
Claude Desktop
桌面端 · 免费增值 · Proprietary
Anthropic 官方推出的 Claude AI 桌面应用程序。支持 MCP 服务器以扩展功能。

datastax/astra-db-mcp
Astra DB MCP服务器是一个为大型语言模型(LLM)提供与Astra数据库交互能力的服务,扩展了LLM作为代理与外部系统交互的功能。
npx -y @datastax/astra-db-mcp{
"mcpServers": {
"astra-db-mcp": {
"command": "npx",
"args": [
"-y",
"@datastax/astra-db-mcp"
],
"env": {
"ASTRA_DB_APPLICATION_TOKEN": "<ASTRA_DB_APPLICATION_TOKEN>",
"ASTRA_DB_API_ENDPOINT": "<ASTRA_DB_API_ENDPOINT>"
}
}
}
}ASTRA_DB_APPLICATION_TOKENASTRA_DB_API_ENDPOINTOPENAI_API_KEYGetCollections
Get all collections in the active keyspace
GetCollectionInfo
Inspect collection options, vector settings, and default ID configuration
CreateCollection
Create a collection with vector options, distance metrics (cosine, euclidean, dot_product), and auto-vectorize configurations
UpdateCollection
Update or rename a collection
DeleteCollection
Delete a collection
EstimateDocumentCount
Get an approximate count of documents in a collection
GetRecord
Get a specific record by ID
CreateRecord
Insert a single document
UpdateRecord
Update a record
DeleteRecord
Delete a record by ID
FindRecord
Find records by exact field value match
FindWithFilter
Rich querying with MongoDB-style filter operators ($and, $or, $gt, $in, $exists, etc.)
FindDistinctValues
Find distinct values for a specific field in a collection
BulkCreateRecords
Insert multiple documents in batch
BulkUpdateRecords
Update multiple documents in batch
BulkDeleteRecords
Delete multiple documents in batch
FindWithVector
Dense vector similarity search with optional metadata filters, similarity scores, and projection
FindWithVectorize
Natural language search query using Astra DB Vectorize serverless embeddings
FindAndRerank
Hybrid search (lexical + dense vector / auto-vectorize) with server-side reranking scores
VectorSearch
Vector similarity search with minScore threshold and projection
HybridSearch
Combine dense vector similarity and text search with weighted scoring
CreateTable
Create a typed table with column definitions and primary keys
AlterTable
Add or drop columns (including vector columns)
DropTable
Drop a table
QueryTable
Query table rows with filters, sorting, projection, and pagination
InsertTableRow
Insert a single row or batch of rows into a table
UpdateTableRow
Update matching rows in a table
DeleteTableRow
Delete matching rows from a table
CreateTableIndex
Create a secondary index on a table column
CreateTableVectorIndex
Create a vector index on a table column with similarity metrics
CreateKeyspace
Create a new keyspace with optional automatic switching
DropKeyspace
Drop a keyspace
UseKeyspace
Switch the active working keyspace for subsequent operations
GetCurrentKeyspace
Inspect the active keyspace name
ListEmbeddingProviders
Discover supported embedding models and providers
ListRerankingProviders
Discover supported reranking models
GetDatabaseInfo
Retrieve environment metadata (ID, region, status, keyspaces)
OpenBrowser
Open a browser for authentication/setup
HelpAddToClient
Assistance with MCP client installation
本页信息摘自该项目的 README。 查看 README
该服务器 README 中提到的客户端:

supabase-community/supabase-mcp
Supabase MCP Server是一个连接Supabase项目与AI助手的工具,通过Model Context Protocol(MCP)标准化大型语言模型(LLMs)与外部服务的交互,实现数据库管理、配置获取和数据查询等功能。

googleapis/genai-toolbox
MCP Toolbox for Databases是一个开源数据库MCP服务器,专注于企业级和生产质量,简化工具开发,提供连接池、认证等复杂功能。

alexander-zuev/supabase-mcp-server
Supabase MCP服务器是一个开源工具,允许IDE安全执行SQL、管理模式变更、调用Supabase管理API和使用Auth Admin SDK,内置安全控制。

MobinX/awesome-mcp-list
这是一个持续更新的MCP服务器精选列表,涵盖了浏览器控制、艺术与文化、云平台、命令行、通信、客户数据平台、数据库、开发者工具、数据科学工具、文件系统、金融与金融科技、游戏、知识与记忆、位置服务、营销、监控、搜索和实用工具等多个类别。每个项目都附带了GitHub链接和星标数量,方便用户快速了解和使用。

stuzero/pg-mcp-server
PG-MCP是一个为PostgreSQL数据库设计的模型上下文协议服务器,提供AI代理发现、连接、查询和理解数据库的API,支持多数据库连接、丰富的目录信息和查询解释功能。

bytebase/dbhub
DBHub是一个实现模型上下文协议(MCP)的通用数据库网关,支持多种数据库连接和操作。