MCP Server Couchbase
未认领Model Context Protocol server for Couchbase - connect AI agents and LLMs like Claude, Cursor, and Copilot to Couchbase/Capella
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'mcp-server-couchbase' -- 'uvx' 'couchbase-mcp-server' '--disabled-tools' 'upsert_document_by_id,' 'delete_document_by_id'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多Databases服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
33 个工具中显示 33 个
文档中列出的工具 (33)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
build_index
Trigger the build of all deferred indexes on a collection. Disabled by default when CBMCPREADONLYMODE=true.
create_collection
Create a new collection in an existing scope (Couchbase Server 7.6+ and Capella). Disabled by default when CBMCPREADONLYMODE=true.
create_index
Create a scalar (non-vector) GSI secondary index on a collection. Deferred by default — call buildindex afterward to build it. Disabled by default when CBMCPREADONLYMODE=true.
create_scope
Create a new scope in a bucket (Couchbase Server 7.6+ and Capella). Disabled by default when CBMCPREADONLYMODE=true.
delete_collection
Delete a collection and all its documents from a scope — permanent. Disabled by default when CBMCPREADONLYMODE=true.
delete_document_by_id
Delete a document by ID from a specified scope and collection. Disabled by default when CBMCPREADONLYMODE=true.
delete_scope
Delete a scope and all its collections from a bucket — permanent. Disabled by default when CBMCPREADONLYMODE=true.
drop_index
Drop a GSI index (scalar or vector) from a collection. Disabled by default when CBMCPREADONLYMODE=true.
explain_sql_plus_plus_query
Generate and evaluate an EXPLAIN plan for a SQL++ query. Returns query metadata, extracted plan, and plan evaluation findings.
get_buckets_in_cluster
Get a list of all the buckets in the cluster
get_cluster_health_and_services
Get cluster health status and list of all running services
get_collections_in_scope
Get a list of all the collections in a specified scope and bucket. Note that this tool requires the cluster to have Query service.
get_document_by_id
Get a document by ID from a specified scope and collection
get_index_advisor_recommendations
Get index recommendations from Couchbase Index Advisor for a given SQL++ query to optimize query performance
get_longest_running_queries
Get longest running queries by average service time
get_most_frequent_queries
Get most frequently executed queries
get_queries_not_selective
Get queries that are not selective (index scans return many more documents than final result)
get_queries_not_using_covering_index
Get queries that don't use a covering index
get_queries_using_primary_index
Get queries that use a primary index (potential performance concern)
get_queries_with_large_result_count
Get queries with the largest result counts
get_queries_with_largest_response_sizes
Get queries with the largest response sizes
get_schema_for_collection
Get the structure for a collection
get_scopes_and_collections_in_bucket
Get a list of all the scopes and collections in the specified bucket
get_scopes_in_bucket
Get a list of all the scopes in the specified bucket
get_server_configuration_status
Get the server status and configuration without connecting to the cluster — reports read-only mode, disabled/confirmation-required tools, OAuth settings, and the resolved logging configuration
insert_document_by_id
Insert a new document by ID (fails if document exists). Disabled by default when CBMCPREADONLYMODE=true.
list_indexes
List all indexes in the cluster with their definitions, with optional filtering by bucket, scope, collection and index name. Set returnrawindexstats=true to return the unprocessed index information.
lookup_subdocument
Look up parts of a document (specific fields, existence checks, or array/object counts) by path without fetching the whole document
mutate_subdocument
Modify parts of an existing document (upsert, insert, replace, remove, array ops, counters) by path without rewriting the whole document. Disabled by default when CBMCPREADONLYMODE=true.
replace_document_by_id
Replace an existing document by ID (fails if document doesn't exist). Disabled by default when CBMCPREADONLYMODE=true.
run_sql_plus_plus_query
Run a SQL++ query on a specified scope.<br><br>Queries are automatically scoped to the specified bucket and scope, so use collection names directly (e.g., SELECT FROM users instead of SELECT FROM bucket.scope.users).<br><br>CBMCPREADONLYMODE is true by default, which means that all write operations
test_cluster_connection
Check the cluster credentials by connecting to the cluster
upsert_document_by_id
Upsert a document by ID to a specified scope and collection. Disabled by default when CBMCPREADONLYMODE=true.