Integrate Tiger Cloud with your AI Assistant

Manage your services and optimize your schema and queries using your AI Assistant

provides access to your resources through Claude and other AI Assistants. mirrors the functionality of and is integrated directly into the binary. You manage your resources using natural language from your AI Assistant. As is integrated with the documentation, ask any question and you will get the best answer.

This page shows you how to install and set up secure authentication for , then manage the resources in your through using your AI Assistant.

Prerequisites

To follow the steps on this page:

• Create a target .

• Install an AI Assistant on your developer device with an active API key.

  The following AI Assistants are automatically configured by : claude-code, cursor, windsurf, codex, gemini/gemini-cli, vscode/code/vs-code. You can also manually configure .

Install and configure MCP Server

is bundled with :

1. Install

   Use the terminal to install the :

   Debian

   curl -s https://packagecloud.io/install/repositories/timescale/tiger-cli/script.deb.sh | sudo os=any dist=any bash
   sudo apt-get install tiger-cli
   

   Ubuntu

   curl -s https://packagecloud.io/install/repositories/timescale/tiger-cli/script.deb.sh | sudo os=any dist=any bash
   sudo apt-get install tiger-cli
   

   Red Hat

   curl -s https://packagecloud.io/install/repositories/timescale/tiger-cli/script.rpm.sh | sudo os=rpm_any dist=rpm_any bash
   sudo yum install tiger-cli
   

   Fedora

   curl -s https://packagecloud.io/install/repositories/timescale/tiger-cli/script.rpm.sh | sudo os=rpm_any dist=rpm_any bash
   sudo yum install tiger-cli
   

   MacOS

   brew install --cask timescale/tap/tiger-cli
   

   x-platform

   curl -fsSL https://cli.tigerdata.com | sh
   

2. Set up API credentials

   1. Log into your :

      tiger auth login
      

      opens in your browser. Log in, then click Authorize.

      You can have a maximum of 10 active client credentials. If you get an error, open credentials and delete an unused credential.

   2. Select a :

      Auth URL is: https://console.cloud.timescale.com/oauth/authorize?client_id=lotsOfURLstuff
      Opening browser for authentication...
      Select a project:
      
      > 1. Tiger Project (tgrproject)
      2. YourCompany (Company wide project) (cpnproject)
      3. YourCompany Department (dptproject)
      
      Use ↑/↓ arrows or number keys to navigate, enter to select, q to quit
      

      If only one is associated with your , this step is not shown.

      Where possible, stores your authentication information in the system keychain/credential manager. If that fails, the credentials are stored in ~/.config/tiger/credentials with restricted file permissions (600). By default, stores your configuration in ~/.config/tiger/config.yaml.

3. Test your authenticated connection to by listing s

   tiger service list
   

   This call returns something like:

   • No s:

     🏜️  No services found! Your project is looking a bit empty.
     🚀 Ready to get started? Create your first service with: tiger service create
     

   • One or more s:

     ┌────────────┬─────────────────────┬────────┬─────────────┬──────────────┬──────────────────┐
     │ SERVICE ID │        NAME         │ STATUS │    TYPE     │    REGION    │     CREATED      │
     ├────────────┼─────────────────────┼────────┼─────────────┼──────────────┼──────────────────┤
     │ tgrservice │ tiger-agent-service │ READY  │ TIMESCALEDB │ eu-central-1 │ 2025-09-25 16:09 │
     └────────────┴─────────────────────┴────────┴─────────────┴──────────────┴──────────────────┘
     

1. Configure your AI Assistant to interact with the and s in your

   For example:

   tiger mcp install
   

2. **Choose the client to integrate with, then press Enter **

   Select an MCP client to configure:
   
   > 1. Claude Code
   2. Codex
   3. Cursor
   4. Gemini CLI
   5. VS Code
   6. Windsurf
   
   Use ↑/↓ arrows or number keys to navigate, enter to select, q to quit
   

And that is it, you are ready to use to manage your s in .

Manage the resources in your Tiger Cloud account through your AI Assistant

Your AI Assistant is connected to your and the documentation, you can now use it to manage your s and learn more about how to implement features. For example:

1. Run your AI Assistant

   claude
   

   Claude automatically runs server that enables you to interact with from your AI Assistant.

2. Check your configuration

   > is the tigerdata mcp server active for you?
   

