Codehooks.io MCP Server (under construction 🚧)

The agent can then runcohocommands directly in the terminal.

- Query and update collections (including metadata) with filters and sorting
- Create and manage collections
- Import/export data (JSON,JSONL,CSV)
- Add schemas and indexes, cap collections

- Upload files to cloud storage
- List and browse files
- Delete files
- Inspect file metadata

- Store key-value pairs
- Retrieve one or many key-value pairs
- Delete key-value pairs
- Set time-to-live (TTL) for key-value pairs

- View application logs
- Access API documentation (local documentation for the MCP agent)

Get Codehooks Admin Token (keep it secret!)

Create a folder for your MCP server scripts:

#!/bin/bash # Set PATH to include common Docker locations export PATH="/usr/local/bin:/opt/homebrew/bin:/usr/bin:/bin:$PATH" exec docker run --rm -i \ --pull always \ -e CODEHOOKS_PROJECT_NAME=your_project_name \ -e CODEHOOKS_ADMIN_TOKEN=your_admin_token \ -e CODEHOOKS_SPACE=your_space_name \ ghcr.io/restdb/codehooks-mcp:latest

@echo off docker run --rm -i ^ --pull always ^ -e CODEHOOKS_PROJECT_NAME=your_project_name ^ -e CODEHOOKS_ADMIN_TOKEN=your_admin_token ^ -e CODEHOOKS_SPACE=your_space_name ^ ghcr.io/restdb/codehooks-mcp:latest

Replaceyour_project_name,your_admin_token, andyour_space_namewith your actual values.

Add to yourclaude_desktop_config.json:

{ "mcpServers": { "codehooks": { "command": "/Users/username/mcp-servers/codehooks.sh" } } }

{ "mcpServers": { "codehooks": { "command": "C:\\Users\\username\\mcp-servers\\codehooks.bat" } } }

{ "mcpServers": { "codehooks": { "command": "/Users/username/mcp-servers/codehooks.sh" } } }

{ "mcpServers": { "codehooks": { "command": "C:\\Users\\username\\mcp-servers\\codehooks.bat" } } }

Replaceusernamewith your actual username.

- "Build a complete survey system: create a database, deploy an API to collect responses, and add search/analytics endpoints"
- "Set up a real-time inventory tracker: import my product CSV, create stock update webhooks, and build low-stock alerts"
- "Build a webhook processing pipeline: receive webhooks from multiple sources, transform and validate data, then trigger automated actions"
- "Build a content management system: create file upload endpoints, set up a metadata database, and deploy content delivery APIs"
- "Set up automated data backups: export my collections to JSON files, store them with timestamps, and create restoration endpoints"
- Create collections(surveys,responses) for data storage
- Add schemasfor data validation and structure
- Deploy JavaScript endpointslikePOST /surveysandGET /surveys/:id/analytics
- Create indexeson response fields for fast searching and analytics
- Import your CSVto populate theproductscollection
- Deploy webhook handlersforPOST /inventory/updateandGET /inventory/low-stock
- Set up key-value storagefor alert thresholds and settings
- Create indexeson SKU and stock levels for real-time queries
- Deploy webhook receiverslikePOST /webhooks/stripeandPOST /webhooks/github
- Create collectionsforwebhook_logs,processed_events, andfailed_events
- Set up data transformationrules and validation schemas for each webhook source
- Use key-value storefor rate limiting and duplicate detection with TTL
- Deploy action triggersthat send emails, update databases, or call other APIs based on webhook data
- Create collectionsforcontent,media, andusers
- Deploy file upload endpointswithPOST /uploadandGET /content/:id
- Upload and manage static filesfor content delivery
- Store metadatalinking files to content records with search indexes
- Export collectionsto JSON format with timestamps
- Upload backup filesto cloud storage automatically
- Deploy restoration APIslikeGET /backupsandPOST /restore/:backup-id
- Store backup metadatain key-value store for tracking and management

Each example demonstrates how multiple MCP tools work together to create complete, production-ready systems through natural conversation with your AI agent.

We thank the following individuals for responsible disclosure and helping improve the security of this project:

This project is licensed under the MIT License.

Deploy production backends, APIs, cron jobs and automations from any AI assistant. Database, auth, storage and 24+ integrations included.

Introspect and query your apps deployed to Convex.

Full-stack backend platform MCP — provision apps, manage databases, deploy functions, and more.

Interact with the Appwrite API to manage databases, users, storage, and more. Requires configuration via environment variables.

Interact with the Appwrite API to manage your backend services.

A Node.js server for the Model Context Protocol that provides access to the Autodesk Platform Services (APS) API with fine-grained access control.

An experimental MCP server providing access to the Autodesk Platform Services (APS) API.

An example MCP server deployed on Cloudflare Workers, without authentication.

A template for deploying a remote, authentication-free MCP server on Cloudflare Workers. Tools are defined directly in the source code.