MCP Datastore Server
An MCP server that provides simple query capabilities for Google Cloud Datastore, allowing users to list kinds, retrieve entities, run basic queries with pagination, filter entities by equality, and count entities.
Tools
datastore_list_kinds
List all available entity kinds (tables) in the Datastore
datastore_get
Get an entity by its key
datastore_query
Execute a query on entities with optional filters
datastore_filter
Query entities with a simple equality filter on any field
datastore_count
Count entities in a kind, optionally with a filter
README
MCP Datastore Server
An MCP (Model Context Protocol) server for Google Cloud Datastore that provides simple query capabilities.
Features
- List Kinds: Get all available entity kinds (tables) in your Datastore
- Get Entity: Retrieve a specific entity by key
- Query Entities: Basic querying with pagination
- Filter Entities: Simple equality filtering on any field (including key fields)
- Count Entities: Count entities in a kind with optional filtering
Setup
- Install dependencies:
npm install
-
Set up authentication:
- Set
GOOGLE_CLOUD_PROJECTenvironment variable - Set
GOOGLE_APPLICATION_CREDENTIALSto point to your service account key file - Or use Application Default Credentials (ADC)
- Set
-
Build the project:
npm run build
- Run the server:
npm start
Available Tools
datastore_list_kinds
Lists all available entity kinds in the Datastore.
datastore_get
Gets an entity by its key.
kind: Entity kindkey: Entity key (name or ID)parent: Parent key (optional)
datastore_query
Queries entities with optional pagination.
kind: Entity kind to querylimit: Maximum results (default: 100)offset: Results to skip (default: 0)
datastore_filter
Filters entities by field equality.
kind: Entity kind to queryfield: Field name to filter on (including__key__orkey)value: Value to match exactlylimit: Maximum results (default: 100)
datastore_count
Counts entities in a kind with optional filtering.
kind: Entity kind to countfield: Field name to filter on (optional)value: Value to match exactly (required if field is provided)
Examples
// List kinds
{"name": "datastore_list_kinds", "arguments": {}}
// Get entity
{"name": "datastore_get", "arguments": {"kind": "User", "key": "12345"}}
// Query with pagination
{"name": "datastore_query", "arguments": {"kind": "User", "limit": 10}}
// Filter by field
{"name": "datastore_filter", "arguments": {"kind": "User", "field": "status", "value": "active"}}
// Filter by key
{"name": "datastore_filter", "arguments": {"kind": "User", "field": "__key__", "value": "12345"}}
// Count all entities
{"name": "datastore_count", "arguments": {"kind": "User"}}
// Count with filter
{"name": "datastore_count", "arguments": {"kind": "User", "field": "status", "value": "active"}}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.