Skip to content

OpenClaw Agent by Nova (CIVAI)

by nova.civai.co · remote · no sign-in to list tools · v1.0.0 · published by co.civai.nova

I execute requests through OpenClaw as a personal AI agent with persistent context, browser and she…

Final · 2Changes · 2

4 tools: 2 do something that can't be undone and 2 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http openclaw-agent https://nova.civai.co/mcp/agents/openclaw-agent

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Can't be undone 2Claude Code: ask
  • converseReply conversationally when the request is ambiguous or needs clarification.No findings

    Why it is in this group

    • The description's first verb is "reply": a word for sending, and what is sent cannot be taken back.
    Description, as the server wrote it
    Reply conversationally when the request is ambiguous or needs clarification.
  • forwardSend instruction through OpenClaw bridge and return history.No findings

    Why it is in this group

    • The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
    Description, as the server wrote it
    Send instruction through OpenClaw bridge and return history.
Changes things 2Claude Code: ask
  • add-telegram-channel-using-tokenAdd Telegram channel to OpenClaw using bot token.No findings

    Why it is in this group

    • The name "add-telegram-channel-using-token" says "add": a word for a change.
    Description, as the server wrote it
    Add Telegram channel to OpenClaw using bot token.
  • telegram-pairing-approvalApprove Telegram pairing via OpenClaw shell script.No findings

    Why it is in this group

    • The description's first verb is "approve": a word for a change.
    Description, as the server wrote it
    Approve Telegram pairing via OpenClaw shell script.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http openclaw-agent https://nova.civai.co/mcp/agents/openclaw-agent

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__openclaw-agent__forward",
      "mcp__openclaw-agent__telegram-pairing-approval",
      "mcp__openclaw-agent__add-telegram-channel-using-token",
      "mcp__openclaw-agent__converse"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as openclaw-agent. Review it before you use it.