sprocket-systems.coda.sdk-mcp

MCP server for the Coda audio processing Python SDK. Provides documentation, examples, live data access, and code validation tools for AI-assisted Coda development.

Quick Start

Requires uv — install it with:

curl -LsSf https://astral.sh/uv/install.sh | sh

Add to your MCP client config (Claude Code, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "coda-sdk": {
      "command": "uvx",
      "args": [
        "--from",
        "sprocket-systems.coda.sdk-mcp@x.x.x",
        "coda-sdk-mcp"
      ],
      "env": {
        "CODA_SDK_MCP_CODA_API_TOKEN": "your-token"
      }
    }
  }
}

Replace x.x.x with the desired version. Pinning ensures a consistent environment — uvx will download that version on first run and cache it for subsequent starts.

Tools (15)

Tool	Description
`sdk_get_api_reference`	Get API reference docs for a module
`sdk_get_guide`	Get usage guide by topic
`sdk_search_docs`	Full-text search across SDK docs
`sdk_list_examples`	List available SDK code examples
`sdk_get_example`	Get full content of an example
`sdk_list_presets`	List Coda presets (optionally filtered by type)
`sdk_list_groups`	List Coda groups with IDs
`sdk_list_io_locations`	List Coda IO locations
`sdk_io_list_folders`	List folders at a path within a Coda IO Location
`sdk_io_list_files`	List files with optional glob/regex filtering
`sdk_io_discover_files`	Discover file metadata (format, stem type, timing)
`sdk_get_source`	Get SDK Python source for a module or symbol
`sdk_search_source`	Full-text search across SDK Python source
`sdk_validate_code`	Static validation of Python/SDK code
`sdk_dry_run_code`	Sandboxed execution with Job.run blocked

MCP Prompts (3)

Prompt	Description
`sdk_build_job`	Step-by-step guide to build a Coda job
`sdk_modify_workflow`	Guide to modify existing workflows
`sdk_troubleshoot`	Debug SDK issues systematically

Configuration

Variable	Default	Description
`CODA_SDK_MCP_CODA_API_TOKEN`	—	Coda API token (required for live data/dry-run)
`CODA_SDK_MCP_CODA_BASE_URL`	https://v2.coda.sprocket.systems	Coda API URL
`CODA_SDK_MCP_LOG_LEVEL`	info	Log level
`CODA_SDK_MCP_LOG_FILE`	—	Optional log file path (rotated at 10 MB)
`CODA_SDK_MCP_TRANSPORT`	stdio	Transport: `stdio` (default) or `http`

Docs, examples, search, and static validation work without a token. Live data tools (sdk_list_presets, sdk_list_groups, sdk_list_io_locations, sdk_io_list_folders, sdk_io_list_files, sdk_io_discover_files) and sdk_dry_run_code require CODA_SDK_MCP_CODA_API_TOKEN.

Metadata

Release files for sprocket-systems.coda.sdk-mcp 1.2.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for sprocket-systems.coda.sdk-mcp 1.2.1
File	Size	Uploaded
sprocket_systems_coda_sdk_mcp-1.2.1.tar.gz	121.3 kB	Oct 13, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for sprocket-systems.coda.sdk-mcp 1.2.1
File	Interpreter	ABI	Platform	Reset
sprocket_systems_coda_sdk_mcp-1.2.1-py3-none-any.whl 155.1 kB Oct 13, 2026	Python 3	none	any	Details

Total release size: 276.4 kB

Release files / sprocket_systems_coda_sdk_mcp-1.2.1.tar.gz

Download URL	sprocket_systems_coda_sdk_mcp-1.2.1.tar.gz
Size	121.3 kB
Tags	Source
SHA-256 checksum How to use checksums	`1382f4be2134fa725871c6e59a032fdf27f0fcd0269f2bdd11032a5d6d592f09`
BLAKE2b-256 checksum How to use checksums	`1fd80bc45390a8952506517ebb0fca247a9a19b8ae26b820a03313f53e9057bb`
Upload date	Oct 13, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.9`

Release files / sprocket_systems_coda_sdk_mcp-1.2.1-py3-none-any.whl

Download URL	sprocket_systems_coda_sdk_mcp-1.2.1-py3-none-any.whl
Size	155.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`301bf97c87385b0cbf07ef6f96e7b85a690c50d862f9feb1d3cc852f5b1bd9e2`
BLAKE2b-256 checksum How to use checksums	`66cd323b673ca8d96ec7d90ddb6c8747b721daedbb246ebacfbb5d977c93998d`
Upload date	Oct 13, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.9`