Paxmod

com.paxmod由 paxmod.com 發布官方發布者v1.0.1更新於 Nov 8, 2026

Content moderation for chat and comments: free test keys, message checks, plain-English policies.

已驗證Streamable HTTP可網頁執行開發者工具安全與監控資料與分析

概覽

AI 產生的概覽

Paxmod 託管 MCP 伺服器，讓助理為聊天與留言接入並調校內容審核、檢查訊息、檢視被標記內容。

可以做什麼
  • 讀取 API 指南並建立免註冊的測試金鑰以供接入
  • 依專案分類與門檻檢查單一訊息，並提供各分類分數
  • 以範例訊息測試草稿或已儲存的進階模式政策與字詞規則，回報哪些結果符合預期
  • 列出專案並讀取專案的審核設定
  • 檢視用量統計與最近的被標記訊息，包含單一玩家的歷史紀錄
適用情境
適合為有玩家聊天或留言的應用程式、遊戲或社群加入審核功能，或依誤判、漏判的範例訊息調校現有政策。也適合檢視最近的被標記訊息與用量。
執行需求
遠端 Streamable HTTP 端點，無需安裝。指南與測試金鑰工具無需登入；訊息檢查與政策測試需要 Paxmod API 金鑰，可用 create_test_api_key 產生的測試金鑰，或專案設定中的金鑰。需登入的專案工具首次使用時會要求使用者登入 Paxmod。
安裝前請注意
create_test_api_key 無需帳號即可簽發可用金鑰並回傳認領連結；測試金鑰上每檢查一則訊息都會計入其 100 則、72 小時額度。moderate_text 會視為實際訊息計入專案用量。被標記訊息與玩家歷史工具會回傳真實玩家聊天內容與玩家 ID，應視為敏感資料。在付費專案上，政策與字詞規則測試不儲存內容、不消耗額度。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Paxmod，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/com.paxmod%2Fpaxmod/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "paxmod": {
      "type": "http",
      "url": "https://www.paxmod.com/mcp"
    }
  }
}

README

Paxmod MCP Server

Connect your AI agent to Paxmod, content moderation for any app where people post or chat: in-app chat, comments, forums, communities, marketplaces and games. It catches profanity, harassment, grooming risk, personal information and spam, plus anything else you describe in a plain-English policy.

This is a hosted (remote) Model Context Protocol server. There is nothing to install:

https://www.paxmod.com/mcp

What your agent can do

  • Add moderation to your app. "Add Paxmod moderation to our app's chat." The agent reads the API guide, creates a test key with no signup, builds the integration and checks it with real messages, then gives you a link to keep the key.
  • Tune your policy from examples. "These 6 messages were flagged but are fine, and these 2 got through. Fix the policy." Advanced mode moderates against a policy you write in plain English. The agent rewrites it and tests each draft against your examples until every one comes back right. Tests store nothing and use no credits on your project (on a free test key, each message checked counts toward its 100).
  • Check messages. "Would this get flagged?" with a score per category.

Tools

ToolWhat it doesNeeds
get_integration_guideThe full API guide: endpoints, responses, errors, rate limits, code for Node, Python, Unity, Roblox and moreNothing
create_test_api_keyA working key with no signup: 100 text messages over 72 hours, plus a claim link to keep itNothing
moderate_textChecks one message with the project's settingsAPI key
test_policyRuns up to 50 examples against a draft or saved policy and reports which come back as expectedAPI key
test_word_rulesShows what word rules (allow, rewrite or block words) do to each message, with no model callAPI key

get_integration_guide, test_policy and test_word_rules are read-only.

Setup

Claude Code

bash
claude mcp add --transport http paxmod https://www.paxmod.com/mcp

Claude and Claude Desktop

Open Settings → Connectors → Add custom connector and enter https://www.paxmod.com/mcp.

Cursor

.cursor/mcp.json in your project, or ~/.cursor/mcp.json for every project:

json
{  "mcpServers": {    "paxmod": { "url": "https://www.paxmod.com/mcp" }  }}

VS Code

.vscode/mcp.json:

json
{  "servers": {    "paxmod": { "type": "http", "url": "https://www.paxmod.com/mcp" }  }}

Other clients

Add a remote MCP server with the URL https://www.paxmod.com/mcp and the Streamable HTTP transport.

Keys

There is no sign-in. Tools that work on a project take its API key, from your project's Settings in the Paxmod console, or a test key from create_test_api_key.

Links

來源：README.md，提交 c5c1a80

工具

11

get_integration_guide

Get the Paxmod integration guide

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).

無需輸入參數。

create_test_api_key

Create a Paxmod test API key

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.

輸入參數namesource

moderate_text

Moderate a message

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).

輸入參數api_key必填message必填user_idcontext_id

test_policy

Test a moderation policy

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.

輸入參數policyapi_key必填examples必填threshold

test_word_rules

Test word rules

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.

輸入參數api_key必填messages必填word_rules

list_projects

List my Paxmod projects

Lists the signed-in user's Paxmod projects: their own and those in organizations they belong to, with each project's id, name, type (text or image), mode (standard or advanced), organization and the user's role. API keys are not included.

無需輸入參數。

get_project_settings

Get project settings

Returns a project's moderation settings: type, mode, categories and thresholds, the Advanced mode policy, and word rules. The API key is not included.

輸入參數project_id必填

get_usage

Get project usage

Returns how many messages a project has sent per day over the last 30 days (up to 90), plus the total for the current calendar month. Counts are updated through the day.

輸入參數daysproject_id必填

test_policy_on_project

Test a policy on my project

Runs example messages against one of the user's Advanced mode projects, with a draft policy or the saved one, and says which would be flagged, with a score and reason for each. 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 and no credits are used. Up to 50 examples per call.

輸入參數policyexamples必填thresholdproject_id必填

list_flagged_messages

List flagged messages

Lists a project's most recent flagged messages, newest first, with the reason, confidence, player id, context id and any reviewer verdict (TP or FP). Filter by date, category or player. Up to 50 per call. Not available for organizations that keep player data in a separate region unless Paxmod has enabled it.

輸入參數limitsinceuser_idcategoryproject_id必填

get_player_history

Get a player's flag history

Returns one player's flagged messages in a project, newest first (up to 50), with a count by reason. Use the player id the game or app sends as user_id. Not available for organizations that keep player data in a separate region unless Paxmod has enabled it.

輸入參數limituser_id必填project_id必填

版本歷史

1
  1. v1.0.1最新Nov 8, 2026

評分

已滿足適用檢查項的 90%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。