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.
Creates a working text-moderation API key with no account: 100 messages over 72 hours, standard mode, every category on. Returns api_key and claim_url; opening claim_url keeps the key in a Paxmod account. Limited to 3 keys per address per day.
Optional project name, for example the game's name.
Optional: the agent or tool asking, for example claude-code.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http paxmod https://www.paxmod.com/mcp
Creates a working text-moderation API key with no account: 100 messages over 72 hours, standard mode, every category on. Returns api_key and claim_url; opening claim_url keeps the key in a Paxmod account. Limited to 3 keys per address per day.
| Argument | Type | Description |
|---|---|---|
| name | string | Optional project name, for example the game's name. |
| source | string | Optional: the agent or tool asking, for example claude-code. |
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Optional project name, for example the game's name."
},
"source": {
"type": "string",
"description": "Optional: the agent or tool asking, for example claude-code."
}
}
}The full Paxmod API guide for coding agents: endpoints, request and response shapes, error codes, rate limits and code samples (Node, Python, Unity, Roblox and more).
No arguments.
{
"type": "object",
"properties": {}
}Checks one chat message with Paxmod, using the project's categories and thresholds. Returns flagged or not_flagged with a score per category. Counts as one of the project's messages, like a live request. Needs a Paxmod API key (create_test_api_key gives one).
| Argument | Type | Description |
|---|---|---|
| api_key* | string | Paxmod API key for the project. |
| message* | string | The message to check, up to 5000 characters. |
| user_id | string | Optional: the player who sent it. |
| context_id | string | Optional: the chat, channel or match it was sent in. |
{
"type": "object",
"required": [
"api_key",
"message"
],
"properties": {
"api_key": {
"type": "string",
"description": "Paxmod API key for the project."
},
"message": {
"type": "string",
"description": "The message to check, up to 5000 characters."
},
"user_id": {
"type": "string",
"description": "Optional: the player who sent it."
},
"context_id": {
"type": "string",
"description": "Optional: the chat, channel or match it was sent in."
}
}
}Runs example messages against an Advanced mode policy and says which would be flagged, with a score and reason for each. Send a draft policy to try changes before saving them; leave it out to test the saved policy. Mark each example with expect "flag" or "pass" and the summary counts how many came back as expected. The project's word rules run first, as they do live. Nothing is stored. No credits are used, except on a free test key from create_test_api_key, where each message checked counts toward its 100 free messages. Up to 50 examples per call.
| Argument | Type | Description |
|---|---|---|
| policy | string | Draft policy in plain English, up to 1,000 characters. Leave out to test the saved policy. |
| api_key* | string | Paxmod API key for the project. |
| examples* | array | Messages to test, up to 50. |
| threshold | number | Flag above this score, 0 to 1. Leave out to use the project's setting. |
{
"type": "object",
"required": [
"api_key",
"examples"
],
"properties": {
"policy": {
"type": "string",
"description": "Draft policy in plain English, up to 1,000 characters. Leave out to test the saved policy."
},
"api_key": {
"type": "string",
"description": "Paxmod API key for the project."
},
"examples": {
"type": "array",
"items": {
"type": "object",
"required": [
"message"
],
"properties": {
"expect": {
"enum": [
"flag",
"pass"
],
"type": "string",
"description": "What the policy should do with it."
},
"message": {
"type": "string",
"description": "A chat message."
}
}
},
"maxItems": 50,
"description": "Messages to test, up to 50."
},
"threshold": {
"type": "number",
"description": "Flag above this score, 0 to 1. Leave out to use the project's setting."
}
}
}Shows what a project's word rules do to each message: block (flag without checking), bypass (pass without checking), or scan with the text rewritten by remove and replace rules. Send draft rules to try changes before saving them. No model call, nothing stored, no credits used.
| Argument | Type | Description |
|---|---|---|
| api_key* | string | Paxmod API key for the project. |
| messages* | array | Messages to test, up to 50. |
| word_rules | array | Draft rules. Leave out to test the saved ones. Whole words, case insensitive. |
{
"type": "object",
"required": [
"api_key",
"messages"
],
"properties": {
"api_key": {
"type": "string",
"description": "Paxmod API key for the project."
},
"messages": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 50,
"description": "Messages to test, up to 50."
},
"word_rules": {
"type": "array",
"items": {
"type": "object",
"required": [
"term",
"mode"
],
"properties": {
"mode": {
"enum": [
"bypass",
"remove",
"substitute",
"block"
],
"type": "string"
},
"term": {
"type": "string"
},
"replacement": {
"type": "string",
"description": "Only for substitute."
}
}
},
"description": "Draft rules. Leave out to test the saved ones. Whole words, case insensitive."
}
}
}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 8, 2026.
Takes a password, API key or token as an argument, so the secret passes through the model's context and chat logs.
Fix: Read credentials from the server's own configuration (environment, OAuth) instead of a tool argument.
What changed in this server's tools since we started watching, newest first. Each change is scanned again.