This server provides focused access to Luma's video modification API through RunAPI, enabling AI agents to create, monitor, and price video tasks.
Authenticate (login): Log in via a browser-based PKCE flow to save credentials to ~/.config/runapi/config.json. Supports a force option to re-authenticate even when valid credentials exist. Alternatively, set the RUNAPI_API_KEY environment variable for headless/CI use.
Create Video Modification Tasks (modify_video): Submit a Luma video modification task with a source video URL and prompt. Supports optional polling until completion (wait: true/false), configurable timeout, and poll interval. Returns a task ID, status, output URLs, and a pricing snapshot.
Poll Task Status (get_task): Fetch the current status and latest result payload for an existing Luma task by its task ID — useful for checking on tasks submitted without waiting.
Check Pricing (check_pricing): Look up the current pricing snapshot for the Luma model and endpoint. No authentication required.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@@runapi.ai/luma-mcp modify video at https://example.com/vid.mp4 to apply a cinematic look"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@runapi.ai/luma-mcp is a focused Model Context Protocol server for the Luma model line on RunAPI.
It gives MCP-compatible assistants direct access to 1 endpoint and 1 model variant without loading the full RunAPI catalog.
Use this per-model server when an agent should stay scoped to Luma. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.
Related MCP server: kling-mcp
Add it to Claude Code:
claude mcp add luma -s user -- npx -y @runapi.ai/luma-mcpUse project scope when the server should be shared with a repository:
claude mcp add luma -s project -- npx -y @runapi.ai/luma-mcpCodex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:
{
"mcpServers": {
"luma": {
"command": "npx",
"args": ["-y", "@runapi.ai/luma-mcp"]
}
}
}check_pricing works before sign-in. For task creation and status polling, ask your assistant to call the login tool. It opens a browser login and saves credentials to ~/.config/runapi/config.json, the same file used by runapi login.
Headless and CI hosts can still set RUNAPI_API_KEY before starting the MCP host.
Ready-made examples are in examples/ for Claude, Cursor, Windsurf, VS Code, and Roo Code.
Tool | Auth | Purpose |
| Yes | Create a Luma modify video task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |
| Yes | Fetch the current status and latest payload for an existing task. |
| No | Look up current pricing for a Luma model and endpoint. |
Luma covers 1 model variant across 1 endpoint. Each tool accepts the models listed for it:
Tool | Models |
|
|
Model availability can change between releases. Use check_pricing or the Luma model page for the current catalog view.
Ask your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.
Run a Luma modify video task with RunAPI.The assistant can call check_pricing, then modify_video, and return the task id, status, and output URLs.
Create the task but don't wait for it to finish.The assistant calls the create tool with wait: false and returns the task id. Check on it later with get_task.
Check current Luma pricing, then create the task if it matches my request.The assistant calls check_pricing and can link to the Luma model page for the canonical catalog entry.
The server resolves auth in this order:
RUNAPI_API_KEY environment variable, useful for headless and CI hosts
~/.config/runapi/config.json, created by the MCP login tool or runapi login
No key, which still allows check_pricing
The config file is normally managed by login. A pre-provisioned headless config can use:
{
"apiKey": "your_runapi_key"
}Do not commit real API keys.
Resource | URL |
Luma model page | |
npm package | |
GitHub repository | |
RunAPI MCP overview | |
RunAPI docs |
Licensed under the Apache License, Version 2.0.
Look up RunAPI pricing for the luma model line.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Model slug. Defaults to the line's primary model. | |
| action | No | Endpoint name. Defaults to the endpoint that offers the model. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description carries full burden. It only states purpose, omitting behavioral traits like being a read-only operation, side-effects, or rate limits. With no extra disclosure, a score of 2 is appropriate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, perfectly front-loaded with the action and resource. No filler words; every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple lookup tool with 2 optional enum parameters and no output schema, the description is adequate. It fully captures the purpose. Could mention return value (pricing data), but not required given low complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, providing clear enum definitions for both parameters. The description adds no additional meaning beyond the schema, so baseline 3 is correct.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Look up') and the specific resource ('RunAPI pricing for the luma model line'). It distinguishes from siblings: 'get_task' retrieves task status, 'modify_video' modifies video content. No ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when pricing info is needed, but provides no explicit guidance on when to use vs. the sibling tools 'get_task' or 'modify_video'. No exclusions or alternatives mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch the current status and latest result payload for a luma task.
