Hosting

Google-managed remote

Transport

Streamable HTTP

Endpoint

https://managedkafka.googleapis.com/mcp

Authentication

Google Cloud authentication: OAuth 2.0 using Application Default Credentials (ADC) in supported Google clients, or a client OAuth ID/secret or bearer token in compatible third-party clients. The principal needs mcp.tools.call plus the underlying product permissions; API key authentication is only available for services that explicitly support it.

Requirements

• A Google Cloud project and access to the target product/resource.
• Enable this MCP service and its underlying Google Cloud API as required by the product guide.
• An MCP client that supports Streamable HTTP.
• An identity with the MCP Tool User role (roles/mcp.toolUser) or equivalent mcp.tools.call permission, plus permissions for the underlying product operations.

Setup steps

1. Choose the correct global or regional endpoint for your data location; this catalog lists the documented endpoint.
2. In the Google Cloud project, enable the MCP service and the underlying product API if the product guide requires it.
3. Authenticate the client with Google Cloud ADC (simplest with Antigravity/Gemini CLI) or configure OAuth 2.0 credentials in a compatible client.
4. Grant the connecting identity roles/mcp.toolUser and only the product IAM roles needed for the intended operations.
5. Add managedkafka.googleapis.com to the client as a Streamable HTTP MCP server and complete sign-in.
6. Refresh the client tool list and check that the tools match the product reference; availability may depend on permissions and selected toolset.

33 tools manage Kafka clusters/topics/consumer groups/ACLs/Connect/connectors. Mutations affect production messaging; creation may take 30+ minutes and incur charges. Verify required parameters and IAM.

• create_cluster

  Create a new cluster for Google Cloud Managed service for Apache Kafka. This tool returns a long-running operation (LRO) that you can poll using the get_operation tool to track the cluster creation status. Cluster creation can take 30 minutes or longer. Important Notes: Do not create the cluster without getting all of the required parameters from the user.

  01
• update_cluster

  Update an existing Google Cloud Managed service for Apache Kafka cluster. This tool returns a long-running operation (LRO) that you can poll using the get_operation tool to track the cluster update status. Cluster updates can take 20 minutes or longer. Important Notes: When calling update_cluster, you must provide the name of the cluster to update, formatted as projects/{project}/locations/{location}/clusters/{cluster} . Do not update the cluster without getting all of the required parameters from the user. To clear a field, use the fields_to_clear parameter with a list of field masks (e.g. ["labels", "tls_config"] ).

  02
• delete_cluster

  Deletes a Google Cloud Managed Service for Apache Kafka cluster. This tool returns a long-running operation (LRO) that you can poll using the get_operation tool to track the cluster deletion status. Cluster deletions can take 10 minutes or longer.

  03
• get_cluster

  Get the details of an existing Google Cloud Managed Service for Apache Kafka cluster.

  04
• list_clusters

  Lists all clusters for Google Cloud Managed service for Apache Kafka in a given project and location.

  05
• get_operation

  Get the status of a long-running operation (LRO). Usage Some tools ( create_cluster and update_cluster ) return a long-running operation. You can use this tool to get the status of the operation. Parameters name : The name of the operation to get. It corresponds to the name field in the long-running operation. It should be in the format of projects/{project}/locations/{location}/operations/{operation} . Returns An Operation object that contains the status of the operation. If the operation is not complete, the response will be empty. If the operation is complete, the response will contain either: A response field that contains the result of the operation and indicates that it was successful. A error field that indicates any errors that occurred during the operation.

  06
• create_topic

  Create a new Google Cloud Managed Service for Apache Kafka topic.

  07
• update_topic

  Update an existing Google Cloud Managed service for Apache Kafka topic. Important Notes: The UpdateTopic request requires the name of the topic to be updated in the format projects/{project}/locations/{location}/clusters/{cluster}/topics/{topic} .

  08
• delete_topic

  Deletes a Google Cloud Managed Service for Apache Kafka topic.

