# UncensoredLLM (remote · api.uncensoredllm.ai)

Abliterated and derestricted open-weight models on one prepaid key, prices readable without a key

- Trust score: 76/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

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

## Channel facts

- Endpoint: `https://api.uncensoredllm.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - 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**: 75/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2944 tokens (~196/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 93% 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.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

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

UncensoredLLM is a hosted endpoint at https://api.uncensoredllm.ai/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 uplinkswitch-uncensoredllm 'https://api.uncensoredllm.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "uplinkswitch-uncensoredllm": {
      "url": "https://api.uncensoredllm.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "uplinkswitch-uncensoredllm": {
      "type": "http",
      "url": "https://api.uncensoredllm.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.uplinkswitch-uncensoredllm]
url = "https://api.uncensoredllm.ai/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add uplinkswitch-uncensoredllm --url 'https://api.uncensoredllm.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  uplinkswitch-uncensoredllm:
    url: "https://api.uncensoredllm.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "uplinkswitch-uncensoredllm": {
      "Transport": "http",
      "Url": "https://api.uncensoredllm.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add uplinkswitch-uncensoredllm -t streamable-http -u 'https://api.uncensoredllm.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "uplinkswitch-uncensoredllm": {
      "type": "http",
      "url": "https://api.uncensoredllm.ai/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.

### 2026-11-20 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 74, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-15 (score 73)

First indexed and scored.

## MCP tools (15)

### `list_models` (~175 tokens)

List every text model and price

Every chat, embedding, rerank and transcription model on UncensoredLLM with its id, type, the routes and tools that take it, our price (per million tokens, or per audio minute for transcription), the developer's list price where recorded, the wire formats it answers (openai, anthropic, gemini) and its specs. Image, video, speech, music and 3D models are in list_media_models. No key needed. Live from GET /v1/catalog.

Input parameters:

- `developer` (string): Only models from this developer (Anthropic, OpenAI, Google, DeepSeek...).
- `search` (string): A substring of the model id or name (opus, deepseek, uncensored...).
- `type` (string): Only models of this type. Default: every text model.

### `list_media_models` (~99 tokens)

List image, video, speech and 3D models and prices

Every media model on UncensoredLLM with its id, kind, endpoint, unit and price per image, second, generation or minute at each setting, next to the developer's price where recorded. No key needed. Live from GET /v1/catalog/media.

Input parameters:

- `kind` (string): Only models of this kind.
- `search` (string): A substring of the model id or name (nano-banana, veo, kling...).

### `media_model` (~114 tokens)

One media model's settings and prices

Everything generate needs to call one image, video, speech, music or 3D model: each setting under params with its type, the values it takes, its range and its default, and the price per unit at each setting under pricing. No key needed. Live from GET /v1/catalog/media.

Input parameters:

- `model` (string, required): A media model id from list_media_models (nano-banana-2, kling-3.0-pro, seedance-2, elevenlabs-v3, image-upscaler...).

### `estimate` (~166 tokens)

Estimate what a request costs

The cost of a request on every chat model (or the ids given), cheapest first, with the developer's list cost and the saving. Give input_tokens, or a prompt / messages to count from. With the caller's key, prices are the key's own (price locks included). Live from POST /v1/estimate.

Input parameters:

- `input_tokens` (integer): Prompt tokens. Give this or a prompt / messages to count from.
- `messages` (array): Chat messages to estimate from, instead of input_tokens.
- `models` (array): Model ids to price. Default: every chat model, cheapest first.
- `output_tokens` (integer): Completion tokens. Default 1000.
- `prompt` (string): Text to estimate the prompt tokens from, instead of input_tokens.

### `media_quote` (~156 tokens)

Price a generation before running it

What generate would charge for exactly these settings, at the key's own rates: the units billed, the charge, and the developer's own price for the same request where one is on record. The settings are checked as a real request's would be, so a wrong value fails here, not at the model. Nothing runs and nothing is charged. Needs the key. Live from POST /v1/generations/quote.

Input parameters:

- `input` (object, required): The model's settings, as media_model lists them under params: prompt, size or aspect_ratio, resolution, duration, image_urls, text, voice... A setting left out takes the model's default.
- `model` (string, required): A media model id from list_media_models.

