
PocketBase MCP Server
A comprehensive server that enables advanced database operations with PocketBase, providing tools for collection management, record operations, user management, and database administration through the Model Context Protocol.
README
Advanced PocketBase MCP Server
A comprehensive MCP server that provides sophisticated tools for interacting with PocketBase databases. This server enables advanced database operations, schema management, and data manipulation through the Model Context Protocol (MCP).
<a href="https://glama.ai/mcp/servers/z2xjuegxxh"><img width="380" height="200" src="https://glama.ai/mcp/servers/z2xjuegxxh/badge" alt="pocketbase-mcp-server MCP server" /></a>
Features
Collection Management
- Create and manage collections with custom schemas
- Migrate collection schemas with data preservation
- Advanced index management (create, delete, list)
- Schema validation and type safety
- Retrieve collection schemas and metadata
Record Operations
- CRUD operations for records
- Advanced querying with filtering, sorting, and aggregation
- Batch import/export capabilities
- Relationship expansion support
- Pagination and cursor-based navigation
User Management
- User authentication and token management
- User account creation and management
- Password management
- Role-based access control
- Session handling
Database Operations
- Database backup and restore
- Multiple export formats (JSON/CSV)
- Data migration tools
- Index optimization
- Batch operations
Available Tools
Collection Management
create_collection
: Create a new collection with custom schemaget_collection_schema
: Get schema details for a collectionmigrate_collection
: Migrate collection schema with data preservationmanage_indexes
: Create, delete, or list collection indexes
Record Operations
create_record
: Create a new record in a collectionlist_records
: List records with optional filters and paginationupdate_record
: Update an existing recorddelete_record
: Delete a recordquery_collection
: Advanced query with filtering, sorting, and aggregationimport_data
: Import data into a collection with create/update/upsert modes
User Management
authenticate_user
: Authenticate a user and get auth tokencreate_user
: Create a new user accountlist_auth_methods
: List all available authentication methodsauthenticate_with_oauth2
: Authenticate a user with OAuth2authenticate_with_otp
: Authenticate a user with one-time passwordauth_refresh
: Refresh authentication tokenrequest_verification
: Request email verificationconfirm_verification
: Confirm email verification with tokenrequest_password_reset
: Request password resetconfirm_password_reset
: Confirm password reset with tokenrequest_email_change
: Request email changeconfirm_email_change
: Confirm email change with tokenimpersonate_user
: Impersonate another user (admin only)
Database Operations
backup_database
: Create a backup of the PocketBase database with format optionsimport_data
: Import data with various modes (create/update/upsert)
Configuration
The server requires the following environment variables:
POCKETBASE_URL
: URL of your PocketBase instance (e.g., "http://127.0.0.1:8090")
Optional environment variables:
POCKETBASE_ADMIN_EMAIL
: Admin email for certain operationsPOCKETBASE_ADMIN_PASSWORD
: Admin passwordPOCKETBASE_DATA_DIR
: Custom data directory path
Usage Examples
Collection Management
// Create a new collection
await mcp.use_tool("pocketbase", "create_collection", {
name: "posts",
schema: [
{
name: "title",
type: "text",
required: true
},
{
name: "content",
type: "text",
required: true
}
]
});
// Manage indexes
await mcp.use_tool("pocketbase", "manage_indexes", {
collection: "posts",
action: "create",
index: {
name: "title_idx",
fields: ["title"],
unique: true
}
});
Advanced Querying
// Query with filtering, sorting, and aggregation
await mcp.use_tool("pocketbase", "query_collection", {
collection: "posts",
filter: "created >= '2024-01-01'",
sort: "-created",
aggregate: {
totalLikes: "sum(likes)",
avgRating: "avg(rating)"
},
expand: "author,categories"
});
Data Import/Export
// Import data with upsert mode
await mcp.use_tool("pocketbase", "import_data", {
collection: "posts",
data: [
{
title: "First Post",
content: "Hello World"
},
{
title: "Second Post",
content: "More content"
}
],
mode: "upsert"
});
// Backup database
await mcp.use_tool("pocketbase", "backup_database", {
format: "json" // or "csv"
});
Schema Migration
// Migrate collection schema
await mcp.use_tool("pocketbase", "migrate_collection", {
collection: "posts",
newSchema: [
{
name: "title",
type: "text",
required: true
},
{
name: "content",
type: "text",
required: true
},
{
name: "tags",
type: "json",
required: false
}
],
dataTransforms: {
// Optional field transformations during migration
tags: "JSON.parse(oldTags)"
}
});
Authentication Methods
// List available authentication methods
await mcp.use_tool("pocketbase", "list_auth_methods", {
collection: "users"
});
// Authenticate with password
await mcp.use_tool("pocketbase", "authenticate_user", {
email: "user@example.com",
password: "securepassword",
collection: "users"
});
// Authenticate with OAuth2
await mcp.use_tool("pocketbase", "authenticate_with_oauth2", {
provider: "google",
code: "auth_code_from_provider",
codeVerifier: "code_verifier_from_pkce",
redirectUrl: "https://your-app.com/auth/callback",
collection: "users"
});
// Request password reset
await mcp.use_tool("pocketbase", "request_password_reset", {
email: "user@example.com",
collection: "users"
});
// Confirm password reset
await mcp.use_tool("pocketbase", "confirm_password_reset", {
token: "verification_token",
password: "new_password",
passwordConfirm: "new_password",
collection: "users"
});
// Refresh authentication token
await mcp.use_tool("pocketbase", "auth_refresh", {
collection: "users"
});
Error Handling
All tools include comprehensive error handling with detailed error messages. Errors are properly typed and include:
- Invalid request errors
- Authentication errors
- Database operation errors
- Schema validation errors
- Network errors
Type Safety
The server includes TypeScript definitions for all operations, ensuring type safety when using the tools. Each tool's input schema is strictly typed and validated.
Best Practices
- Always use proper error handling with try/catch blocks
- Validate data before performing operations
- Use appropriate indexes for better query performance
- Regularly backup your database
- Use migrations for schema changes
- Follow security best practices for user management
- Monitor and optimize database performance
Development
- Clone the repository
- Install dependencies:
npm install
- Copy
.env.example
to.env
and configure - Build:
npm run build
- Start your PocketBase instance
- The MCP server will automatically connect to your PocketBase instance
Installing via Smithery
To install PocketBase Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install pocketbase-server --client claude
Contributing
- Fork the repository
- Create a feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
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.