{
"markdown": "# mcp-helm\n\n[](https://github.com/kubedoll-heavy-industries/helm-mcp/actions/workflows/ci.yml)\n[](https://codecov.io/gh/kubedoll-heavy-industries/helm-mcp)\n[](https://goreportcard.com/report/github.com/kubedoll-heavy-industries/helm-mcp)\n[](https://github.com/kubedoll-heavy-industries/helm-mcp/releases/latest)\n[](LICENSE)\n\nGive your AI assistant access to real Helm chart data. No more hallucinated `values.yaml` files.\n\n## What is this?\n\nWhen you ask Claude, Cursor, or other AI assistants to help with Kubernetes deployments, they don't have access to Helm chart schemas. So they guess — and the guesses look plausible but don't match reality.\n\n**Without mcp-helm:**\n- :x: Hallucinates field names that look right but don't exist\n- :x: Suggests stale or deprecated chart versions\n- :x: Wastes tokens on web fetches and guesswork\n\n**With mcp-helm:**\n- :white_check_mark: Queries actual Helm repositories for real chart data\n- :white_check_mark: Gets the latest chart version automatically\n- :white_check_mark: Correct configurations the first time\n\nmcp-helm implements the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) — a standard way for AI assistants to access external data sources.\n\n## Try It Now\n\nAdd this to your editor's MCP config to use our public instance (rate limited, no install required):\n\n```json\n{\n \"mcpServers\": {\n \"helm\": {\n \"type\": \"http\",\n \"url\": \"https://helm-mcp.kubedoll.com/mcp\"\n }\n }\n}\n```\n\nThen ask your AI: *\"What values can I configure for the bitnami/postgresql chart?\"*\n\n## Editor Setup\n\n\nClaude Code
\n\nEdit `~/.claude/mcp.json`:\n\n```json\n{\n \"mcpServers\": {\n \"helm\": {\n \"command\": \"docker\",\n \"args\": [\"run\", \"--rm\", \"-i\", \"ghcr.io/kubedoll-heavy-industries/mcp-helm\", \"--transport=stdio\"]\n }\n }\n}\n```\n\n \n\n\nClaude Desktop
\n\nEdit `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\\Claude\\claude_desktop_config.json` (Windows):\n\n```json\n{\n \"mcpServers\": {\n \"helm\": {\n \"command\": \"docker\",\n \"args\": [\"run\", \"--rm\", \"-i\", \"ghcr.io/kubedoll-heavy-industries/mcp-helm\", \"--transport=stdio\"]\n }\n }\n}\n```\n\n \n\n\nCursor
\n\nEdit MCP settings in Cursor's configuration:\n\n```json\n{\n \"mcpServers\": {\n \"helm\": {\n \"command\": \"docker\",\n \"args\": [\"run\", \"--rm\", \"-i\", \"ghcr.io/kubedoll-heavy-industries/mcp-helm\", \"--transport=stdio\"]\n }\n }\n}\n```\n\n \n\n\nVS Code + Continue
\n\nAdd to your Continue config (`~/.continue/config.json`):\n\n```json\n{\n \"experimental\": {\n \"modelContextProtocolServers\": [\n {\n \"transport\": {\n \"type\": \"stdio\",\n \"command\": \"docker\",\n \"args\": [\"run\", \"--rm\", \"-i\", \"ghcr.io/kubedoll-heavy-industries/mcp-helm\", \"--transport=stdio\"]\n }\n }\n ]\n }\n}\n```\n\n \n\n\nWithout Docker
\n\nIf you prefer to run the binary directly, [install mcp-helm](#install) and replace the Docker config with:\n\n```json\n{\n \"mcpServers\": {\n \"helm\": {\n \"command\": \"mcp-helm\"\n }\n }\n}\n```\n\n \n\n## Available Tools\n\n| Tool | What it does | Useful parameters |\n|------|--------------|-------------------|\n| `search_charts` | List or search charts in a Helm repo | `keyword` (substring filter), `limit` |\n| `get_versions` | Get available versions of a chart (newest first) | `limit=1` for the latest only |\n| `get_values` | Get chart `values.yaml`, optionally as a focused subsection | `path` (e.g. `.ingress`), `depth` (default 2, `0` for full YAML), `include_schema=true`, `include_examples=true` (requires `path`) |\n| `get_dependencies` | Get a chart's sub-charts (with their repo URLs, which can be fed back into the other tools) | — |\n| `get_notes` | Get chart NOTES.txt (post-install instructions) | — |\n\nOCI registries (`oci://...`) do not support browsing — for OCI you must already know the chart name, then call `get_versions` or `get_values` directly with that name.\n\n## Install\n\n**Docker** (recommended — no install required, used in Editor Setup above):\n\n```bash\ndocker pull ghcr.io/kubedoll-heavy-industries/mcp-helm:latest\n```\n\n**Binary:**\n\n```bash\ncurl -fsSL https://github.com/kubedoll-heavy-industries/helm-mcp/releases/latest/download/mcp-helm_$(uname -s)_$(uname -m).tar.gz | tar xz\nsudo mv mcp-helm /usr/local/bin/\n```\n\n**Go:**\n\n```bash\ngo install github.com/kubedoll-heavy-industries/helm-mcp/cmd/mcp-helm@latest\n```\n\n## Self-Hosting\n\nFor shared deployments or when you need an HTTP endpoint:\n\n```bash\ndocker run -p 8012:8012 ghcr.io/kubedoll-heavy-industries/mcp-helm:latest \\\n --transport=http --listen=:8012\n# Connect to http://localhost:8012/mcp\n```\n\nSee [docs/self-hosting.md](docs/self-hosting.md) for health endpoints and production recommendations.\n\n## Documentation\n\n- [Configuration Reference](docs/configuration.md) — CLI flags, env vars, transport modes\n- [Self-Hosting Guide](docs/self-hosting.md) — Docker HTTP, health endpoints, production tips\n- [Troubleshooting](docs/troubleshooting.md) — common issues and fixes\n- [Contributing](docs/contributing.md) — development setup, testing, PR guidelines\n- [Security Policy](SECURITY.md) — reporting vulnerabilities\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n",
"bytes": 5773,
"sha": "7bd73ada89a4d55973ee220fb2f9b7f31b6d24aeba77400d88469e97b7f5db9e",
"repo_slug": "kubedoll-heavy-industries/helm-mcp",
"fonte": "repo",
"truncated": false,
"api": "https://agentalog.com/api/listings/mcp_io_github_kubedoll_heavy_industries_helm_59c2cafb/readme"
}