Step Plan MCP MVP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| STEP_API_KEY | Yes | Step Plan API Key. Required for API calls. Can also be configured via the step_configure_api_key tool. | |
| STEP_OUTPUT_DIR | No | Base output directory. Default: outputs/ | outputs/ |
| STEP_API_BASE_URL | No | Base URL for Step API. Default: https://api.stepfun.com | https://api.stepfun.com |
| STEP_MCP_CONFIG_PATH | No | Path to the local configuration file where API key is stored. Default: ~/.step-plan-mcp/config.json | ~/.step-plan-mcp/config.json |
| STEP_AUDIO_OUTPUT_DIR | No | Audio output directory. Default: outputs/audio/ | outputs/audio/ |
| STEP_IMAGE_OUTPUT_DIR | No | Image output directory. Default: outputs/images/ | outputs/images/ |
| STEP_AUDIO_SPEECH_PATH | No | API path for text-to-speech. Default: /step_plan/v1/audio/speech | /step_plan/v1/audio/speech |
| STEP_IMAGE_GENERATIONS_PATH | No | API path for image generation. Default: /step_plan/v1/images/generations | /step_plan/v1/images/generations |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| step_get_setup_statusA | Check whether Step Plan MCP is installed and whether an API key is configured. Use this when the user asks what Step Plan abilities are available or whether setup is complete. |
| step_configure_api_keyA | Save a Step Plan API Key for this local MCP server. Use only when the user explicitly asks to configure or update Step Plan and provides a key. Do not echo the full key back to the user. |
| step_generate_imageA | Generate an image with Step Plan. Use this when the user asks to create an image, poster, visual report, infographic, cover image, social media graphic, or any visual artifact from the current conversation. Before calling, summarize the relevant conversation into a complete image prompt. |
| step_text_to_speechA | Generate speech audio with Step Plan TTS. Use this when the user asks to turn text, scripts, narration, ads, reports, or dialogue into an audio file. Before calling, pass the exact text to be spoken, not a vague reference to prior conversation. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: checking setup status, configuring an API key, generating an image, and generating speech. There is no meaningful overlap between the four tools.
All names use snake_case with a consistent 'step_' prefix, and most follow a verb_noun pattern. 'step_text_to_speech' is the one outlier because it lacks an explicit verb like 'generate' or 'synthesize'.
Four tools is well-scoped for an MVP server that handles setup plus two core generation capabilities. Each tool earns its place without unnecessary bloat.
The setup flow is covered with status and configuration tools, and the two main generation tasks are present. Minor gaps exist around resetting or removing the API key and managing generated outputs, but these are not critical for the stated MVP scope.