Chutes Media MCP

io.github.TheStreamCodePublished by GitHub account TheStreamCodev2.1.0Updated Nov 7, 2026

Generate image, video, music and speech through Chutes and save assets into your project.

VerifiedSTDIODesktop onlyMedia & DesignAI & ML

Overview

AI-generated overview

Generates image, video, music and speech through Chutes media models and saves the assets into your project workspace.

What you can do
  • Discover available Chutes media models by kind or free-text query
  • Inspect a model's live cords and input schema, with required fields, types, defaults and an example payload
  • Run a generation and save the asset under the output directory, returning the file path
  • Edit existing media by passing workspace file paths such as image or mask, which the server reads and encodes
When to use it
Useful when a coding agent needs to create or edit image, video, music or speech assets as part of a project, and you want the files written directly into the workspace with a provenance record rather than copied by hand.
Requirements
Runs locally over stdio via npm (npx or global install); Node.js 20.3 or newer is required. A Chutes API key must be supplied in the CHUTES_API_KEY environment variable. Optional variables tune the auth scheme, API base URL, output directory, warmup, cold-start retries, asset size limit, progress interval, unknown-parameter handling and provenance. Network access to Chutes is needed.
Before you install
Generation consumes Chutes GPU calls and may incur costs on your Chutes account. The server sends prompts and any referenced workspace files to Chutes, so avoid passing sensitive content. It writes files into the workspace and can overwrite existing assets only when overwrite is explicitly set. The API key is read from CHUTES_API_KEY and kept in memory; custom API base URLs never receive the key. It is an independent community project, not affiliated with Chutes.

Installation

In SourceWeft

  1. Open Chutes Media MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Chutes Media MCP

Generate image, video, music, and speech through Chutes from any coding agent, with the asset saved straight into the project you are working on.

[CI] [License] [npm]

[Chutes Media MCP at work: an MCP client, the model's live schema, and media saved into the workspace]

Chutes Media MCP is a Model Context Protocol (MCP) server and command-line interface (CLI) that give coding agents access to Chutes media models. It ships as an MCP server on standard input/output (stdio), a thin CLI for agents without MCP support, and a bundled Agent Skill for the describe-then-generate workflow.

Instead of hardcoding a payload per model, the server fetches the model's live schema and validates each request before spending a GPU call, then writes the asset and a provenance record into your workspace. It works with Claude Code, Cursor, Cline, Windsurf, Codex, OpenCode, and Claude Desktop.

This is an independent community project. It is not affiliated with, sponsored by, or endorsed by Chutes.

Install

Run the server from npm without installing it globally:

bash
npx -y chutes-media-mcp

Install it globally to put both binaries on your path:

bash
npm install -g chutes-media-mcp

Register the server with Claude Code:

bash
claude mcp add chutes-media --env CHUTES_API_KEY=cpk_your_key -- npx -y chutes-media-mcp

For Cursor, Cline, Windsurf, OpenCode, and Claude Desktop, add the mcpServers entry documented in docs/mcp-and-cli.md. Running from GitHub instead of npm is supported with npx -y github:TheStreamCode/chutes-media-mcp. Upgrading from 1.x? See docs/migration-2.0.md.

Quick start

  1. Create a Chutes API key at chutes.ai and register the server as shown under Install.
  2. Ask your agent for an asset: "Generate a cinematic hero image of a misty mountain range and save it in this project."
  3. The agent discovers a suitable model, reads its live schema, validates the payload, and saves the result under assets/chutes/image/. The returned path is ready to reference from your code.

The same describe-then-generate flow is available from a shell through the chutes-media CLI. See docs/mcp-and-cli.md for the tool reference, CLI examples, and image editing.

Features

  • Four media kinds (image, video, music, speech), plus image editing when a model exposes an edit cord such as img2img or inpaint.
  • Live model contract: cords and input schema are fetched at runtime, never hardcoded.
  • Payload validation against the live schema before any GPU call is made.
  • Workspace-contained file access; existing assets survive unless overwrite is explicitly set.
  • A provenance sidecar per asset with model, cord, params, and schema hash.
  • Automatic cold-start retry with backoff for models that scale to zero.
  • Progress updates for long video and music jobs.
  • One shared core, so the MCP server and the CLI behave identically.

Requirements

  • Node.js 20.3 or newer for the published server and CLI. Node.js 20 is end-of-life; use Node.js 22 or 24 LTS in production.
  • A Chutes API key.
  • Contributors using the locked toolchain need Node.js ^20.19.0, >= 22.13.0, or >= 24.

