01 · Add a connection
Choose a connector, enter its configuration in GateRook, and test that your computer can reach the service.
The GateRook field guide
Your stack.
Connected to AI.
From the first connection to a useful answer. Find your service, follow the setup, and see exactly what your AI can do through MCP.
One workflow for your whole stack
Connect. Set boundaries. Ask.
02 · Create an endpoint
Select connections and give each tool a mode: Off, Read only, or Approval. Keep development and production separate.
03 · Connect your AI
Use Clients to connect your MCP app. The agent requests tools; GateRook checks access, runs allowed calls and returns results.
Find your integration
A practical guide for every connection.
Built-in connectors, supported database variants, log backends and external MCP servers. Each guide includes configuration, available tools, an illustrated request and troubleshooting.
15 integration guides
Databases
MySQL
Connect MySQL to an MCP-compatible AI app with GateRook. Explore schemas, run read-only SQL, review changes and keep database credentials out of prompts.
PostgreSQL
Connect PostgreSQL to an MCP-compatible AI app with GateRook. Explore schemas, run read-only SQL, review changes and keep database credentials out of prompts.
MariaDB
Connect MariaDB to an MCP-compatible AI app with GateRook. Explore schemas, run read-only SQL, review changes and keep database credentials out of prompts.
Redis
Connect Redis to an AI app through MCP. Scan allowed keys, inspect values and TTLs, and troubleshoot cache data with the read-only GateRook connector.
MongoDB
Connect MongoDB to AI through MCP. Find documents, run read-only aggregations and scope collections with GateRook, without putting credentials in prompts.
APIs & logs
Loki
Connect Loki to AI through MCP. Search and follow scoped logs with GateRook, using native queries, bounded time ranges and private credentials.
AWS CloudWatch Logs
Connect AWS CloudWatch Logs to AI through MCP. Search and follow scoped logs with GateRook, using native queries, bounded time ranges and private credentials.
Google Cloud Logging
Connect Google Cloud Logging to AI through MCP. Search and follow scoped logs with GateRook, using native queries, bounded time ranges and private credentials.
OpenSearch
Connect OpenSearch to AI through MCP. Search and follow scoped logs with GateRook, using native queries, bounded time ranges and private credentials.
HTTP API
Connect a REST or HTTP API to AI through MCP. Scope base URLs and paths, keep API keys in GateRook, and approve requests that change data.
Cloud & infrastructure
AWS
Connect Claude, Codex or Cursor to AWS through GateRook. Inspect resources and CloudWatch metrics with scoped regions, local credentials and read-only MCP tools.
Google Cloud
Use AI with Google Cloud through GateRook MCP tools. Search Cloud Asset inventory, inspect supported resources live and query Cloud Monitoring with scoped credentials.
Kubernetes
Connect AI to Kubernetes with GateRook. Inspect pods, events and logs over MCP, restrict namespaces, and review rollout restarts or manifest changes before execution.
SSH
Use SSH from AI through GateRook MCP runbooks. Connect with keys, passwords or Vault SSH CA, verify host keys, and approve commands that change your servers.
MCP servers
MCP servers
Put an existing stdio or Streamable HTTP MCP server behind GateRook. Review discovered tools, configure secret injection, choose endpoint modes and audit calls.
Your infrastructure, on your terms
Give your AI the context it needs.
Start with one connection. Choose what your AI can do.