### `proof` (~86 tokens)

Daily real-model check

Whether each model is still the model it says it is: every day one fixed prompt goes to every model and the verdict per model is stable, changed, failed or unchecked, with the time of the last check and how long the answer has been unchanged. No key needed. Live from GET /v1/proof.

Input parameters:

- `model` (string): One model id. Default: every model.

### `chat` (~232 tokens)

Send a chat request

Sends messages to any chat model id through POST /v1/chat/completions and returns the answer, the token usage and what the request cost. system adds instructions, image_urls lets a model that sees images look at them (a file generate made works), web_search lets the model search while it answers. Billed to the key in the MCP request's Authorization header (Bearer sk-ullm-live-...); without one it fails.

Input parameters:

- `image_urls` (array): Image URLs attached to the last user message, for the chat models that take images (input_modalities in list_models). A file generate made works.
- `max_tokens` (integer): Cap on completion tokens.
- `messages` (array, required): The conversation, OpenAI chat format.
- `model` (string, required): A chat model id from list_models.
- `system` (string): Instructions placed ahead of the conversation as a system message.
- `temperature` (number)
- `web_search` (boolean): True: the model may search the web while it answers (billed per search, the price in GET /v1/catalog server_tools).

### `compare` (~250 tokens)

Ask several models the same thing

Sends the same conversation (or one prompt) to 2 to 5 chat model ids at once through POST /v1/chat/completions and returns every answer side by side with its token usage, cost and time, plus the total. For a second opinion from another model, or to pick the model that answers a kind of question best. Completions are capped at max_tokens each (default 1024). Each model is billed to the key in the MCP request's Authorization header; a model that fails is reported and not charged.

Input parameters:

- `image_urls` (array): Image URLs attached to the last user message, for the chat models that take images (input_modalities in list_models). A file generate made works.
- `max_tokens` (integer): Cap on completion tokens per model. Default 1024.
- `messages` (array): The conversation, OpenAI chat format.
- `models` (array, required): 2 to 5 chat model ids from list_models, asked at the same time.
- `prompt` (string): One user message, in place of messages.
- `system` (string): Instructions placed ahead of the conversation as a system message.
- `temperature` (number)

### `search` (~128 tokens)

Search the web

One web search through POST /v1/search: titles, URLs, snippets and publish dates, up to 10 results, optionally only from the last day, week, month or year. Billed as one search to the key in the MCP request's Authorization header (the price in GET /v1/catalog server_tools); a search that fails is not charged.

Input parameters:

- `freshness` (string): Only pages published inside this window.
- `max_results` (integer): 1 to 10 results. Default 5.
- `query` (string, required): What to search for, up to 400 characters.

### `embed` (~101 tokens)

Turn text into vectors

Embeds one text or up to 64 through POST /v1/embeddings with an embedding model id from list_models (type embedding) and returns one vector per text, in order, with the token usage and the charge. Billed to the key in the MCP request's Authorization header.

Input parameters:

- `input` (required): One text, or up to 64 texts, to embed.
- `model` (string, required): An embedding model id from list_models (type embedding).

### `rerank` (~138 tokens)

Rank documents by relevance

Orders up to 100 documents by relevance to a query through POST /v1/rerank with a rerank model id from list_models (type rerank): each result's index into documents, its score and its text, best first. Billed per input token to the key in the MCP request's Authorization header.

Input parameters:

- `documents` (array, required): Up to 100 texts to rank.
- `model` (string, required): A rerank model id from list_models (type rerank).
- `query` (string, required): What the documents are ranked against.
- `top_n` (integer): How many to return, best first. Default: all.

### `transcribe` (~224 tokens)

Transcribe audio or video

Turns the speech in an audio or video file at an https URL (25 MB at most; a file generate made works) into text through POST /v1/audio/transcriptions, or into English with translate. Use a transcription model id from list_models (type transcription). Billed per second of audio to the key in the MCP request's Authorization header; a request that fails is not charged.

