Skip to main content
Alginte ships a built-in Model Context Protocol server: AI agents (Claude Code, Claude Desktop, and any other MCP client) can inspect your Kafka cluster through the same service layer the UI uses — list and describe topics, read consumer-group lag, check connectors and schemas, and sample messages.
Available from 0.6.0. The MCP tool set is read-only and included in the free Community edition. Nothing on the MCP surface can create, delete, or modify anything.

​
Endpoint

The server speaks Streamable HTTP at /mcp on the regular application port — same process, same port, same network reachability as the UI:
There is nothing to enable — it is on by default. To switch the whole surface off:

​
Connecting a client

​
Claude Code

​
Claude Desktop

Settings → Connectors → Add custom connector, with the same URL.

​
With authentication enabled

If the optional login is on, /mcp requires the same credentials over HTTP Basic — MCP clients send them as a header:
With an OIDC-only login there is no header credential an MCP client can send. To use MCP on an OIDC-protected instance, also configure the username/password login — or keep the instance inside its network boundary with the login off.

​
Tools

All tools are read-only (readOnlyHint) and honor the same settings as the REST API — for example, sensitive config values stay masked unless the operator enabled ALGINTE_SHOWSENSITIVECONFIG. The Connect and Schema Registry tools need their upstream URLs configured, exactly like the corresponding UI areas.

​
Sampling messages

consume_messages fetches up to 500 messages (default 20) without joining a consumer group or committing anything — it never affects your applications. The seekType argument picks the window: Newest (default), Oldest, OffsetGE / OffsetLE (from an offset), After / Before (from a timestamp). Key and value deserializers default to String; JSON, numeric types, Bytes, and the Schema-Registry-backed JSONSchema / Avro / Protobuf are available.

​
Security notes

The MCP endpoint binds like every other route — it is inside the same deployment boundary as the UI, and the login (when enabled) covers it. One consideration specific to agents: content an agent reads from Kafka (message payloads, connector configs, schema documents) is untrusted input to that agent’s context. The read-only tool design bounds the blast radius — there is nothing destructive an injected instruction could call — but review your MCP client’s own confirmation settings before pointing agents at sensitive clusters.