OpenClaw Agent by Nova (CIVAI)
Server Details
I execute requests through OpenClaw as a personal AI agent with persistent context, browser and she…
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
The four tools have mostly distinct purposes: add-telegram-channel-using-token and telegram-pairing-approval both concern Telegram setup but are clearly different actions, while converse and forward serve different interaction modes. An agent might occasionally hesitate between converse and forward, but the descriptions provide enough guidance to avoid major misselection.
Naming follows mixed conventions: add-telegram-channel-using-token is a long kebab-case action phrase, converse and forward are bare verbs, and telegram-pairing-approval is a noun phrase. The names are readable but do not follow a predictable pattern.
Four tools is a reasonable, focused set for a narrow OpenClaw/Telegram bridge server, and each tool appears to earn its place. The count is slightly thin for broader agent management but appropriate for the apparent scope.
The surface covers adding a Telegram channel, approving pairing, forwarding instructions, and conversational fallback, but lacks lifecycle operations like listing or removing channels, revoking pairing, or broader OpenClaw management. These are notable gaps that an agent may need to work around.
Available Tools
4 toolsadd-telegram-channel-using-tokenCInspect
Add Telegram channel to OpenClaw using bot token.
Inputs: token.
converseCInspect
Reply conversationally when the request is ambiguous or needs clarification.
Inputs: reply_hint.
forwardCInspect
Send instruction through OpenClaw bridge and return history.
Inputs: instruction (required).
telegram-pairing-approvalCInspect
Approve Telegram pairing via OpenClaw shell script.
Inputs: pairing_id, telegram_user_id.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Your own AI agent on an always-on cloud computer: Claude Code, Codex and more, or managed OpenClaw.
Deploy, monitor, and manage your OpenClaw AI assistants via natural language.
A personal agent with lasting memory and a morning brief, inside the Claude or ChatGPT you use.
Autonomous cloud agent tasks: real browser + your tools, structured evidence-backed results.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceLets AI agents drive a real browser through shell-style text commands like cd, ls, cat, click and type, returning compact plain-text output (merged lists, outlines, and only newly appeared text after actions) to use a fraction of the tokens of snapshot- or screenshot-based tools. It can operate the user's own Chrome with existing logins, while refusing payments, passwords and sensitive file locations.MIT
- AlicenseCqualityBmaintenanceEnables AI assistants to execute commands an1559 PyPIMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to automate a real Chromium browser through the unchanged upstream Playwright MCP tool surface, covering navigation, research, testing, and daily web workflows in plain language. It ships via npm or Docker over stdio or Streamable HTTP, and supports persistent login profiles, Chrome extension loading, proxy/GeoIP matching, and humanized mouse, keyboard, and scroll behavior.297 npmMIT
- AlicenseNot gradedqualityDmaintenanceAutomate your real Chrome browser locally with AI, supporting vision, human-like input, code execution, macros, and watchdogs.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.