| Name | Required | Description | Default |
|---|---|---|---|
| action | No | Asynchronous endpoint the task was created on. Defaults to the line's only asynchronous endpoint. | |
| task_id | Yes | Task id returned when the task was created. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It clearly conveys a read-only fetch operation, but does not disclose potential caveats such as whether the tool blocks until completion, may return empty payloads, or requires authentication. The language is truthful but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no filler. It effectively communicates the core purpose without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a simple schema and no output schema, so the description must clarify return expectations. It mentions status and result payload, but lacks detail on possible states (e.g., pending vs. completed) or payload format, leaving some ambiguity for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters. The description adds no extra meaning beyond identifying a 'luma task', which maps directly to task_id. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool fetches the current status and latest result payload for a task, using a specific verb ('fetch') and resource ('luma task'). This distinguishes it from siblings like login, modify_video, and check_pricing, which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied: you call this tool when you need to check the status or retrieve the result of a previously created Luma task. However, there is no explicit guidance on when to use it versus alternatives, nor any mention of lifecycle prerequisites such as logging in first.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.
| Name | Required | Description | Default |
|---|---|---|---|
| force | No | Re-run browser login when the current credential comes from the local config file. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It mentions browser flow and file saving but doesn't clarify conditional behavior based on existing credentials or force parameter.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words, front-loaded with purpose. Efficient and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity (1 optional param, no output schema), the description covers key aspects but could mention when login is skipped.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the only parameter. The tool description adds no additional meaning beyond the schema's description of 'force'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Authenticate RunAPI' with a specific mechanism (PKCE login flow) and saving location. It distinguishes from siblings which are about pricing, tasks, and video.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for authentication but does not explicitly state when to use vs. alternatives or exclude scenarios. Context from siblings helps but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a Luma task on RunAPI (modify video). Returns a task id, status, and output URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| wait | No | Poll until the task reaches a terminal status. | |
| model | No | RunAPI model slug for this model line. | |
| prompt | Yes | ||
| watermark | No | ||
| timeout_ms | No | ||
| callback_url | No | ||
| poll_interval_ms | No | ||
| source_video_url | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only states that a task is created and returns an ID/status/output URLs, but fails to mention critical behavior such as asynchronous nature, the optional 'wait' parameter, polling, or potential side effects. This is insufficient for a task-creation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the primary purpose and includes the return value. There is no fluff or redundant wording; every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 8 parameters and no output schema or annotations, yet the description provides only a minimal overview. It omits crucial contextual details such as how the task is executed, the meaning of key parameters, and the workflow implications (e.g., using get_task to poll). The description is too sparse for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 25% (wait and model have descriptions), and the tool description adds no parameter meaning. It does not explain what 'prompt' or 'source_video_url' are for, nor mention parameters like 'timeout_ms' or 'callback_url'. The description fails to compensate for the sparse schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create a Luma task') and the resource ('modify video'), and clarifies the platform ('on RunAPI'). It also mentions the return value, making it distinct from sibling tools like get_task (which retrieves) and check_pricing (which checks costs).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for modifying a video via RunAPI, but does not explicitly state when to use this tool versus alternatives like get_task or check_pricing. It gives context but lacks explicit exclusions or alternative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.7get_task1 field changedInput schema / properties / action / descriptionPrevious value: -"Endpoint the task was created on. Defaults to the line's only endpoint."New value: +"Asynchronous endpoint the task was created on. Defaults to the line's only asynchronous endpoint."modify_video5 fields changedInput schema / properties / callback_urlAdded value: +{
+ "type": "string"
+}Input schema / properties / prompt / typeAdded value: +"string"Input schema / properties / source_video_url / typeAdded value: +"string"Input schema / properties / watermarkAdded value: +{
+ "type": "string"
+}Input schema / requiredAdded value: +[
+ "prompt",
+ "source_video_url"
+]v0.1.6loginv0.1.4check_pricingget_taskmodify_videoEach tool has a clear, distinct purpose: login handles authentication, modify_video creates a task, get_task retrieves task status, and check_pricing looks up rates. No two tools overlap in function.
All tool names follow a consistent snake_case verb_noun pattern (login, modify_video, get_task, check_pricing). The naming is predictable and uniform.
With 4 tools, the server is well-scoped for its purpose—covering authentication, task creation, status polling, and pricing. The count is neither excessive nor too sparse.
The core workflow of log in, modify a video, and check task status is fully covered, with pricing lookup as a bonus. Minor gaps like listing or canceling tasks exist, but they aren't essential for the primary use case.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Create and manage cinematic AI video renders through the Future Video Studio Agent API.
Run multi-step AI pipelines for video, image, audio and text: upload media, run, poll results.
130+ AI models for image, video, music, and audio — 18 model families, one RunAPI account.
Create AI images and videos, manage projects and credits, and use workspace campaign context.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/runapi-ai/luma-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
