Vectr

Name: Vectr
Author: swapnanil

swapnanil

Semantic codebase search + persistent working memory for AI code editors. Local, zero-config, MCP. No API key.

Setup

Choose your client, copy the config, then fill in any required environment variables.

claude mcp add vectr -- uvx vectr

~/.codex/config.toml

[mcp_servers.vectr]
command = "uvx"
args = ["vectr"]

# codex mcp add vectr -- uvx vectr

~/.cursor/mcp.json

{
  "mcpServers": {
    "vectr": {
      "command": "uvx",
      "args": [
        "vectr"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "vectr": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "vectr"
      ]
    }
  }
}

~/.gemini/settings.json

{
  "mcpServers": {
    "vectr": {
      "command": "uvx",
      "args": [
        "vectr"
      ]
    }
  }
}

claude_desktop_config.json

{
  "mcpServers": {
    "vectr": {
      "command": "uvx",
      "args": [
        "vectr"
      ]
    }
  }
}

.trae/mcp.json

{
  "mcpServers": {
    "vectr": {
      "command": "uvx",
      "args": [
        "vectr"
      ]
    }
  }
}