Qyra exposes a Model Context Protocol server that AI assistants (Claude, ChatGPT, Codex, Cursor, Claude Code, and any other MCP client) connect to for querying the semantic layer. Enabling it on a self-hosted instance is a one-flag change.

Prerequisites

• Enterprise license — QYRA_LICENSE_KEY must be set on your instance.
• HTTPS — MCP clients connect over HTTPS. See secure Qyra with HTTPS if your instance is HTTP-only.

Enable MCP

Set the following environment variable on your Qyra deployment:

MCP_ENABLED=true

The OAuth server is built into Qyra, so no external OAuth configuration is needed — the authentication flow works the same way as it does on Qyra Cloud.

Optional configuration

Set MCP_RUN_SQL_MAX_LIMIT to override the default row cap for the run_sql tool, tuned independently of AI Analyst. For example:

MCP_RUN_SQL_MAX_LIMIT=5000

Requests that ask for more rows are clamped to this limit.

MCP URL format

Once enabled, the MCP endpoint is available at:

https://<your-qyra-host>/api/v1/mcp

Replace <your-qyra-host> with your instance's domain (e.g. qyra.yourcompany.com).

Connect an AI assistant

Follow the same steps as Qyra Cloud, using your self-hosted URL instead of a .qyraflow.com address. See the Qyra MCP installation guide for detailed instructions per AI assistant.

For example, with Claude Code:

claude mcp add qyra https://<your-qyra-host>/api/v1/mcp -t http

Network requirements

If your Qyra instance sits behind a firewall or VPN, ensure the MCP client can reach it over HTTPS. See the MCP network requirements for additional domains that may need allow-listing depending on the AI assistant.

Troubleshooting