Please use the form below to provide your feedback. Because your feedback is valuable to us, the information you submit in this form is recorded in our issue tracking system (JIRA), which is publicly available. You can track the status of your feedback using the ticket number displayed in the dialog once you submit the form.

Couchbase MCP Server for Couchbase Server

  • concept
Couchbase MCP Server lets AI agents connect to Couchbase clusters, on Capella or self-managed. It provides tools for cluster health, schema discovery, key-value operations, and query performance. Read-only mode and fine-grained tool controls keep it safe to use.

Couchbase MCP Server is a self-hosted MCP Server that allows AI agents to connect to and interact with data in Couchbase clusters. Clusters can be hosted on Capella or self-managed. It provides tools across categories including Cluster Health, Data Schema, Key-Value, Query, and Performance. Safety controls include read-only mode and fine-grained tool disabling. It supports both STDIO and Streamable HTTP transports.

The Couchbase MCP server ships as a Python Package Index (PyPI) package and via Docker. Enterprise support for Couchbase MCP Server is available by licensing Couchbase AI Data Plane. This license also entitles use and enterprise support of Couchbase Agent Memory and Couchbase Agent Catalog.

Get Started

To set up the server, see Prerequisites, then follow the Quick Start.

Tools

The server exposes several tools across multiple categories. The tools page lists which tools work on Capella and which need self-managed Couchbase Server.

See the Tools page for full details.

Category Tools

MCP Server Status and Configuration

get_server_configuration_status

Cluster Setup & Health

test_cluster_connection, get_cluster_health_and_services, get_client_connectivity_report, get_cluster_health_snapshot, get_cluster_metrics, get_cluster_tasks, get_cluster_system_events, get_cluster_query_vitals, get_index_stats, get_bucket_config

Data Model & Schema Discovery

get_buckets_in_cluster, get_scopes_in_bucket, get_collections_in_scope, get_scopes_and_collections_in_bucket, get_schema_for_collection, create_scope, create_collection, delete_scope, delete_collection

Document KV Operations

get_document_by_id, upsert_document_by_id, insert_document_by_id, replace_document_by_id, delete_document_by_id, lookup_subdocument, mutate_subdocument

Query and Index

run_sql_plus_plus_query, explain_sql_plus_plus_query, get_active_queries, delete_active_query, run_vector_query, list_indexes, get_index_advisor_recommendations, create_index, build_index, drop_index, create_query_index

Search Operations

list_search_indexes, get_search_index_definition, run_search, upsert_search_index, drop_search_index, run_vector_search

Query Performance Analysis

get_longest_running_queries, get_most_frequent_queries, get_queries_not_selective, get_queries_not_using_covering_index, get_queries_using_primary_index, get_queries_with_largest_response_sizes, get_queries_with_large_result_count

Reference Data

discover_tool_input_values

Learn More

Watch the following video for a guided tour of the server.

Video Walkthrough