  09
• get_topic

  Get the details of an existing Google Cloud Managed Service for Apache Kafka topic.

  10
• list_topics

  List all topics for Google Cloud Managed Service for Apache Kafka for a given project, location, and cluster.

  11
• update_consumer_group

  Update an existing Google Cloud Managed Service for Apache Kafka consumer group. This tool can only be used to update the offsets for topics consumed by the group. Important Notes: To update a consumer group's offsets, the consumer group must be inactive (i.e., there are no active consumers in the group), and topics with new offsets must be provided. Before making an update, the agent should call get_consumer_group to retrieve the current consumer group configuration.

  12
• delete_consumer_group

  Deletes a Google Cloud Managed Service for Apache Kafka consumer group.

  13
• get_consumer_group

  Get the details of an existing Google Cloud Managed Service for Apache Kafka consumer group.

  14
• list_consumer_groups

  List all consumer groups for Google Cloud Managed Service for Apache Kafka for a given project, location, and cluster.

  15
• get_acl

  Get the details of an existing Google Cloud Managed Service for Apache Kafka ACL.

  16
• list_acls

  List all ACLs for Google Cloud Managed Service for Apache Kafka for a given project, location, and cluster.

  17
• add_acl_entry

  Adds an ACL entry to an existing Google Cloud Managed Service for Apache Kafka ACL. If the ACL does not exist, it will be created. The following fields must be provided: * cluster (required): The cluster in which to add the ACL entry. Structured like projects/{project}/locations/{location}/clusters/{cluster} . * resource_type (required): The resource type for the ACL. Accepted values: CLUSTER, TOPIC, CONSUMER_GROUP, TRANSACTIONAL_ID. * resource_name (required): The resource name for the ACL. Can be the wildcard literal "*". * pattern_type (optional): The pattern type for the ACL. Accepted values: LITERAL, PREFIXED. If not specified, defaults to LITERAL. * principal (required): The principal. Specified as Google Cloud account, with the Kafka StandardAuthorizer prefix "User:". For example: "User:test-kafka-client@test-project.iam.gserviceaccount.com" . Can be the wildcard "User:*" to refer to all users. * operation (required): The operation type. Allowed values are (case insensitive): ALL, READ, WRITE, CREATE, DELETE, ALTER, DESCRIBE, CLUSTER_ACTION, DESCRIBE_CONFIGS, ALTER_CONFIGS, and IDEMPOTENT_WRITE. * permission_type (optional): The permission type. Accepted values are (case insensitive): ALLOW, DENY. If not specified, defaults to ALLOW. Important Notes: Certain resource types only allow certain operations. For the cluster resource type, only CREATE, CLUSTER_ACTION, DESCRIBE_CONFIGS, ALTER_CONFIGS, IDEMPOTENT_WRITE, ALTER, DESCRIBE, and ALL are allowed. For the topic resource type, only READ, WRITE, CREATE, DESCRIBE, DELETE, ALTER, DESCRIBE_CONFIGS, ALTER_CONFIGS, and ALL are allowed. For the consumerGroup resource type, only READ, DESCRIBE, DELETE, and ALL are allowed. For the transactionalId resource type only DESCRIBE, WRITE, and ALL are allowed.

