Directory / Media & generation
UberLLM
Generate and edit images, start and follow video and music jobs, list models with current prices, quote a request before running it, and check the balance through one UberLLM API key (required, prepaid). Endpoint: https://api.uberllm.dev/mcp
Live Answered an MCP handshake without credentials and listed 9 tools.
- Category
- Media & generation
- Transport
http- Source
- https://uberllm.dev/docs/mcp
- Endpoint
https://api.uberllm.dev/mcp- MCP Registry
dev.uberllm/mcp- Reports itself as
- uberllm 1.0.0
- Protocol
- 2025-06-18
- Tools
- 9
- Context cost
- about 1,607 tokens for the tool definitions (estimated at four characters per token)
- Tool definitions last changed
- 2026-11-19
- Handshake time
- 159 ms
- Last checked
- 2026-11-22 11:27:52 UTC
- Listed since
- 2026-11-18
Health and compatibility
| Endpoint reachable | Verified | Responded in 159 ms |
|---|---|---|
| MCP handshake (initialize) | Verified | Completed without credentials |
| Tool discovery (tools/list) | Verified | 9 tools listed |
| Authentication | Verified | None needed to connect |
| Protocol version | Verified | 2025-06-18 |
| Transport | Verified | Streamable HTTP |
| Capabilities declared | Verified | logging, tools |
Last checked . Verified means the check saw it happen; it says nothing about whether the server is safe.
Recent history
5 daily checks so far; median response 159 ms. Green answered, violet asked for auth, red did not answer.
Set up in your client
Claude Code
Run this in a terminal:
claude mcp add --transport http uberllm https://api.uberllm.dev/mcpClaude Desktop
Open Settings → Connectors → Add custom connector and paste this URL:
https://api.uberllm.dev/mcpOr bridge it through mcp-remote in claude_desktop_config.json (needs Node.js):
{
"mcpServers": {
"uberllm": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.uberllm.dev/mcp"
]
}
}
}Cursor
Or add it to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):
{
"mcpServers": {
"uberllm": {
"url": "https://api.uberllm.dev/mcp"
}
}
}VS Code
Or add it to .vscode/mcp.json:
{
"servers": {
"uberllm": {
"type": "http",
"url": "https://api.uberllm.dev/mcp"
}
}
}Or from a terminal:
code --add-mcp '{"name": "uberllm", "type": "http", "url": "https://api.uberllm.dev/mcp"}'Windsurf
Add it to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"uberllm": {
"serverUrl": "https://api.uberllm.dev/mcp"
}
}
}Other clients
Most clients accept this shape. The endpoint is:
https://api.uberllm.dev/mcp{
"mcpServers": {
"uberllm": {
"type": "http",
"url": "https://api.uberllm.dev/mcp"
}
}
}If it does not connect
- Restart the client after editing a config file, and keep keys out of files you commit.
- If the tools do not appear, open the client's MCP log: a 401 means the credentials were not accepted, and a timeout means the server did not answer.
Tools 9
Names, descriptions and input schemas exactly as the server returned them on 2026-11-22. This is the server author's own text. Nothing is run from this page. Labels such as read-only are declared by the server and are not verified. Raw JSON
balanceread-onlyYour balance in US dollars: what you can spend now and what is held for requests and jobs still running.
Your balance in US dollars: what you can spend now and what is held for requests and jobs still running.
Takes no parameters.
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "balance",
"arguments": {}
}
}edit_imagecan modifyexternal accessChange a picture you give (image_url or input_images, as https:// links or data: URIs) following a prompt, …
Change a picture you give (image_url or input_images, as https:// links or data: URIs) following a prompt, with an editing model. Spends from your balance.
| Parameter | Type | Description | |
|---|---|---|---|
model | string | required | An image model id. |
prompt | string | required | What to make. |
n | integer | optional | How many pictures, 1 to 10. Default 1. |
size | string | optional | Width x height, e.g. 1024x1024, when the model lists sizes. |
aspect_ratio | string | optional | Shape, e.g. 16:9, when the model lists aspect ratios. |
max_cost | number | optional | The most you will pay in US dollars; a request that can cost more is refused before anything is spent. |
return_image | boolean | optional | Also return the pictures themselves in the answer, so you can look at them. |
options | object | optional | Any other option from get_model's parameters schema. |
image_url | string | optional | The picture to change: an https:// link or a data: URI. |
input_images | null | array | optional | Several pictures to work from (https:// links or data: URIs). |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "edit_image",
"arguments": {
"model": "...",
"prompt": "..."
