Quriobot MCP
OfficialThis server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Quriobot MCP
Work with your Quriobot account from any AI agent: answer live chats, read responses and contacts, look into a bot's settings, anything you do in control.quriobot.com. This is an MCP server over the Quriobot API, which is what control.quriobot.com itself runs on, acting with your own API key. It runs on your machine, needs Node.js 18 or later, and has no dependencies.
Your API key
In control.quriobot.com, open Profile → API keys and create a key. It acts as you, in every
organisation you are a member of. You can delete it there at any time, and the list shows when it
was last used. Every setup below gives it to the server as QURIOBOT_API_KEY.
Related MCP server: telegram-mcp
Setup
Claude Code
The plugin asks for the key while installing and keeps it in Claude Code's credential store (the
macOS keychain, or ~/.claude/.credentials.json), not in a settings file:
/plugin marketplace add quriobot/quriobot-mcp
/plugin install quriobot@quriobotTo change the key later: /plugin configure quriobot@quriobot. From a script, without the key in
your shell history:
claude plugin marketplace add quriobot/quriobot-mcp
claude plugin install quriobot@quriobot
jq -Rn --rawfile k /path/to/key-file '{api_key: ($k | rtrimstr("\n"))}' \
| claude plugin configure quriobot@quriobot --values-stdinVS Code (GitHub Copilot)
In .vscode/mcp.json; VS Code asks for the key once and stores it securely:
{
"inputs": [{ "type": "promptString", "id": "quriobot-key", "description": "Quriobot API key", "password": true }],
"servers": {
"quriobot": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@quriobot/mcp"],
"env": { "QURIOBOT_API_KEY": "${input:quriobot-key}" }
}
}
}Claude Desktop, Cursor, Gemini CLI and other clients
They take the same entry under mcpServers: Claude Desktop in claude_desktop_config.json
(Settings → Developer → Edit Config), Cursor in ~/.cursor/mcp.json, Gemini CLI in
~/.gemini/settings.json:
{
"mcpServers": {
"quriobot": {
"command": "npx",
"args": ["-y", "@quriobot/mcp"],
"env": { "QURIOBOT_API_KEY": "your API key" }
}
}
}Codex
In ~/.codex/config.toml:
[mcp_servers.quriobot]
command = "npx"
args = ["-y", "@quriobot/mcp"]
env = { QURIOBOT_API_KEY = "your API key" }These files hold the key in plain text: keep them out of version control.
Tools
Tool | What it does |
| Searches the API's public specification by words, e.g. "chat messages" |
| The parameters, request body and responses of one endpoint |
| A GET, or a POST to a list ( |
| POST, PATCH, PUT or DELETE: sends a chat message, closes a chat, changes a bot |
Reading and writing are separate tools, so you can let the agent read freely and still approve
every change. In Claude Code, for example, in .claude/settings.json:
{
"permissions": {
"allow": ["mcp__plugin_quriobot_quriobot__find_endpoints", "mcp__plugin_quriobot_quriobot__describe_endpoint", "mcp__plugin_quriobot_quriobot__read"],
"ask": ["mcp__plugin_quriobot_quriobot__write"]
}
}Other clients ask before each tool call by default, or let you allow tools one by one.
Good to know
Almost every call needs your organisation's id. Ask the agent to find it, or copy it from control.quriobot.com: it is the part of the address after the host.
Bulk actions (closing, assigning or marking chats as spam) act on everything their filters select unless they name the chats by id. The server tells the agent this; approving writes yourself lets you check each one.
Chats and contacts contain what other people wrote. The agent is told to treat that as data, not as instructions, but approving writes yourself is the safe default.
QURIOBOT_API_URLpoints the server at another Quriobot API, such as a development stack.
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Operate WhatsApp from an agent: read conversations and contacts, send messages, by API key.
Official WhatsApp Business API (Meta Cloud API) for your own CRM or SaaS, from WasapFlow, a Meta Tech Provider. Your AI can search the Bridge docs, list connected numbers, create Embedded Signup links so clients connect their own WhatsApp (Coexistence supported), send text and template messages, list templates, check and retry failed webhooks, see usage and open support tickets. Docs tools work without a key; account tools use the x-partner-key header.
Send WhatsApp messages and templates, manage chats, contacts, broadcasts and AI agents.
Manage Chatbase agents, sources, conversations and help-desk tickets.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables interaction with SendPulse Chatbots API to manage chatbot accounts, retrieve bot information, and access dialog conversations. Supports flexible authentication through API credentials or OAuth tokens for comprehensive chatbot management through natural language.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to interact with a user's Telegram account: list chats, read history, search, and send messages through Telegram's MTProto API.2MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to control a personal Telegram account for sending/reading messages, media, group management, and more via the MTProto API.MIT
- AlicenseAqualityCmaintenanceEnables AI assistants to list and retrieve conversations, read and send messages or internal notes, and toggle conversation status through the Chatwoot API.5MIT