# UberLLM (remote · api.uberllm.dev)

Make images and videos, price requests, list AI models and read your balance, from one API key.

- Trust score: 76/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `api.uberllm.dev`: 76/100 (this document), [markdown](https://verifymcp.io/servers/dev-uberllm-mcp/api.md), [page](https://verifymcp.io/servers/dev-uberllm-mcp/api)

## Channel facts

- Endpoint: `https://api.uberllm.dev/mcp`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1260 tokens (~140/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the UberLLM MCP server?

UberLLM is a hosted endpoint at https://api.uberllm.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http dev-uberllm-mcp 'https://api.uberllm.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-uberllm-mcp": {
      "url": "https://api.uberllm.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-uberllm-mcp": {
      "type": "http",
      "url": "https://api.uberllm.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-uberllm-mcp]
url = "https://api.uberllm.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-uberllm-mcp": {
      "type": "remote",
      "url": "https://api.uberllm.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-uberllm-mcp --url 'https://api.uberllm.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-uberllm-mcp:
    url: "https://api.uberllm.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-uberllm-mcp": {
      "Transport": "http",
      "Url": "https://api.uberllm.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-uberllm-mcp -t streamable-http -u 'https://api.uberllm.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-uberllm-mcp": {
      "type": "http",
      "url": "https://api.uberllm.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 76, +40)

- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100

### 2026-10-30 (score 36)

First indexed and scored.

## MCP tools (9)

### `balance` (~29 tokens)

Balance

Your balance in US dollars: what you can spend now and what is held for requests and jobs still running.

### `edit_image` (~250 tokens)

Edit an image

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.

Input parameters:

- `aspect_ratio` (string): Shape, e.g. 16:9, when the model lists aspect ratios.
- `image_url` (string): The picture to change: an https:// link or a data: URI.
- `input_images` (null|array): Several pictures to work from (https:// links or data: URIs).
- `max_cost` (number): The most you will pay in US dollars; a request that can cost more is refused before anything is spent.
- `model` (string, required): An image model id.
- `n` (integer): How many pictures, 1 to 10. Default 1.
- `options` (object): Any other option from get_model's parameters schema.
- `prompt` (string, required): What to make.
- `return_image` (boolean): Also return the pictures themselves in the answer, so you can look at them.
- `size` (string): Width x height, e.g. 1024x1024, when the model lists sizes.

### `generate_image` (~194 tokens)

Make an image

Make pictures from a prompt. Spends from your balance; the answer carries the links and what it cost (usage.cost_usd).

Input parameters:

- `aspect_ratio` (string): Shape, e.g. 16:9, when the model lists aspect ratios.
- `max_cost` (number): The most you will pay in US dollars; a request that can cost more is refused before anything is spent.
- `model` (string, required): An image model id.
- `n` (integer): How many pictures, 1 to 10. Default 1.
- `options` (object): Any other option from get_model's parameters schema.
- `prompt` (string, required): What to make.
- `return_image` (boolean): Also return the pictures themselves in the answer, so you can look at them.
- `size` (string): Width x height, e.g. 1024x1024, when the model lists sizes.

### `get_job` (~49 tokens)

Get a job

The status of a video or music job, its progress and, once it succeeded, the links to its files and what it cost.

Input parameters:

- `job_id` (string, required): The job id start_video returned.

### `get_model` (~70 tokens)

Get a model

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).

Input parameters:

- `model` (string, required): The model id, e.g. bytedance/seedance-2-0-fast-image-to-video.

### `list_models` (~92 tokens)

List models

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.

Input parameters:

- `search` (string): Only models whose id or name contains these words, e.g. seedance or kling.
- `type` (string): Only models of this type: chat, image, video, music, speech or transcription.

### `quote` (~122 tokens)

Quote a request

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: it is never billed more) and what is held while it runs (max_cost_usd).

Input parameters:

- `model` (string, required): The model id.
- `options` (object): The rest of the request, as get_model's parameters schema describes it, e.g. {"duration_seconds": 5, "image_url": "https://..."}.
- `prompt` (string): What to make.

### `start_video` (~245 tokens)

Start a video

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.

Input parameters:

- `aspect_ratio` (string): e.g. 16:9, when the model lists aspect ratios.
- `duration_seconds` (number): Length in seconds; one of the lengths get_model lists.
- `end_image_url` (string): The last frame, for models that make a transition.
- `idempotency_key` (string): Send the same key when you retry, so a retry never starts or pays for a second video.
- `image_url` (string): The first frame (https:// link or data: URI); needed by image-to-video models.
- `max_cost` (number): The most you will pay in US dollars; a job that can cost more is refused before anything is spent.
- `model` (string, required): A video model id.
- `options` (object): Any other option from get_model's parameters schema.
- `prompt` (string, required): What to make.
- `resolution` (string): e.g. 720p, when the model lists resolutions.

### `wait_job` (~78 tokens)

Wait for a job

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.

Input parameters:

- `job_id` (string, required): The job id start_video returned.
- `timeout_seconds` (integer): How long to wait, 1 to 50 seconds. Default 50.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-uberllm-mcp/api#diagnostics

## Score history

- 2026-11-05: 76
- 2026-11-04: 36
- 2026-11-03: 36
- 2026-11-02: 36
- 2026-11-01: 36
- 2026-10-31: 36
- 2026-10-30: 36

## Common questions

### What is the UberLLM MCP server?

UberLLM is an MCP server listed in the public MCP registry as dev.uberllm/mcp. Make images and videos, price requests, list AI models and read your balance, from one API key. This page covers its hosted endpoint (https://api.uberllm.dev/mcp).

### Is the UberLLM MCP server safe to use?

UberLLM scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the UberLLM MCP server expose?

UberLLM exposes 9 tools: balance, edit_image, generate_image, get_job, get_model, and 4 more. Their descriptions and schemas cost roughly 1,129 tokens of context every time the server is loaded.

### Does the UberLLM MCP server require authentication?

Yes. UberLLM asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the UberLLM MCP server still maintained?

UberLLM is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the UberLLM MCP server?

VerifyMCP ran 12 checks on UberLLM, covering TLS certificate, Authorization, HTTPS, HSTS header and 8 more. One item could not be completed, a gap on our side rather than a finding about UberLLM: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.uberllm.dev/mcp
- Repository: https://github.com/PSA-Team-source/uberllm
- Website: https://uberllm.dev/docs/mcp
- Changelog RSS feed: https://verifymcp.io/servers/dev-uberllm-mcp/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-uberllm-mcp/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/dev-uberllm-mcp/api.json
- HTML version of this page: https://verifymcp.io/servers/dev-uberllm-mcp/api