Configuration

VariableRequiredDefaultPurpose
CHUTES_API_KEYYesnoneChutes API key. Read from the environment; never written to disk.
CHUTES_AUTH_SCHEMENorawHow the key is sent in Authorization: raw (the key as-is) or bearer (value prefixed with Bearer and a space). On a 401, try the other value.
CHUTES_API_BASE_URLNohttps://api.chutes.aiManagement API base URL. HTTPS is required except for loopback development; custom endpoints never receive the Chutes API key.
CHUTES_OUTPUT_DIRNoassets/chutesOutput directory inside the agent's working directory. A <kind>/ subfolder is appended.
CHUTES_WARMUPNotrueWarm models up before invoking them. Set to false to skip warmup.
CHUTES_COLD_START_RETRIESNo4Retries when a cold model returns 503 no-instances. 0 disables retries.
CHUTES_COLD_START_BACKOFF_MSNo8000Base backoff between cold-start retries; it grows per attempt.
CHUTES_MAX_ASSET_MBNo512Maximum response or local input asset size kept in memory. The maximum is 4096.
CHUTES_PROGRESS_INTERVAL_MSNo5000How often progress heartbeats are emitted while a call blocks.
CHUTES_ALLOW_UNKNOWN_PARAMSNofalseWhen true, accept parameters that are not in the model schema. The default rejects them so a renamed field fails loudly.
CHUTES_PROVENANCENotrueWrite a <asset>.json sidecar with model, cord, params, and schema hash. Set to false to disable.

Generated assets are saved under ./assets/chutes/<kind>/, relative to wherever the agent runs, so they land inside the project. Output traversal and symlink escapes are rejected, and existing files are preserved unless overwrite is enabled.

Privacy and security

The API key is read from CHUTES_API_KEY and kept in memory. Credential-bearing requests go only 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 do not end up in logs. The project collects no telemetry. See SECURITY.md for reporting.

Troubleshooting

A Chutes request returns 401

The key is missing, invalid, or sent with the wrong authentication scheme. Confirm CHUTES_API_KEY is set for the process that launches the server, then set CHUTES_AUTH_SCHEME to bearer or raw, whichever differs from the current value.

A model returns 503 no-instances

The model is scaled to zero and Chutes has no instance ready. The server retries automatically; raise CHUTES_COLD_START_RETRIES and CHUTES_COLD_START_BACKOFF_MS if the delay is too short, or pick another model of the same kind.

Generation fails with an unknown or rejected parameter

The live model schema changed or the parameter name is wrong. Call describe_media_model again and rebuild the payload from the current schema. CHUTES_ALLOW_UNKNOWN_PARAMS=true is a temporary workaround, not a fix.

An asset write is rejected

Every input and output path must resolve inside the current workspace, and an existing file is not replaced implicitly. Pass the explicit overwrite option (or --overwrite in the CLI) after checking the target path.

Development

Requirements: Node.js ^20.19.0, >= 22.13.0, or >= 24 with npm.

bash
git clone https://github.com/TheStreamCode/chutes-media-mcpcd chutes-media-mcpnpm cinpm run checknpm run verify:mcpnpm run release:check

npm run check runs the format check, lint, type check, coverage tests, and the build. npm run verify:mcp starts the built stdio server with a placeholder key and validates the MCP handshake, the instructions and the three tool definitions without calling Chutes. npm run release:check keeps package.json, CHANGELOG.md, CITATION.cff and server.json on the same version. CONTRIBUTING.md covers the Windows path caveat and the opt-in live tests.

Support

Ask usage questions in GitHub Discussions, report reproducible defects in GitHub Issues, and report vulnerabilities privately as described in SECURITY.md.

Contributing

See CONTRIBUTING.md. Pull requests must pass the required CI checks.

License

MIT — see LICENSE. Third-party notices are in NOTICE.

Maintained by Michael Gasperini (Mikesoft). If this project is useful to you, consider sponsoring its maintenance.

Source: README.md at commit 5142afe

Tools

3

list_media_models

List Chutes media models

List available Chutes media-generation models (image / video / music / speech), optionally filtered by kind or a free-text query. Use this to discover a model, then call describe_media_model before generate_media.

Parameterskindlimitquery

describe_media_model

Describe a Chutes media model

Fetch a model's live cords and input schemas so you can compose a valid request. ALWAYS call this before generate_media for an unfamiliar model. Returns every cord (e.g. generate, and img2img/inpaint when present) with its required fields, types, defaults and a minimal example payload.

Parametersmodelrequired

generate_media

Generate media with Chutes

Run a generation and save the asset into the workspace. `params` is the payload you composed from describe_media_model. For editing, `params` may reference workspace file paths (e.g. image, mask) which the server reads and encodes. The asset is saved under output_dir (default ./assets/chutes/<kind>/) and the saved path is returned. Long video/music jobs block with progress updates.

Parameterscordkindrequiredmodelrequiredparamsrequiredfilenameoverwriteoutput_dirtimeout_ms

Version history

2
  1. v2.1.0LatestOct 31, 2026
  2. v2.0.5Sep 16, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts