API Stock is an MCP server published by io.github.APIStock, hosted at api.api-stock.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 8 tools, including list_models, get_model, estimate_cost, create_generation, create_upload_url.
Generate AI video, images and music. Browse models and prices; OAuth and one prepaid balance.
2 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
List the video, image and music models available, with the starting price of each. Call this first to pick a model.
| Parameter | Type | Description |
|---|---|---|
| type | string | Only models that produce this kind of media. |
| query | string | Case-insensitive match on the model id, name or vendor. |
{
"name": "list_models",
"title": "List models",
"description": "List the video, image and music models available, with the starting price of each. Call this first to pick a model.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"type": {
"enum": [
"video",
"image",
"music"
],
"type": "string",
"description": "Only models that produce this kind of media."
},
"query": {
"type": "string",
"maxLength": 100,
"description": "Case-insensitive match on the model id, name or vendor."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
The full parameter list, price table and an example request for one model. Call this before create_generation: parameters differ between models.
| Parameter | Type | Description |
|---|---|---|
| model * | string | Model id from list_models. |
{
"name": "get_model",
"title": "Get model details",
"description": "The full parameter list, price table and an example request for one model. Call this before create_generation: parameters differ between models.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"model"
],
"properties": {
"model": {
"type": "string",
"description": "Model id from list_models."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}The exact amount create_generation would charge for this request. Nothing is created or charged.
| Parameter | Type | Description |
|---|---|---|
| input * | object | Model parameters, exactly as get_model lists them (camelCase). Media inputs are public URLs. |
| model * | string | Model id from list_models, for example `veo3.1-fast`. |
{
"name": "estimate_cost",
"title": "Estimate cost",
"description": "The exact amount create_generation would charge for this request. Nothing is created or charged.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"model",
"input"
],
"properties": {
"input": {
"type": "object",
"description": "Model parameters, exactly as get_model lists them (camelCase). Media inputs are public URLs.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"model": {
"type": "string",
"description": "Model id from list_models, for example `veo3.1-fast`."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Start a generation. Charges the user's balance and returns a taskId at once; the result arrives later — poll get_task. A failed generation is refunded.
| Parameter | Type | Description |
|---|---|---|
| input * | object | Model parameters, exactly as get_model lists them (camelCase). Media inputs are public URLs. |
| model * | string | Model id from list_models, for example `veo3.1-fast`. |
| webhook | string | HTTPS URL to call when the generation completes. |
| maxCostUsd | number | Refuse the request if it would cost more than this. |
| idempotencyKey | string | Repeat a call with the same key and the same request to get the same task instead of a second charge. |
{
"name": "create_generation",
"title": "Create generation",
"description": "Start a generation. Charges the user's balance and returns a taskId at once; the result arrives later — poll get_task. A failed generation is refunded.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"model",
"input"
],
"properties": {
"input": {
"type": "object",
"description": "Model parameters, exactly as get_model lists them (camelCase). Media inputs are public URLs.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"model": {
"type": "string",
"description": "Model id from list_models, for example `veo3.1-fast`."
},
"webhook": {
"type": "string",
"format": "uri",
"description": "HTTPS URL to call when the generation completes."
},
"maxCostUsd": {
"type": "number",
"minimum": 0,
"description": "Refuse the request if it would cost more than this."
},
"idempotencyKey": {
"type": "string",
"pattern": "^[A-Za-z0-9_.:-]{1,128}$",
"description": "Repeat a call with the same key and the same request to get the same task instead of a second charge."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Get a signed URL to PUT one local image, video or audio file (up to 25 MiB). Upload is free, but requires a positive balance. After PUT succeeds, use publicUrl as a generation input. The upload URL expires in 10 minutes; at most 20 URLs per minute per user.
| Parameter | Type | Description |
|---|---|---|
| contentType * | string | MIME type of the input file. |
| contentLength * | integer | Exact file size in bytes. The upload must have this size. |
{
"name": "create_upload_url",
"title": "Create input upload URL",
"description": "Get a signed URL to PUT one local image, video or audio file (up to 25 MiB). Upload is free, but requires a positive balance. After PUT succeeds, use publicUrl as a generation input. The upload URL expires in 10 minutes; at most 20 URLs per minute per user.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"contentLength",
"contentType"
],
"properties": {
"contentType": {
"enum": [
"image/png",
"image/jpeg",
"image/webp",
"video/mp4",
"video/quicktime",
"video/webm",
"audio/mpeg",
"audio/wav",
"audio/mp4"
],
"type": "string",
"description": "MIME type of the input file."
},
"contentLength": {
"type": "integer",
"maximum": 26214400,
"minimum": 1,
"description": "Exact file size in bytes. The upload must have this size."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Status of a generation and, once finished, the URLs of its files. Pass waitSeconds to wait for it to finish instead of polling in a loop.
| Parameter | Type | Description |
|---|---|---|
| taskId * | string | The taskId create_generation returned. |
| waitSeconds | integer | Wait up to this many seconds for the task to finish (max 30). |
{
"name": "get_task",
"title": "Get task status",
"description": "Status of a generation and, once finished, the URLs of its files. Pass waitSeconds to wait for it to finish instead of polling in a loop.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"taskId"
],
"properties": {
"taskId": {
"type": "string",
"description": "The taskId create_generation returned."
},
"waitSeconds": {
"type": "integer",
"maximum": 30,
"minimum": 0,
"description": "Wait up to this many seconds for the task to finish (max 30)."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}The user's generations, newest first.
| Parameter | Type | Description |
|---|---|---|
| page | integer | |
| type | string | one of ["video","image","music"] |
| status | string | one of ["not_started","processing","finished","failed","expired"] |
| pageSize | integer |
{
"name": "list_generations",
"title": "List recent generations",
"description": "The user's generations, newest first.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"page": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": 1
},
"type": {
"enum": [
"video",
"image",
"music"
],
"type": "string"
},
"status": {
"enum": [
"not_started",
"processing",
"finished",
"failed",
"expired"
],
"type": "string"
},
"pageSize": {
"type": "integer",
"maximum": 20,
"minimum": 1
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}The prepaid balance generations are charged from, and where to top it up.
No parameters.
{
"name": "get_account",
"title": "Get account balance",
"description": "The prepaid balance generations are charged from, and where to top it up.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Generate video, images and music with third-party AI models, paid from the user's prepaid balance. Tool discovery is public. Sign in through OAuth before calling any tool. Generation is asynchronous and costs money: 1. list_models, then get_model for the exact parameters and price of the one you picked. 2. estimate_cost if the user should see the price first. 3. create_generation returns a taskId immediately and charges the balance. 4. get_task with waitSeconds until status is finished, then give the user the file URLs. A failed generation is refunded automatically. Input media (images, video, audio) are passed as public URLs. For a local input file, call create_upload_url, PUT its bytes to uploadUrl using the returned headers, then pass publicUrl as the model input.
Names, descriptions and schemas were written by the server and are shown as data.