  18
• remove_acl_entry

  Removes an ACL entry from an existing Google Cloud Managed service for Apache Kafka ACL. If the removed entry was the last one in the ACL, the ACL will be deleted. The following fields must be provided: * cluster (required): The cluster in which to remove the ACL entry. Structured like projects/{project}/locations/{location}/clusters/{cluster} . * resource_type (required): The resource type for the ACL. Accepted values: CLUSTER, TOPIC, CONSUMER_GROUP, TRANSACTIONAL_ID. * resource_name (required): The resource name for the ACL. Can be the wildcard literal "*". * pattern_type (optional): The pattern type for the ACL. Accepted values: LITERAL, PREFIXED. If not specified, defaults to LITERAL. * principal (required): The principal. Specified as Google Cloud account, with the Kafka StandardAuthorizer prefix "User:". For example: "User:test-kafka-client@test-project.iam.gserviceaccount.com" . Can be the wildcard "User:*" to refer to all users. * operation (required): The operation type. Allowed values are (case insensitive): ALL, READ, WRITE, CREATE, DELETE, ALTER, DESCRIBE, CLUSTER_ACTION, DESCRIBE_CONFIGS, ALTER_CONFIGS, and IDEMPOTENT_WRITE. * permission_type (optional): The permission type. Accepted values are (case insensitive): ALLOW, DENY. If not specified, defaults to ALLOW.

  19
• create_connect_cluster

  Create a new Google Cloud Managed Service for Apache Kafka Connect cluster. This tool returns a long-running operation (LRO) that you can poll using the get_operation tool to track the Connect cluster creation status. Connect cluster creation can take 20 minutes or longer. Important Notes: Do not create the connect cluster without getting all of the required parameters first.

  20
• update_connect_cluster

  Update an existing Google Cloud Managed service for Apache Kafka Connect cluster. This tool returns a long-running operation (LRO) that you can poll using the get_operation tool to track the Connect cluster update status. Connect cluster updates can take 20 minutes or longer. Important Notes: When calling update_connect_cluster, you must provide the name of the Connect cluster to update, formatted as projects/{project}/locations/{location}/connectClusters/{connect_cluster_id} . The kafka_cluster field is immutable and cannot be updated after creation. To clear a field, use the fields_to_clear parameter with a list of field masks.

  21
• delete_connect_cluster

  Deletes a Google Cloud Managed service for Apache Kafka Connect cluster. This tool returns a long-running operation (LRO) that you can poll using the get_operation tool to track the Connect cluster deletion status. Connect cluster deletions can take 10 minutes or longer.

  22
• get_connect_cluster

  Get the details of an existing Google Cloud Managed service for Apache Kafka Connect cluster.

  23
• list_connect_clusters

  List all Connect clusters for Google Cloud Managed Service for Apache Kafka Connect for a given project and location.

  24
• create_connector

  Create a new Google Cloud Managed service for Apache Kafka Connect connector. The user should first be prompted on which connector type they want to create, and then provide the necessary properties for that connector type in the configs field. Only use the example configuration for reference. The following connector types are supported: configs (required): Key-value pairs for connector properties. The available connector types are: MirrorMaker 2.0 Source connector Example Configuration: connector.class (required): "org.apache.kafka.connect.mirror.MirrorSourceConnector" name : "MM2_CONNECTOR_ID" source.cluster.alias (required): "source" target.cluster.alias (required): "target" topics (required): "TOPIC_NAME" source.cluster.bootstrap.servers (required): "SOURCE_CLUSTER_DNS" target.cluster.bootstrap.servers (required): "TARGET_CLUSTER_DNS" offset-syncs.topic.replication.factor : "1" source.cluster.security.protocol : "SASL_SSL" source.cluster.sasl.mechanism : "OAUTHBEARER" source.cluster.sasl.login.callback.handler.class : com.google.cloud.hosted.kafka.auth.GcpLoginCallbackHandler source.cluster.sasl.jaas.config : org.apache.kafka.common.security.oauthbearer.OAuthBearerLoginModule required; target.cluster.security.protocol : "SASL_SSL" target.cluster.sasl.mechanism : "OAUTHBEARER" target.cluster.sasl.login.callback.handler.class : "com.google.cloud.hosted.kafka.auth.GcpLoginCallbackHandler" target.cluster.sasl.jaas.config : "org.apache.kafka.common.security.oauthbearer.OAuthBearerLoginModule required;" Replace with these: MM2_CONNECTOR_ID : The ID or name of the MirrorMaker 2.0 Source connector. TOPIC_NAME : The name of the Kafka topic(s) to mirror. SOURCE_CLUSTER_DNS : The DNS endpoint for the source Kafka cluster. TARGET_CLUSTER_DNS : The DNS endpoint for the target Kafka cluster. MirrorMaker 2.0 Checkpoint connector Example Configuration: connector.class (required): "org.apache.kafka.connect.mirror.MirrorCheckpointConnector" name : "MM2_CONNECTOR_ID"…

