MCP Server

QuetraAI provides an MCP (Model Context Protocol) server that exposes governance tools to any MCP-compatible AI agent. Zero code required — just add a server URL to your config.

Two Connection Options

MethodSetupMulti-agentRequires Node.js
Remote (recommended)Paste one URLYesNo
Local (stdio)npx @quetra/mcpNoYes

Remote Server URL

https://mcp.quetra.dev/<your-api-key>/mcp

Replace <your-api-key> with your API key from the dashboard. The remote server supports multi-agent routing — use quetra_list_agents to discover agents.

Available Tools (9)

Governance tools evaluate, track, and report on spending. Connector tools execute authenticated actions on third-party services via Composio and Arcade.dev. Quetra governs first; connectors execute second.

ToolPurpose
quetra_list_agentsDiscover agents with budget details and rule summaries (remote only)
quetra_evaluateGovernance check — approves/rejects spending, tracks budget
quetra_check_budgetView remaining budget and limits
quetra_can_spendQuick approval check with rejection reasons
quetra_fetchx402-aware fetch for paid APIs
quetra_transactionsView transaction history
quetra_executeExecute an authenticated action via Composio or Arcade.dev (connector)
quetra_connect_serviceGet auth URL for connecting a third-party service (connector)
quetra_list_provider_toolsDiscover available tools for a service/toolkit (connector)

Platform Guides

npm Packages

  • @quetra/mcp — Local MCP server (stdio transport). npm
  • @quetra/sdk — TypeScript client library. npm

External Resources