOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.