com.openuncensored/open-uncensoredv1.1.0 Domain verified
Open-weight and abliterated LLMs on one API: compare models and rankings, chat, check credits.
Maintain this server? Claim it
Try it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
buy_credits
Start a credit purchase for your human: returns a Stripe payment_url to show them, plus session_id and claim_token for check_purchase. Omit api_key for a new key; pass it to top up.
Existing key to top up (optional).
US cents, 500 to 100000. Default 1000 ($10).
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Install
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http open-uncensored https://openuncensored.com/mcp/connect
Tools (9)
buy_creditsStart a credit purchase for your human: returns a Stripe payment_url to show them, plus session_id and claim_token for check_purchase. Omit api_key for a new key; pass it to top up.
buy_credits
Start a credit purchase for your human: returns a Stripe payment_url to show them, plus session_id and claim_token for check_purchase. Omit api_key for a new key; pass it to top up.
| Argument | Type | Description |
|---|---|---|
| api_key | string | Existing key to top up (optional). |
| credits_cents | integer | US cents, 500 to 100000. Default 1000 ($10). |
Input schema (JSON)
{
"type": "object",
"properties": {
"api_key": {
"type": "string",
"description": "Existing key to top up (optional)."
},
"credits_cents": {
"type": "integer",
"maximum": 100000,
"minimum": 500,
"description": "US cents, 500 to 100000. Default 1000 ($10)."
}
}
}chatSend one message to a model on Open Uncensored and return its reply, the model and provider that answered, and the cost in USD charged to the account.
chat
Send one message to a model on Open Uncensored and return its reply, the model and provider that answered, and the cost in USD charged to the account.
| Argument | Type | Description |
|---|---|---|
| model* | string | Model id from list_models, e.g. glm-5.3-flash-uncensored |
| system | string | Optional system prompt. |
| api_key | string | Defaults to the key in the MCP config. |
| message* | string | The user message to send. |
| max_tokens | integer | Reply length cap. Default 2048. |
Input schema (JSON)
{
"type": "object",
"required": [
"model",
"message"
],
"properties": {
"model": {
"type": "string",
"description": "Model id from list_models, e.g. glm-5.3-flash-uncensored"
},
"system": {
"type": "string",
"description": "Optional system prompt."
},
"api_key": {
"type": "string",
"description": "Defaults to the key in the MCP config."
},
"message": {
"type": "string",
"description": "The user message to send."
},
"max_tokens": {
"type": "integer",
"maximum": 32000,
"minimum": 1,
"description": "Reply length cap. Default 2048."
}
}
}check_balanceRemaining prepaid credit on the Open Uncensored account, in USD.
read-only
check_balance
Remaining prepaid credit on the Open Uncensored account, in USD.
| Argument | Type | Description |
|---|---|---|
| api_key | string | Defaults to the key in the MCP config. |
Input schema (JSON)
{
"type": "object",
"properties": {
"api_key": {
"type": "string",
"description": "Defaults to the key in the MCP config."
}
}
}check_purchasePoll a purchase from buy_credits. When paid, returns the new api_key exactly once.
read-only
check_purchase
Poll a purchase from buy_credits. When paid, returns the new api_key exactly once.
| Argument | Type | Description |
|---|---|---|
| session_id* | string | |
| claim_token* | string |
Input schema (JSON)
{
"type": "object",
"required": [
"session_id",
"claim_token"
],
"properties": {
"session_id": {
"type": "string"
},
"claim_token": {
"type": "string"
}
}
}get_guideThe full guide to Open Uncensored for agents: buying a key, calling the API, errors, pricing.
read-only
get_guide
The full guide to Open Uncensored for agents: buying a key, calling the API, errors, pricing.
No arguments.
Input schema (JSON)
{
"type": "object",
"properties": {}
}get_modelDetails for one model id: price, context length, providers, score breakdown and an example API call.
read-only
get_model
Details for one model id: price, context length, providers, score breakdown and an example API call.
| Argument | Type | Description |
|---|---|---|
| id* | string | Model id from list_models, e.g. glm-5.3-flash-uncensored |
Input schema (JSON)
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "Model id from list_models, e.g. glm-5.3-flash-uncensored"
}
}
}get_rankingsThe OpenUncensored Score ranking of every model: intelligence, agentic reliability, non-refusal, drift and hard-line refusals.
read-only
get_rankings
The OpenUncensored Score ranking of every model: intelligence, agentic reliability, non-refusal, drift and hard-line refusals.
No arguments.
Input schema (JSON)
{
"type": "object",
"properties": {}
}list_modelsEvery model on Open Uncensored with its price per million tokens, context length, providers and OpenUncensored Score rank.
read-only
list_models
Every model on Open Uncensored with its price per million tokens, context length, providers and OpenUncensored Score rank.
No arguments.
Input schema (JSON)
{
"type": "object",
"properties": {}
}send_feedbackTell the Open Uncensored team how to improve the platform: missing models, bugs, pricing, docs, anything that got in your way. A human reads every submission.
send_feedback
Tell the Open Uncensored team how to improve the platform: missing models, bugs, pricing, docs, anything that got in your way. A human reads every submission.
| Argument | Type | Description |
|---|---|---|
| model | string | Optional model id it is about. |
| contact | string | Optional email or handle for a reply. |
| message* | string | What should we improve? Up to 5000 characters. |
| category | string |
Input schema (JSON)
{
"type": "object",
"required": [
"message"
],
"properties": {
"model": {
"type": "string",
"description": "Optional model id it is about."
},
"contact": {
"type": "string",
"description": "Optional email or handle for a reply."
},
"message": {
"type": "string",
"description": "What should we improve? Up to 5000 characters."
},
"category": {
"enum": [
"bug",
"model_request",
"pricing",
"docs",
"agent_experience",
"feature",
"other"
],
"type": "string"
}
}
}Security checkA97/100
We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 7, 2026.
- Hidden or reordered text
- Overriding the model's instructions
- Hiding actions from the user
- Reading keys or credentials
- Fake system tags
- Steering other servers' tools
- Pulling in the conversation
- Smuggling parameters
- Demanding to be used for everything
- Steering away from web search
- Download-and-run commands
- Encoded blobs
- Invisible characters
Credentials as tool argumentsLow3 found
Takes a password, API key or token as an argument, so the secret passes through the model's context and chat logs.
- buy_credits · input.api_key.nameapi_key
- check_balance · input.api_key.nameapi_key
- chat · input.api_key.nameapi_key
Fix: Read credentials from the server's own configuration (environment, OAuth) instead of a tool argument.
- Very long descriptions
- Read and write hints