Cekura

About

Cekura is an MCP connector that gives the Sazabi agent tools to test, monitor, and evaluate AI agent workflows. Cekura's MCP server accepts API key authentication via HTTP headers. Sazabi stores your key securely and sends it as the X-CEKURA-API-KEY header to Cekura's MCP endpoint. Once connected, the agent can run evaluations, check workflow health, and surface issues in your AI pipelines.

What the agent can do:

• Run evaluations and test suites against AI agent workflows
• Monitor workflow health and surface failures
• Retrieve evaluation results and historical run data
• Trigger on-demand checks on specific workflow configurations
• Browse workflow definitions and test case libraries

Prerequisites

• A Cekura account
• A Cekura API key from Settings > API Keys in the Cekura dashboard

Set up in the dashboard

Configure connectors in the dashboard under Settings > MCP connectors.

Set up with the CLI

Cekura authenticates with a Cekura API key, and sazabi mcp-connectors connect only supports OAuth providers — so set up this connector in the dashboard first (above). Once it's connected, the Sazabi CLI can inspect and manage it (installed and authenticated — see sazabi mcp-connectors reference):

sazabi mcp-connectors list
sazabi mcp-connectors details <connection-id>

Find the connection ID with sazabi mcp-connectors list. To rotate the stored credentials later, use sazabi mcp-connectors update-credentials <connection-id>.

Verify

Open the connector's connection page under Settings > MCP connectors and confirm Sazabi lists the tools it discovered. Then, in a thread, ask the agent to use one of those tools and confirm it runs. If no tools appear, confirm the key is correct.

Troubleshooting

No tools discovered — Check that the API key is valid and was copied correctly from the Cekura dashboard.

Connection shows needs attention — The key may have expired or been revoked; reconnect from Settings > MCP connectors.

Further reading