   You see something like:

   MCP server is active. I can see the following Tiger Data-related tools available:
   
   - mcp__tiger__get_guide - Retrieve TimescaleDB guides and best practices
   - mcp__tiger__semantic_search_postgres_docs - Search PostgreSQL documentation
   - mcp__tiger__semantic_search_tiger_docs - Search Tiger Cloud and TimescaleDB documentation
   - mcp__tiger__tiger_service_create - Create new database services
   - mcp__tiger__tiger_service_list - List all database services
   - mcp__tiger__tiger_service_show - Show detailed service information
   - mcp__tiger__tiger_service_update_password - Update service passwords
   
   Is there something specific you'd like to do with the Tiger Data MCP server?
   

3. Ask a basic question about your s

   > can you list my active services please
   

   You see something like:

   ⏺ You have 3 active services, all with the same name "my-first-service":
   
   1. tgrservice1 - READY - TimescaleDB - us-east-1 - 1 CPU/4GB - Created: 2025-09-30
   2. tgrservice1 - READY - TimescaleDB - us-east-1 - 1 CPU/4GB - Created: 2025-09-30
   3. tgrservice1 - READY - TimescaleDB - us-east-1 - 1 CPU/4GB - Created: 2025-09-30
   

4. Manage your s without having to learn how to

   For example:

   Can you create a new ai service called bob with a replica for me please
   

   You see something like:

    tiger - Create Database Service (MCP)(name: "bob", addons: ["ai"], replicas: 1, wait: false)
   

5. Find best practice for things you need to do

   For example:

   >  I need to migrate a database with 25 million rows of data to Tiger Cloud,
   please tell me what service optimizations i should do before migration.
   
   

   You see something like:

   ⏺ For migrating a database with 25 million rows to Tiger Cloud, here are the key service optimizations to do before migration:
   
   Pre-Migration Service Optimizations
   
   1. Right-size your compute resources:
     - For 25M rows, start with at least 2 CPU/8GB or 4 CPU/16GB
     - You can scale up during migration if needed, then scale down after
   
   2. Enable the appropriate addons:
     - Use time-series addon if you are working with time-series data
     - Use ai addon if you need vector/AI capabilities
   
   3. Choose optimal region:
     - Select the region closest to your current database to minimize network transfer time
     - This significantly reduces migration duration
   
   4. Consider enhanced storage (Enterprise only):
     - If you expect high write throughput during migration, enhanced storage provides better IOPS (up to 32,000)
   
   5. Skip replicas initially:
     - Start with 0 replicas during migration
     - Add replicas after migration completes to avoid duplicate data copying
   
   6. Plan for storage space:
     - Estimate your uncompressed data size
     - Allocate sufficient high-performance storage (scales automatically but good to plan)
     - You can enable tiered storage later for older data
   
   During Migration Best Practices
   
   Migration method selection:
     - 25M rows: Use schema-then-data migration (migrate schema first, then copy data in chunks)
     - Allows restart if a copy operation fails
     - Better for databases >10GB
   
   Database configuration to set AFTER migration:
     - Set up compression policies (once data is loaded)
     - Configure retention policies
     - Create continuous aggregates
     - Enable tiered storage for cost optimization
   
   Connection settings:
     - Use the pooled connection endpoint for better performance during bulk inserts
     - Disable unnecessary constraints/indexes during migration, re-enable after
   
   Would you like me to help you create an optimized service for this migration?
   

That beats working. Let do it all for you.

Manually configure MCP Server

If your MCP client is not supported by tiger mcp install, follow the client’s instructions to install MCP servers. For example, many clients use a JSON file like the following that use tiger mcp start to start :

{
   "mcpServers": {
      "tiger": {
         "command": "tiger",
         "args": [
            "mcp",
            "start"
         ]
      }
   }
}

Tiger MCP Server tools

exposes the following MCP tools to your AI Assistant:

