Skip to main content
Glama
mcp-debezium

mcp-debezium

mcp-debezium

CI License: MIT npm

A Model Context Protocol server for Debezium (via the Kafka Connect REST API). It lets an MCP-capable client (Claude Desktop, Claude Code, etc.) monitor and manage change-data-capture connectors — status, config, restarts, lifecycle — with behaviour controlled entirely by flags.

Safe by default: it starts read-only, can be scoped to an allowlist of connectors, protects critical connectors from mutation, redacts credentials in connector configs, and gates deletion behind an explicit opt-in.

Features

  • Monitoring — worker/cluster info, connector list, plugins, per-connector config, status (with failed-task traces), and topics.

  • Management — create/update, pause/resume, restart connector or a single task.

  • Lifecycle — delete connectors (admin).

  • Access modes — read-only → read-write → admin, layered so a mode never exposes tools above its level.

  • Credential redaction — database.password and other secret-shaped config values are replaced with ***REDACTED*** before results are returned.

  • Security flags — connector allowlist, protected connectors, delete gating, dry-run, and JSON audit logging (see below).

Related MCP server: Kafka MCP Server

Security model

Concern

Flag

Default

Effect

What can the server do?

DEBEZIUM_MODE

read-only

read-only exposes monitoring only; read-write adds lifecycle management; admin adds delete. Tools above the mode are never registered.

Which connectors are in scope?

DEBEZIUM_CONNECTOR_ALLOWLIST

(all)

When set, operations on other connectors are refused.

Which connectors are read-only forever?

DEBEZIUM_PROTECTED_CONNECTORS

(none)

Inspectable but never paused/reconfigured/deleted.

Can it delete?

DEBEZIUM_ALLOW_DELETE

false

delete_connector needs this and admin mode.

Preview without touching Connect

DEBEZIUM_DRY_RUN

false

Write/admin tools validate + log intent, then return.

Audit trail

DEBEZIUM_AUDIT_LOG

true

Emits a JSON line to stderr per guarded operation.

Interactive confirmation

(automatic)

—

Destructive & high-impact actions prompt the human to approve via MCP elicitation before running. The prompt shows the tool, the exact (secret-redacted) arguments and a fingerprint (for update_connector_config a redacted current → new config diff, for create_connector the redacted config); the target's version is pinned across the prompt and the action is refused if it changed; a prompt nobody answers is a refusal.

Require a human

DEBEZIUM_REQUIRE_HUMAN_APPROVAL

false

When true, delete_connector, create_connector and update_connector_config are refused if the client cannot elicit (instead of falling back to the *_ALLOW_* gate alone).

Credential redaction

(always on)

—

Secret-shaped config values are redacted before return.

Tools

Read (read-only+): cluster_info, list_connectors, list_connector_plugins, get_connector, get_connector_config, get_connector_status, get_connector_topics

Write (read-write+): create_connector, update_connector_config, pause_connector, resume_connector, restart_connector, restart_task

Admin (admin): delete_connector (needs DEBEZIUM_ALLOW_DELETE)

Quickstart — add to your agent

Published on npm as @dockndevai/mcp-debezium. No clone or build needed — your MCP client runs it on demand with npx. Start in read-only mode; see .env.example for every variable and docs/CLIENTS.md for the full per-client guide.

Claude Code (CLI)

claude mcp add debezium -e CONNECT_URL="http://localhost:8083" -e DEBEZIUM_MODE="read-only" -- npx -y @dockndevai/mcp-debezium

Claude Desktop · Cursor · Windsurf — same block in claude_desktop_config.json, .cursor/mcp.json, or ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "debezium": {
      "command": "npx",
      "args": [
        "-y",
        "@dockndevai/mcp-debezium"
      ],
      "env": {
        "CONNECT_URL": "http://localhost:8083",
        "DEBEZIUM_MODE": "read-only"
      }
    }
  }
}

