{
  "markdown": "# Anaconda MCP\n\n`anaconda mcp` is a CLI and server for exposing conda environment management tools to MCP-enabled AI coding assistants. It acts as a unified MCP endpoint, giving AI assistants like Claude, Cursor, and VS Code awareness of your conda environments, packages, and channel configurations.\n\n📖 **Full documentation:** [anaconda.com/docs](https://www.anaconda.com/docs/cli-reference/anaconda-mcp/getting-started) · [Development Guide](docs/DEVELOPMENT.md)\n\n---\n\n## Prerequisites\n\n- [Conda](https://docs.conda.io/en/latest/) (Miniconda or Anaconda Distribution)\n\n---\n\n## Installation\n\n```bash\nconda create -n anaconda-mcp anaconda-mcp\nconda activate anaconda-mcp\n```\n\n---\n\n## Installation via pip or uvx\n\n**Requires Python 3.10–3.14.**\n\n```bash\npip install anaconda-mcp\n```\n\n```bash\nuvx anaconda-mcp@latest\n```\n\n**Prerequisite:** `conda` must be installed separately and discoverable on your `PATH`. pip and uvx do not provide conda. Without a working conda installation, the conda tools this server exposes will fail. Install [Miniconda or Anaconda Distribution](https://docs.conda.io/en/latest/) first, then follow the `anaconda login` and `anaconda mcp terms accept` steps below.\n\n> **Important:** The Anaconda MCP Server connects your conda environments to MCP-compatible AI assistants, enabling them to create, modify, and delete environments and packages on your machine. Install only if you trust the AI assistant you intend to connect and understand it can take real actions on your machine. By installing you acknowledge: (1) The AI assistant you connect to this MCP server is an independent third-party model, not a product or service of Anaconda. (2) Anaconda is NOT responsible for the actions the AI assistant directs within your environment, including unintended changes or deletions.\n\n---\n\n## Anaconda Login\n\nAuthentication is **required**. The server will not start and tool calls will not succeed without a valid Anaconda login.\n\n```bash\nanaconda login\n```\n\nThis opens a browser for OAuth login and stores the token in your system keyring. Subsequent starts use the stored token automatically.\n\n---\n\n## Accept the Terms of Service\n\nAnaconda MCP requires you to accept the [Beta Terms](https://www.anaconda.com/legal/terms/mcpbeta) before tool calls will succeed.\n\n**Interactive (recommended):**\n\n```bash\nanaconda mcp terms accept\n```\n\n**Non-interactive (CI / headless):**\n\n```bash\nexport ANACONDA_MCP_ACCEPTED_TERMS=true\nexport ANACONDA_MCP_ACCEPTED_TERMS_VERSION=2026-05-27\n```\n\n---\n\n## Setup\n\nConfigure your AI client to use Anaconda MCP:\n\n```bash\nanaconda mcp setup\n```\n\nThis launches an interactive wizard that detects supported clients and writes the appropriate config. Supported clients: Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, OpenCode, and Kilo Code.\n\nTo configure a specific client non-interactively:\n\n```bash\nanaconda mcp setup --client claude-code\nanaconda mcp setup --client cursor --scope project\nanaconda mcp setup --client kilo\n```\n\n### Kilo Code Configuration\n\nAnaconda MCP writes a plain `kilo.json` file (global `~/.config/kilo/kilo.json` or project `.kilo/kilo.json`) which Kilo Code deep-merges with any existing `kilo.jsonc`. This means hand-written comments in `kilo.jsonc` are preserved across `anaconda mcp setup` runs. **Important:** if you hand-edit `kilo.json` itself with comments, `anaconda mcp setup` cannot parse it — it treats the file as empty and silently overwrites it, discarding your changes. Keep comments in `kilo.jsonc` instead.\n\n---\n\n## Manual Client Configuration\n\nIf you prefer to configure your AI client manually, add an entry to your client's MCP config JSON. The `anaconda mcp setup` command resolves the Python path for you, but if writing by hand you'll need the full path to the environment's Python.\n\nExample for Claude Code (`.mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"anaconda-mcp\": {\n      \"type\": \"stdio\",\n      \"command\": \"/path/to/anaconda3/envs/anaconda-mcp/bin/python\",\n      \"args\": [\"-m\", \"anaconda_mcp\", \"serve\"],\n      \"env\": {}\n    }\n  }\n}\n```\n\nOptionally, you can pass authentication and TOS acceptance via the `env` dict instead of running `anaconda login` and `anaconda mcp terms accept`:\n\n```json\n\"env\": {\n  \"ANACONDA_AUTH_API_KEY\": \"<your-api-key>\",\n  \"ANACONDA_MCP_ACCEPTED_TERMS\": \"true\",\n  \"ANACONDA_MCP_ACCEPTED_TERMS_VERSION\": \"2026-05-27\"\n}\n```\n\nAPI keys can be obtained from your [Anaconda account settings](https://anaconda.com/app).\n\n⚠️ **Each client has a different JSON schema.** Check your client's MCP documentation carefully when writing configuration manually — field names and structure vary between Claude Code, Cursor, VS Code, and others.\n\n---\n\n## Experimental: `ana` CLI\n\nThe [`ana` CLI](https://github.com/anaconda/anaconda-cli#installation) handles\nAnaconda MCP runtime installation and environment setup automatically, so you\ndon't need to manage a dedicated `anaconda-mcp` conda environment path.\n\n`ana mcp serve` installs and runs the managed Anaconda MCP runtime. It does not\ninstall Miniconda, Anaconda Distribution, or a user-facing `conda` command. If\nyou want to activate or inspect environments from a terminal, notebook, or other\nlocal tooling, install and configure conda separately for that workflow.\n\nInstall `ana`:\n\n```bash\ncurl -fsSL https://anaconda.sh/install.sh | sh\n```\n\nYou still need to authenticate and accept TOS by running `anaconda login` and `anaconda mcp terms accept` beforehand.\n\nWhen configuring your client manually with `ana`, use:\n\n```json\n{\n  \"mcpServers\": {\n    \"anaconda-mcp\": {\n      \"type\": \"stdio\",\n      \"command\": \"ana\",\n      \"args\": [\"mcp\", \"serve\"],\n      \"env\": {}\n    }\n  }\n}\n```\n",
  "bytes": 5664,
  "sha": "7679b6f2b709e3b3233801d4944a43c1d71b9369d99f8e11c9c4def27eef16f0",
  "repo_slug": "anaconda/anaconda-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_anaconda_anaconda_mcp_37ae97c8/readme"
}