}
}
}generate_imagecan modifyexternal accessMake pictures from a prompt. Spends from your balance; the answer carries the links and what it cost …
Make pictures from a prompt. Spends from your balance; the answer carries the links and what it cost (usage.cost_usd).
| Parameter | Type | Description | |
|---|---|---|---|
model | string | required | An image model id. |
prompt | string | required | What to make. |
n | integer | optional | How many pictures, 1 to 10. Default 1. |
size | string | optional | Width x height, e.g. 1024x1024, when the model lists sizes. |
aspect_ratio | string | optional | Shape, e.g. 16:9, when the model lists aspect ratios. |
max_cost | number | optional | The most you will pay in US dollars; a request that can cost more is refused before anything is spent. |
return_image | boolean | optional | Also return the pictures themselves in the answer, so you can look at them. |
options | object | optional | Any other option from get_model's parameters schema. |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "generate_image",
"arguments": {
"model": "...",
"prompt": "..."
}
}
}get_jobread-onlyThe status of a video or music job, its progress and, once it succeeded, the links to its files and what it …
The status of a video or music job, its progress and, once it succeeded, the links to its files and what it cost.
| Parameter | Type | Description | |
|---|---|---|---|
job_id | string | required | The job id start_video returned. |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "get_job",
"arguments": {
"job_id": "..."
}
}
}get_modelread-onlyOne model: its price, what it makes and, for an image, video, music or speech model, a JSON Schema of the …
One model: its price, what it makes and, for an image, video, music or speech model, a JSON Schema of the options a request takes (parameters).
| Parameter | Type | Description | |
|---|---|---|---|
model | string | required | The model id, e.g. bytedance/seedance-2-0-fast-image-to-video. |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "get_model",
"arguments": {
"model": "..."
}
}
}list_modelsread-onlyModels you can call right now, with their price. Filter by type (chat, image, video, music, speech, …
Models you can call right now, with their price. Filter by type (chat, image, video, music, speech, transcription) and by words in the id or name.
| Parameter | Type | Description | |
|---|---|---|---|
type | string | optional | Only models of this type: chat, image, video, music, speech or transcription. One of: chat, image, video, music, speech, transcription |
search | string | optional | Only models whose id or name contains these words, e.g. seedance or kling. |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "list_models",
"arguments": {}
}
}quoteread-onlyCheck an image, video, music or text-to-speech request against the model and price it, without making …
Check an image, video, music or text-to-speech request against the model and price it, without making anything or spending. Returns the listed price (cost_usd; the bill is what the provider charges, which can be less or more) and what is held while it runs (max_cost_usd: it is never billed more).
| Parameter | Type | Description | |
|---|---|---|---|
model | string | required | The model id. |
prompt | string | optional | What to make. |
options | object | optional | The rest of the request, as get_model's parameters schema describes it, e.g. {"duration_seconds": 5, "image_url": "https://..."}. |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "quote",
"arguments": {
"model": "..."
}
}
}start_videocan modifyexternal accessStart making a video. Returns a job; call wait_job with its id until it is done. Spends from your balance …
Start making a video. Returns a job; call wait_job with its id until it is done. Spends from your balance when the video is made; a failed job costs nothing.
| Parameter | Type | Description | |
|---|---|---|---|
model | string | required | A video model id. |
prompt | string | required | What to make. |
image_url | string | optional | The first frame (https:// link or data: URI); needed by image-to-video models. |
end_image_url | string | optional | The last frame, for models that make a transition. |
duration_seconds | number | optional | Length in seconds; one of the lengths get_model lists. |
resolution | string | optional | e.g. 720p, when the model lists resolutions. |
aspect_ratio | string | optional | e.g. 16:9, when the model lists aspect ratios. |
max_cost | number | optional | The most you will pay in US dollars; a job that can cost more is refused before anything is spent. |
idempotency_key | string | optional | Send the same key when you retry, so a retry never starts or pays for a second video. |
options | object | optional | Any other option from get_model's parameters schema. |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "start_video",
"arguments": {
"model": "...",
"prompt": "..."
}
}
}wait_jobread-onlyWait until a video or music job ends, for at most timeout_seconds (50 at most). Returns the job; if done is …
Wait until a video or music job ends, for at most timeout_seconds (50 at most). Returns the job; if done is false, call wait_job again.
| Parameter | Type | Description | |
|---|---|---|---|
job_id | string | required | The job id start_video returned. |
timeout_seconds | integer | optional | How long to wait, 1 to 50 seconds. Default 50. |
Example call (required arguments only, placeholder values):
{
"method": "tools/call",
"params": {
"name": "wait_job",
"arguments": {
"job_id": "..."
}
}
}Badge
Maintain this server? Put its live status in your README:
[](https://mcp.aianytime.net/s/uberllm/)Edit this entry · Report a problem
More in Media & generation
Checks record what a server answered, not whether it is safe. A listing is not a security audit; read a server's source and permissions before you connect it. Add a server · JSON · llms.txt · llms-full.txt
Browse: Agents, IDEs & developer tools · Search & discovery · Knowledge, memory & context · Media & generation · Security · Finance & markets · Marketing, content & social · Cloud, ops & data · Commerce, travel & logistics · Work & productivity · No account needed · Local servers