OpenAI Codex CLI — in ~/.codex/config.toml:

[mcp_servers.debezium]
command = "npx"
args = ["-y", "@dockndevai/mcp-debezium"]
env = { CONNECT_URL = "http://localhost:8083", DEBEZIUM_MODE = "read-only" }

VS Code (GitHub Copilot, Agent mode) — in .vscode/mcp.json:

{
  "servers": {
    "debezium": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@dockndevai/mcp-debezium"
      ],
      "env": {
        "CONNECT_URL": "http://localhost:8083",
        "DEBEZIUM_MODE": "read-only"
      }
    }
  }
}

Example prompts

  • "Which connectors are FAILED, and why?"

  • "Restart the failed task on pg-orders." (needs read-write)

  • "Show the config for mysql-inventory." (credentials come back redacted)

Run from source (development)

Prefer the published package above. To run from a clone:

npm install
npm run build
node dist/index.js   # with the environment variables set

Develop

npm run dev
npm test          # security policy + config redaction
npm run typecheck

Publishing

This server ships a server.json for the official MCP registry and an mcpName for npm ownership validation. See PUBLISHING.md for publishing to npm and listing on the MCP registry, Smithery, Glama, Cursor, and PulseMCP.

License

MIT

Available Tools

7 tools
cluster_infoConnect cluster infoA
Read-onlyIdempotent

Kafka Connect worker version, commit, and Kafka cluster id.

Inputs: no named parameters.

get_connectorGet connectorA
Read-onlyIdempotent

Full connector info (config + tasks). Secret config values are redacted.

Inputs: name (required).

get_connector_configGet connector configA
Read-onlyIdempotent

The connector's configuration map. Secret values are redacted.

Inputs: name (required).

get_connector_statusGet connector statusB
Read-onlyIdempotent

Connector and task states (RUNNING / PAUSED / FAILED), worker assignment, and failure traces.

Inputs: name (required).

get_connector_topicsGet connector topicsB
Read-onlyIdempotent

The set of topics a connector has read from or written to.

Inputs: name (required).

list_connector_pluginsList connector pluginsA
Read-onlyIdempotent

List the connector plugin classes installed on the worker (incl. Debezium connectors).

Inputs: no named parameters.

list_connectorsList connectorsA
Read-onlyIdempotent

List connector names. Connectors outside the allowlist are filtered out.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 7 tools

    Disambiguation4/5

    Most tools target distinct aspects of Kafka Connect/Debezium introspection. get_connector overlaps somewhat with get_connector_config and get_connector_status because it returns full connector info including config and tasks, but the descriptions clarify the specialized scopes.

    Naming Consistency4/5

    The naming is mostly consistent snake_case with clear verb_noun patterns such as get_connector_config and list_connectors. cluster_info is a minor deviation because it lacks a verb, but it remains readable and predictable.

    Tool Count5/5

    Seven tools is well-scoped for a connector introspection server. Each tool covers a distinct read-only concern, from connector lists and configs to status, topics, plugins, and cluster info.

    Completeness4/5

    The read-only introspection surface is largely complete: connectors, config, status, topics, plugins, and cluster details are covered. Mutation or lifecycle operations like create, update, restart, pause, and delete are absent, but they may be outside this server's apparent monitoring scope.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to manage and monitor Apache Kafka clusters through natural language, providing real-time operations, health monitoring, consumer lag analysis, and temporal trend detection for intelligent cluster management.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables interaction with Kafka clusters via MCP, supporting topic management (list, create, delete, inspect), connection initialization, and more through natural language.
      1
      Apache 2.0
    • F
      license
      C
      quality
      D
      maintenance
      Exposes Kafka administration operations as MCP tools, enabling AI agents to inspect Kafka clusters using natural language.
      1
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI-powered MCP clients to interact with data lakehouse components including Kafka, Flink, and Trino/Iceberg for managing topics, jobs, catalogs, and executing queries.
      2
      -