{
  "markdown": "# GetRun MCP Server\n\nRemote [Model Context Protocol](https://modelcontextprotocol.io) server for\n[GetRun](https://getrun.id) — generate images, video, audio and chat with\n**61 AI models from 16 providers** from inside any MCP client.\n\n```\nhttps://run.getcore.id/mcp\n```\n\nNo API key to paste. The server speaks OAuth 2.1 with dynamic client\nregistration, so a client is authorised once through a consent screen and\nbilled against the same Rupiah balance as the web app and the REST API.\n\n| | |\n|---|---|\n| **Endpoint** | `https://run.getcore.id/mcp` |\n| **Transport** | Streamable HTTP |\n| **Auth** | OAuth 2.1 + dynamic client registration ([RFC 7591](https://datatracker.ietf.org/doc/html/rfc7591)) |\n| **Protocol versions** | `2025-06-18`, `2025-03-26`, `2024-11-05` |\n| **Scopes** | `read`, `generate`, `manage` |\n| **Tools** | 14 |\n| **Pricing** | Per use, in Indonesian Rupiah. No subscription. Failed tasks are not charged. |\n\nThis repository holds the connector's public metadata and setup guide. The\nservice itself is hosted — there is nothing to install and no server to run.\n\n## Install\n\n### Claude (claude.ai)\n\nSettings → Connectors → **Add custom connector**. Name it `GetRun`, paste the\nURL above, save, then press **Connect** and approve the permissions.\n\n### Claude Code\n\n```bash\nclaude mcp add --transport http getrun https://run.getcore.id/mcp\n```\n\nThen run `/mcp` inside a session, pick `getrun`, and complete the browser\nconsent flow once.\n\n### Cursor\n\n`~/.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"getrun\": {\n      \"url\": \"https://run.getcore.id/mcp\"\n    }\n  }\n}\n```\n\n### Any other MCP client\n\nPoint it at the URL. Clients that only speak stdio can bridge with\n[`mcp-remote`](https://www.npmjs.com/package/mcp-remote):\n\n```json\n{\n  \"mcpServers\": {\n    \"getrun\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-remote\", \"https://run.getcore.id/mcp\"]\n    }\n  }\n}\n```\n\n## Tools\n\n| Tool | What it does |\n|---|---|\n| `getrun_generate_image` | Text → image, or image-to-image with a reference |\n| `getrun_generate_video` | Text or image → video clip |\n| `getrun_generate_audio` | Text → song, sound effect, or speech |\n| `getrun_chat` | Chat models, billed per token |\n| `getrun_run_model` | Any catalogue model with its raw parameters |\n| `getrun_list_models` | Catalogue with prices and JSON Schema per model |\n| `getrun_estimate_price` | Cost of a generation before running it |\n| `getrun_get_balance` | Available and reserved balance |\n| `getrun_get_task` | Status and result of a running generation |\n| `getrun_list_creations` | History with prompts, cost and output URLs |\n| `getrun_hide_creation` | Tidy the gallery; billing history is kept |\n| `getrun_list_characters` | Saved characters — a consistent face across generations |\n| `getrun_save_character` | Create or update a character |\n| `getrun_delete_character` | Delete a character; past generations remain |\n\n## Catalogue\n\n61 models from 16 providers, as of September 2026:\n\n| Category | Models | Examples |\n|---|---|---|\n| Video | 27 | Seedance 2.0, Kling 3.0, PixVerse V6, MiniMax H3 |\n| Image | 14 | Nano Banana 2, Seedream 5.0 Pro, GPT Image 2, Qwen3 |\n| Text & chat | 14 | Claude Opus 4.8, Claude Sonnet 5, GPT-5.6, Grok 4.6 |\n| Audio | 6 | Suno V5, ElevenLabs TTS / Music / Sound Effects |\n\nThe live list is always at [`GET /v1/models`](https://getrun.id/v1/models) —\nthis table is a snapshot, that endpoint is the source of truth.\n\n## Billing\n\nIdentical to the REST API: every tool calls `/v1` in the same process, so\npricing, balance reservation, schema validation and rate limits are the same,\nand results appear in the dashboard's usage history.\n\nGeneration tools spend real balance. `getrun_estimate_price` returns the cost\nof a call before you make it, and a task that fails is never charged.\n\n## Also available\n\n- [REST API documentation](https://getrun.id/docs) — one `POST /v1/tasks` for every model\n- [`llms.txt`](https://getrun.id/llms.txt) — the whole API as compact markdown, for coding agents\n- [OpenAPI 3.1 spec](https://getrun.id/openapi-v1.yaml)\n- [Model catalogue](https://getrun.id/market) and [pricing](https://getrun.id/pricing)\n\n## Registry metadata\n\n[`server.json`](./server.json) is the manifest published to the\n[official MCP Registry](https://modelcontextprotocol.io/registry/about) under\nthe DNS-verified namespace `id.getrun`.\n\n## Support\n\n`support@getcore.id` — include the `task_id` or `request_id` when reporting a\nfailed generation.\n\nOperated by PT Core Digital Asia (GetCore), Indonesia.\n",
  "bytes": 4519,
  "sha": "7aad1991908801cf11b373fbe867c1e84198af6aa480bc226f9d8f06fa3c8d36",
  "repo_slug": "getcore-id/getrun-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_id_getrun_getrun_905112cf/readme"
}