  25
• update_connector

  Update an existing Google Cloud Managed Service for Apache Kafka Connect connector. The configs field can be updated. The agent can first use the get_connector method to get the current connector configuration, to provide a baseline configuration for the user to edit. Use the example configurations provided below for reference. configs: Key-value pairs for connector properties. The following connectors support configuration updates: MirrorMaker 2.0 Source connector Example Configuration: connector.class (required): "org.apache.kafka.connect.mirror.MirrorSourceConnector" name : "MM2_CONNECTOR_ID" source.cluster.alias (required): "source" target.cluster.alias (required): "target" topics (required): "TOPIC_NAME" source.cluster.bootstrap.servers (required): "SOURCE_CLUSTER_DNS" target.cluster.bootstrap.servers (required): "TARGET_CLUSTER_DNS" offset-syncs.topic.replication.factor : "1" source.cluster.security.protocol : "SASL_SSL" source.cluster.sasl.mechanism : "OAUTHBEARER" source.cluster.sasl.login.callback.handler.class : com.google.cloud.hosted.kafka.auth.GcpLoginCallbackHandler source.cluster.sasl.jaas.config : org.apache.kafka.common.security.oauthbearer.OAuthBearerLoginModule required; target.cluster.security.protocol : "SASL_SSL" target.cluster.sasl.mechanism : "OAUTHBEARER" target.cluster.sasl.login.callback.handler.class : "com.google.cloud.hosted.kafka.auth.GcpLoginCallbackHandler" target.cluster.sasl.jaas.config : "org.apache.kafka.common.security.oauthbearer.OAuthBearerLoginModule required;" Replace with these: MM2_CONNECTOR_ID : The ID or name of the MirrorMaker 2.0 Source connector. TOPIC_NAME : The name of the Kafka topic(s) to mirror. SOURCE_CLUSTER_DNS : The DNS endpoint for the source Kafka cluster. TARGET_CLUSTER_DNS : The DNS endpoint for the target Kafka cluster. MirrorMaker 2.0 Checkpoint connector Example Configuration: connector.class (required): "org.apache.kafka.connect.mirror.MirrorCheckpointConnector" name : "MM2_CONNECTOR_ID"…

  26
• delete_connector

  Deletes a Google Cloud Managed Service for Apache Kafka Connect connector.

  27
• get_connector

  Get the details of an existing Google Cloud Managed Service for Apache Kafka Connect connector.

  28
• list_connectors

  List all connectors for Google Cloud Managed Service for Apache Kafka Connect for a given project, location, and Connect cluster.

  29
• pause_connector

  Pauses a Google Cloud Managed service for Apache Kafka Connect connector and its tasks.

  30
• resume_connector

  Resumes a Google Cloud Managed service for Apache Kafka Connect connector and its tasks.

  31
• restart_connector

  Restarts a Google Cloud Managed service for Apache Kafka Connect Connector.

  32
• stop_connector

  Stops a Google Cloud Managed service for Apache Kafka Connect connector.

  33

• official server catalog

  Official Google Cloud catalog lists this product as an available remote MCP server.

• official setup guide

  Google Cloud describes remote MCP client setup, Streamable HTTP transport, supported authentication options, and ADC setup.

• official authentication guide

  Google documents supported identity types and authorization requirements for Google Cloud MCP calls.

• official source

  Official Google Cloud MCP primary documentation checked 2026-10-28.

• official source

  Official Google Cloud MCP primary documentation checked 2026-10-28.

Documentation checked 2026-10-28. Connection has not been runtime tested.