Command	Parameter	Required	Description
service_list	-	-	Returns a list of the s in the current .
service_get	-	-	Returns detailed information about a .
	service_id	✓	The unique identifier of the (10-character alphanumeric string).
	with_password	-	Set to true to include the password in the response and connection string. WARNING: never do this unless the user explicitly requests the password.
service_create	-	-	Create a new in . WARNING: creates billable resources.
	name	-	Set the human-readable name of up to 128 characters for this .
	addons	-	Set the array of addons to enable for the . Options: time-series: enables ai: enables the AI and vector extensions Set an empty array for -only.
	region	-	Set the AWS region to deploy this in.
	cpu_memory	-	CPU and memory allocation combination. Available configurations are: shared/shared 0.5 CPU/2 GB 1 CPU/4 GB 2 CPU/8 GB 4 CPU/16 GB 8 CPU/32 GB 16 CPU/64 GB 32 CPU/128 GB
	replicas	-	Set the number of high-availability replicas for fault tolerance.
	wait	-	Set to true to wait for the to be fully ready before returning.
	timeout_minutes	-	Set the timeout in minutes to wait for to be ready. Only used when wait=true. Default: 30 minutes
	set_default	-	By default, the new is the default for following commands in . Set to false to keep the previous as the default.
	with_password	-	Set to true to include the password for this in response and connection string. WARNING: never set to true unless user explicitly requests the password.
service_fork	-	-	Fork an existing to create a new independent copy. WARNING: creates billable resources.
	service_id	✓	The unique identifier of the to fork (10-character alphanumeric string).
	fork_strategy	✓	Fork strategy: NOW: fork at the current database state LAST_SNAPSHOT:fork at last existing snapshot. This is the faster option PITR: create a point-in-time recovery. You must also set the target_time parameter for PITR forks.
	target_time	-	Set the target time for a PIRT fork_strategy in RFC3339 format. For example 2025-01-15T10:30:00Z).
	name	-	Set the human-readable name for the forked . Defaults to {source-service-name}-fork.
	cpu_memory	-	CPU and memory allocation combination. Inherits from source if not specified. Available configurations are: shared/shared 0.5 CPU/2 GB 1 CPU/4 GB 2 CPU/8 GB 4 CPU/16 GB 8 CPU/32 GB 16 CPU/64 GB 32 CPU/128 GB
	wait	-	Set to true to wait for the forked to be fully ready before returning. Default: false.
	timeout_minutes	-	Set the timeout in minutes to wait for forked to be ready. Only used when wait=true. Default: 30 minutes
	set_default	-	By default, the forked is set as the default for following commands in . Set to false to keep the previous as the default.
	with_password	-	Set to true to include the password for the forked in response and connection string. WARNING: never set to true unless user explicitly requests the password.
service_update_password	-	-	Update the password for the tsdbadmin for this . The password change takes effect immediately and may terminate existing connections.
	service_id	✓	The unique identifier of the you want to update the password for.
	password	✓	The new password for the tsdbadmin user.
db_execute_query	-	-	Execute a single SQL query against a . This command returns column metadata, result rows, affected row count, and execution time. Multi-statement queries are not supported. WARNING: can execute destructive SQL including INSERT, UPDATE, DELETE, and DDL commands.
	service_id	✓	The unique identifier of the . Use tiger_service_list to find IDs.
	query	✓	The SQL query to execute. Single statement queries are supported.
	parameters	-	Query parameters for parameterized queries. Values are substituted for the $n placeholders in the query.
	timeout_seconds	-	The query timeout in seconds. Default: 30.
	role	-	The role/username to connect as. Default: tsdbadmin.
	pooled	-	Use connection pooling. This is only available if you have already enabled it for the . Default: false.

Tiger CLI commands for MCP Server

You can use the following commands to run :

Usage: tiger mcp [subcommand] --<flags>

Command	Subcommand	Description
mcp		Manage
	install [client]	Install and configure for a specific client installed on your developer device. Supported clients are: claude-code, cursor, windsurf, codex, gemini/gemini-cli, vscode/code/vs-code. Flags: --no-backup: do not back up the existing configuration --config-path: open the configuration file at a specific location
	start	Start . This is the same as tiger mcp start stdio
	start stdio	Start with stdio transport
	start http	Start with HTTP transport. This option is for users who wish to access without using stdio. For example, your AI Assistant does not support stdio, or you do not want to run on your device. Flags are: --port <port number>: the default is 8000 --host <hostname>: the default is localhost

Global flags

You can use the following global flags when you run :

Flag	Default	Description
--analytics	true	Set to false to disable usage analytics
--color	true	Set to false to disable colored output
--config-dir string	~/.config/tiger	Set the directory that holds config.yaml
--debug	No debugging	Enable debug logging
--help	-	Print help about the current command. For example, tiger service --help
--password-storage string	keyring	Set the password storage method. Options are keyring, pgpass, or none
--service-id string	-	Set the to manage
--skip-update-check	-	Do not check if a new version of is available