Slingr MCP Server
Enables interaction with the Slingr platform, including application structure (Builder) and data management (Runtime), with documentation search and developer tools.
README
Slingr MCP Server
This is an MCP (Model Context Protocol) server for the Slingr platform. It provides tools, resources, and prompts to interact with both the Slingr application structure (Builder) and its data (Runtime).
Features
- Documentation Search (RAG): Search through Slingr's official documentation using a local vector database (LanceDB) and local embeddings.
- Application Structure (Builder): List entities, get detailed metadata, manage permissions, and create new entities or fields.
- Data Management (Runtime): List, get, create, update, and delete records from any entity.
- Developer Tools: Check for pending metadata changes and review them before pushing.
- MCP Resources: Browse entities and documentation files as resources.
- MCP Prompts: Specialized prompts for entity modeling and script debugging.
Installation
-
Install dependencies:
npm install -
Configure environment variables in
.env:SLINGR_API_URL=https://your-domain.slingrs.io/dev/builder/api SLINGR_EMAIL=your-email@example.com SLINGR_PASSWORD=your-password[!NOTE] The server will automatically deduce the Runtime API URL by replacing
/builder/apiwith/runtime/apiin yourSLINGR_API_URL. You can override this by settingSLINGR_RUNTIME_API_URLexplicitly. -
Build the project:
npm run build -
Ingest documentation (first time or when updated):
# Using the standalone script npx tsx scripts/ingest-docs.ts
Usage
In Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"slingr": {
"command": "node",
"args": ["/path/to/slingr-mcp/build/index.js"],
"env": {
"SLINGR_API_URL": "https://your-domain.slingrs.io/dev/builder/api",
"SLINGR_EMAIL": "your-email@example.com",
"SLINGR_PASSWORD": "your-password"
}
}
}
}
Tools
Application structure (Builder)
check_connection: Verifies the API connection.list_entities: Lists all entities.get_entity: Gets detailed entity metadata (useverbose: truefor full details).create_entity: Creates a new entity.create_field: Adds a field to an entity.list_groups: Lists security groups (roles).get_entity_permissions: Gets permissions for an entity (simplified output).update_entity_permissions: Updates permissions for a group.check_pending_changes: Checks for development changes.get_pending_changes: Lists changes ready to be pushed.
Data Management (Runtime)
list_records: Fetches records from an entity.get_record: Fetches a specific record. Supportsfieldsparameter for partial fetching.create_record: Creates a new record.update_record: Updates a record.delete_record: Deletes a record.
Other
search_documentation: Searches the documentation.ingest_documentation: Updates the vector database.
Resources
slingr://entities: Full list of entities in JSON format.slingr://docs/{path}: Access any documentation file as a resource.
Prompts
create_entity_with_fields: Guide to modeling a new entity.debug_slingr_script: Help for debugging scripts using documentation context.
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.