# Chutes Media MCP **Category:** πŸŽ₯ Multimedia Process **Repository:** https://github.com/TheStreamCode/chutes-media-mcp **Views:** 1 **Installs:** 0 **Upvotes:** 0 **Directory Page:** https://allmcps.com/mcp/chutes-media-mcp ## Description Generate image, video, music and speech through Chutes and save assets into your project. ## Claude Desktop Quick Installation Heuristic fallback β€” verify the package name and runner against the repository README before running it. Uses `npx` (confidence: low): ```json "mcpServers": { "chutes-media-mcp": { "command": "npx", "args": ["-y","chutes-media-mcp"] } } ``` ## Documentation & README # chutes-media-mcp [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE) [![Node >= 20.3](https://img.shields.io/badge/node-%3E%3D20.3-brightgreen.svg)](https://nodejs.org) [![npm](https://img.shields.io/npm/v/chutes-media-mcp.svg)](https://www.npmjs.com/package/chutes-media-mcp) [![CI](https://github.com/TheStreamCode/chutes-media-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/TheStreamCode/chutes-media-mcp/actions/workflows/ci.yml) Generate **image, video, music and speech** through [Chutes](https://chutes.ai) from inside any coding agent β€” Claude Code, Cursor, Cline, Windsurf, Codex, OpenCode, Claude Desktop β€” and save the generated asset straight into the project you're working on. > **Independent community project.** Not officially affiliated with or endorsed by Chutes. ## Quick start Requires **Node.js 20.3+** and a [Chutes API key](https://chutes.ai). Add the server to Claude Code: ```bash claude mcp add chutes-media --env CHUTES_API_KEY=cpk_your_key -- npx -y chutes-media-mcp ``` Then ask your agent naturally: > Generate a cinematic hero image of a misty mountain range and save it in this project. The agent discovers a suitable model, reads its live input schema, validates the request, and saves the result under `assets/chutes//`. For Cursor, Cline, Windsurf, OpenCode and Claude Desktop, see [Use as an MCP server](#use-as-an-mcp-server).

chutes-media-mcp

## Why chutes-media-mcp? | Live model contract | Safer project I/O | Project-native output | One shared core | | ----------------------------------------------------------------- | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------ | -------------------------------------------------------------------------- | | Reads each model's current schema instead of hardcoding payloads. | Contains file access to the workspace and protects existing assets by default. | Saves generated media and optional provenance directly beside your code. | MCP and CLI expose the same discovery, validation and generation behavior. | It ships as: - an **MCP server** (`chutes-media-mcp`, stdio) β€” the primary, universal interface, - a thin **CLI** (`chutes-media`) β€” a fallback for shells and agents without MCP support, and - an optional **Agent Skill** ([`skill/chutes-media`](./skill/chutes-media)) documenting the describeβ†’generate workflow (auto-loaded by Claude Code; usable as reference by any agent). Both frontends are thin adapters over one shared, transport-agnostic core. --- ## Features - 🎨 Four media kinds: **image, video, music, speech** β€” plus **image editing** (img2img / inpaint) when a model exposes an edit cord. - πŸ”Ž **describe β†’ generate** workflow: the live model schema is fetched and handed to the agent; payloads are never hardcoded. - πŸ’Ύ Saves assets into your project (default `./assets/chutes//`) and returns the path. - βœ… **Validates** the payload against the live schema before spending a GPU call. - 🧾 **Provenance + guardrails**: writes a sidecar (model, params, schema hash) next to each asset, rejects unknown params, and verifies the returned media type matches what you asked for. - πŸ” **Automatic cold-start retry** with backoff for models scaled to zero. - πŸ“‘ Progress updates during long video/music jobs (MCP progress notifications / CLI stderr). - 🧩 Works everywhere: MCP server **or** CLI, same behavior. ## How it works: describe β†’ generate Chutes models differ wildly (FLUX vs Qwen-Image vs Wan vs LTX vs ACE-Step vs a TTS model), so payloads are **never hardcoded**. The flow is always: 1. **`list_media_models`** β€” discover a model for the kind you want. 2. **`describe_media_model`** β€” fetch the model's live cords and input schema. 3. **`generate_media`** β€” submit the payload you composed; the asset is saved into the workspace. The server owns all the plumbing: auth, cold-start warmup + retry, blocking invocation with progress, downloading, saving, light validation, and best-effort cost reporting. --- ## Requirements - **Node.js β‰₯ 20.3** for the published MCP server and CLI - Use a supported LTS release (**Node.js 22 or 24**) for production. Node.js 20 compatibility is retained for the current major release, but Node.js 20 itself is end-of-life. - Contributors using the locked quality toolchain need **Node.js ^20.19.0, β‰₯ 22.13.0, or β‰₯ 24** - A **Chutes API key** (`CHUTES_API_KEY`). Create one in your Chutes account. ## Installation options An MCP server isn't "installed" like an app β€” it's registered as a **command** in your MCP client's config (see [Use as an MCP server](#use-as-an-mcp-server)). Pick whichever way of providing that command suits you: **1. `npx` from npm β€” recommended (no install):** ```bash npx chutes-media-mcp # MCP server (stdio) npx -p chutes-media-mcp chutes-media --help # CLI bin ``` **2. Global install:** ```bash npm install -g chutes-media-mcp # then `chutes-media-mcp` (server) and `chutes-media` (CLI) are on your PATH ``` **3. Directly from GitHub (no npm needed):** builds on install via the `prepare` script. ```bash npx -y github:TheStreamCode/chutes-media-mcp ``` **4. From source (for development):** ```bash git clone https://github.com/TheStreamCode/chutes-media-mcp cd chutes-media-mcp && npm ci && npm run build # then point your client at: node /abs/path/dist/mcp/server.js ``` > The package ships two bins: `chutes-media-mcp` (the MCP server) and `chutes-media` (the CLI). ## Configuration | Variable | Required | Default | Purpose | | ------------------------------ | -------- | ----------------------- | ---------------------------------------------------------------------------------------------------------------------------- | | `CHUTES_API_KEY` | βœ… | β€” | Your Chutes API key. Read from the environment; never written to disk. | | `CHUTES_AUTH_SCHEME` | | `raw` | How the key is sent in `Authorization`: `raw` (the key as-is) or `bearer` (prefixed `Bearer `). On a 401, try flipping this. | | `CHUTES_API_BASE_URL` | | `https://api.chutes.ai` | Management API base URL. HTTPS is required except for loopback development; custom endpoints receive no Chutes API key. | | `CHUTES_OUTPUT_DIR` | | `assets/chutes` | Output directory inside the agent's CWD. A `/` subfolder is appended. | | `CHUTES_WARMUP` | | `true` | Warm models up before invoking. Set `false` to skip. | | `CHUTES_COLD_START_RETRIES` | | `4` | Retries when a cold model returns `503 no-instances` (`0` disables). | | `CHUTES_COLD_START_BACKOFF_MS` | | `8000` | Base backoff between cold-start retries (grows per attempt). | | `CHUTES_MAX_ASSET_MB` | | `512` | Maximum response or local input-asset size accepted in memory (max `4096`). | | `CHUTES_PROGRESS_INTERVAL_MS` | | `5000` | How often progress heartbeats are emitted while a call blocks. | | `CHUTES_ALLOW_UNKNOWN_PARAMS` | | `false` | When `true`, allow params not in the model schema. Default rejects them so a renamed/unknown field fails loudly. | | `CHUTES_PROVENANCE` | | `true` | Write a `.json` provenance sidecar (model, cord, params, schema hash). Set `false` to disable. | Generated assets are saved to `./assets/chutes//` by default, relative to wherever the agent is running β€” so they land inside the project being worked on. Output traversal and symlink escapes are rejected. Existing files are not replaced unless `overwrite` is explicitly enabled. --- ## Use as an MCP server **Claude Code:** ```bash claude mcp add chutes-media --env CHUTES_API_KEY=cpk_your_key -- npx -y chutes-media-mcp ``` **Cursor / Cline / Windsurf / OpenCode / Claude Desktop** (generic `mcpServers` config): ```json { "mcpServers": { "chutes-media": { "command": "npx", "args": ["-y", "chutes-media-mcp"], "env": { "CHUTES_API_KEY": "cpk_your_key" } } } } ``` > To run without npm, replace the args with `["-y", "github:TheStreamCode/chutes-media-mcp"]`. ### Tools - **`list_media_models`** β€” `{ kind?, query?, limit? }` β†’ matching models. - **`describe_media_model`** β€” `{ model }` β†’ every cord with required fields, types, defaults, a minimal example payload, and a top-level `supportsEditing`. Call this before generating. - **`generate_media`** β€” `{ model, kind, params, cord?, output_dir?, filename?, timeout_ms?, overwrite? }` β†’ runs the generation and returns `{ path, kind, model, cord, bytes, contentType, cost?, durationMs, schemaHash?, provenancePath? }`. `params` is what you composed from the described schema. `schemaHash` pins the exact cord schema the payload was validated against; `provenancePath` points at the sidecar (omitted when `CHUTES_PROVENANCE=false`). Each tool publishes an output schema and returns the same JSON object both as text and as MCP `structuredContent`, so clients can consume typed results without parsing the text representation. ### Example agent workflow > "Generate a hero image of a misty mountain range and drop it into the landing page." The agent calls `describe_media_model` on an image model, composes `{ prompt: "misty mountain range at dawn, cinematic", width: 1024, height: 1024 }`, calls `generate_media`, gets back `./assets/chutes/image/-.png`, and references that path in `index.html`. --- ## Use as a CLI ```bash export CHUTES_API_KEY="cpk_your_key" # PowerShell: $env:CHUTES_API_KEY = "cpk_..." # Discover models chutes-media list --kind image chutes-media list --query flux # Inspect a model's schema chutes-media describe owner/model-slug # Generate (inline JSON, @file, or a path to a .json file for --params) chutes-media generate --kind image --model owner/model-slug \ --params '{"prompt":"a red bicycle on a cobblestone street"}' # Replacing an existing named asset must be explicit chutes-media generate --kind image --model owner/model-slug --filename hero.jpg --overwrite \ --params '{"prompt":"a red bicycle on a cobblestone street"}' ``` Progress is printed to **stderr**; the JSON result (including the saved `path`) is printed to **stdout**, so agents can parse it. --- ## Image editing (img2img / inpaint) Chutes has **no platform-wide edit endpoint**. Editing exists only when a model publishes an edit cord (e.g. `img2img`, `inpaint`) or is a dedicated edit model. `describe_media_model` reports `supportsEditing` and lists those cords. To use one, reference a workspace file in `params` (a single field like `image`, or an array like `image_b64s`) β€” the server reads the file and base64-encodes it: ```bash chutes-media generate --kind image --model owner/edit-capable --cord img2img \ --params '{"prompt":"make it snowy","image":"assets/chutes/image/scene.jpg","strength":0.6}' ``` When a model has no edit cord, only generation is available. --- ## Agent Skill (optional) The MCP server already ships **instructions** (the describeβ†’generate workflow), so any client receives guidance on connect β€” no skill required. For Claude Code you can additionally install the bundled **Agent Skill** ([`skill/chutes-media`](./skill/chutes-media)) for richer, auto-loaded guidance: ```bash npx -p chutes-media-mcp chutes-media install-skill # β†’ ~/.claude/skills/chutes-media npx -p chutes-media-mcp chutes-media install-skill --project # β†’ ./.claude/skills/chutes-media ``` (Or copy the folder into your skills directory manually.) Agents without skill auto-loading don't need it β€” the tool descriptions and server instructions already guide them. --- ## Cost Chutes prices by compute units. When a model exposes the cost via a response header it is returned as `cost`; otherwise `cost` is omitted. Check the [Chutes pricing](https://chutes.ai) for per-model rates. > πŸ’‘ Many public models scale to zero and may return `503 no-instances` until they warm up. The > server retries automatically; if a model stays cold, pick another of the same kind. --- ## Development See [CONTRIBUTING.md](./CONTRIBUTING.md) for setup, the build/test commands, and the Windows `#`-path caveat. Quick version: ```bash npm ci npm run check ``` ## Security Never commit your API key. Credential-bearing requests are limited to HTTPS Chutes hosts, remote asset URLs are screened against private-network destinations, and file access is contained to the workspace. Query strings and fragments are removed from network-error messages so signed asset URLs are not copied into logs. See [SECURITY.md](./SECURITY.md) for details and vulnerability reporting. ## Migrating from 1.x Version 2.0 makes the safety boundaries enforceable instead of best-effort: - Existing named assets are preserved unless `overwrite` / `--overwrite` is explicitly set. - Input and output paths must resolve inside the current workspace; symlink and junction escapes are rejected. - Custom management API URLs require HTTPS, except loopback URLs used for local development. The Chutes API key is never attached to custom or loopback management endpoints. - Management and invocation credentials are sent only to HTTPS Chutes hosts, and asset downloads must resolve to public HTTPS destinations. - Responses and local input assets are capped by `CHUTES_MAX_ASSET_MB` (512 MiB by default). If an existing automation intentionally replaces a file, add the explicit overwrite option after confirming the target path. ## Support - Ask usage questions in [GitHub Discussions](https://github.com/TheStreamCode/chutes-media-mcp/discussions). - Report reproducible bugs through [GitHub Issues](https://github.com/TheStreamCode/chutes-media-mcp/issues). - Report vulnerabilities privately by following [SECURITY.md](./SECURITY.md). ## Author Built by **[Michael Gasperini](https://mikesoft.it)** β€” founder of [Mikesoft](https://mikesoft.it), building small, focused, privacy-aware developer tools. [![Sponsor](https://img.shields.io/badge/Sponsor-EA4AAA?logo=githubsponsors&logoColor=white)](https://github.com/sponsors/TheStreamCode) If this project is useful to you, consider [sponsoring its development](https://github.com/sponsors/TheStreamCode). ## License [MIT](./LICENSE) Β© Michael Gasperini (Mikesoft). Project-owned code, documentation, and other project-created materials are MIT-licensed except for the third-party rights below. ## Third-party notices and provider terms This independent project is not affiliated with, sponsored by, or endorsed by Chutes Global Corp. The Chutes name, logo, platform, services, branding, and related marks are the property of Chutes Global Corp or their respective owners. The MIT License and this project grant no rights to use them. [`assets/chutes-media-mcp.png`](https://github.com/TheStreamCode/chutes-media-mcp/blob/main/assets/chutes-media-mcp.png) is the only project image in this repository that incorporates Chutes logo/marks. It is one of exactly three user-created Chutes-logo image compositions across the Chutes projects; the embedded Chutes logo/marks remain the property of their owner and are not licensed under MIT. The MIT License does not grant rights in Chutes services or in third-party models, model content, or generated outputs. Their use is subject to applicable provider terms and model licenses. Review Chutes' official [Terms of Service](https://chutes.ai/terms) and [Privacy Policy](https://chutes.ai/privacy). See [NOTICE](./NOTICE) for the packaged notice.