Input parameters:

- `audio_url` (string, required): An https URL of the audio or video file: mp3, mp4, m4a, wav, webm, ogg, flac or aac, 25 MB at most. A file generate made works.
- `language` (string): The spoken language as an ISO-639-1 code (en, es, zh...), when known.
- `model` (string, required): A transcription model id from list_models (type transcription).
- `prompt` (string): Names or words to spell right, or the text that came before.
- `translate` (boolean): True: translate the speech into English instead (the models that can).

### `generate` (~272 tokens)

Generate an image, video, speech, music or 3D file

Runs any media model id from list_media_models with its settings (see media_model) through POST /v1/generations, waits up to wait_seconds for the files, and returns the generation: a link per file (kept 30 days), a finished image inline, and the charge. A video that is still running when the wait ends is returned as it stands; call generation with its id to keep waiting. Charged to the key in the MCP request's Authorization header when the model accepts the task; a failed generation is refunded in full. To go from an image to a video or an edit, pass the image's URL in image_urls.

Input parameters:

- `input` (object, required): The model's settings, as media_model lists them under params: prompt, size or aspect_ratio, resolution, duration, image_urls, text, voice... A setting left out takes the model's default.
- `model` (string, required): A media model id from list_media_models.
- `preview` (boolean): Default true: a finished image comes back inline as image content besides its link.
- `wait_seconds` (integer): Seconds to wait for the files before answering with the generation as it stands, 0 to 120. Images usually finish inside the default 60; a video takes minutes, so follow up with generation.

### `generation` (~155 tokens)

A generation's status and files

One generation by id: its status, progress, files and charge, waiting up to wait_seconds for it to finish first. Use it after generate answers with a video still running. Needs the key the generation was made with. Live from GET /v1/generations/{id}.

Input parameters:

- `id` (string, required): The generation id generate answered with (gen_ then 24 hex characters).
- `preview` (boolean): Default true: a finished image comes back inline as image content besides its link.
- `wait_seconds` (integer): Seconds to wait for the files before answering with the generation as it stands, 0 to 120. Images usually finish inside the default 60; a video takes minutes, so follow up with generation.

### `generations` (~132 tokens)

List the generations made on this key's organization

The organization's generations, newest first, each with its status, model, files and charge: the asset library behind generate. Filter by kind, model or status; page with before. Files are kept 30 days. Needs the key. Live from GET /v1/generations.

Input parameters:

- `before` (integer): Only generations created before this Unix time (seconds, or the ms next_before of the last page).
- `kind` (string)
- `limit` (integer): How many, newest first. Default 20.
- `model` (string): Only this media model id.
- `status` (string)

## Diagnostics

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

## Score history

- 2026-11-21: 76
- 2026-11-20: 76
- 2026-11-19: 75
- 2026-11-18: 75
- 2026-11-17: 74
- 2026-11-16: 74
- 2026-11-15: 73

## Common questions

### What is the UncensoredLLM MCP server?

UncensoredLLM is an MCP server listed in the public MCP registry as io.github.uplinkswitch/uncensoredllm. Abliterated and derestricted open-weight models on one prepaid key, prices readable without a key. This page covers its hosted endpoint (https://api.uncensoredllm.ai/mcp).

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

UncensoredLLM 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 UncensoredLLM MCP server expose?

UncensoredLLM exposes 15 tools: list_models, list_media_models, media_model, estimate, media_quote, and 10 more. Their descriptions and schemas cost roughly 2,428 tokens of context every time the server is loaded.

### Does the UncensoredLLM MCP server require authentication?

No. We connected to UncensoredLLM without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the UncensoredLLM MCP server still maintained?

UncensoredLLM is still listed as active in the MCP registry. We last reached this channel on 21 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 UncensoredLLM MCP server?

VerifyMCP ran 13 checks on UncensoredLLM, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. 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.uncensoredllm.ai/mcp
- Repository: https://github.com/uplinkswitch/uplinkswitch-mcp
- Website: https://uncensoredllm.ai/
- Changelog RSS feed: https://verifymcp.io/servers/uplinkswitch-uncensoredllm/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/uplinkswitch-uncensoredllm/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/uplinkswitch-uncensoredllm/api.json
- HTML version of this page: https://verifymcp.io/servers/uplinkswitch-uncensoredllm/api
