Tiger Cloud: Performance, Scale, Enterprise, Free

Self-hosted products

MST

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

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

To follow the steps on this page:

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

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

Tiger MCP is bundled with Tiger CLI:

  1. Install Tiger CLI

    Use the terminal to install the CLI:

  2. Set up API credentials

    1. Log Tiger CLI into your Tiger Cloud account:

      tiger auth login

      Tiger CLI opens Console 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 Tiger Cloud project:

      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 project is associated with your account, this step is not shown.

      Where possible, Tiger CLI 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, Tiger CLI stores your configuration in ~/.config/tiger/config.yaml.

  3. Test your authenticated connection to Tiger Cloud by listing services

    tiger service list

    This call returns something like:

    • No services:

      🏜️ 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 services:

      ┌────────────┬─────────────────────┬────────┬─────────────┬──────────────┬──────────────────┐
      │ 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 project and services in your Tiger Cloud account

    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 Tiger MCP to manage your services in Tiger Cloud.

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

  1. Run your AI Assistant

    claude

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

  2. Check your Tiger MCP 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 services

    > 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 services 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 Tiger MCP do it all for you.

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 Tiger MCP:

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

Tiger MCP exposes the following MCP tools to your AI Assistant:

CommandParameterRequiredDescription
service_list--Returns a list of the services in the current project.
service_get--Returns detailed information about a service.
service_idThe unique identifier of the service (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 service in Tiger Cloud.
WARNING: creates billable resources.
name-Set the human-readable name of up to 128 characters for this service.
addons-Set the array of addons to enable for the service. Options:
  • time-series: enables TimescaleDB
  • ai: enables the AI and vector extensions
Set an empty array for Postgres-only.
region-Set the AWS region to deploy this service 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 service to be fully ready before returning.
timeout_minutes-Set the timeout in minutes to wait for service to be ready. Only used when wait=true. Default: 30 minutes
set_default-By default, the new service is the default for following commands in CLI. Set to false to keep the previous service as the default.
with_password-Set to true to include the password for this service in response and connection string.
WARNING: never set to true unless user explicitly requests the password.
service_fork--Fork an existing service to create a new independent copy.
WARNING: creates billable resources.
service_idThe unique identifier of the service to fork (10-character alphanumeric string).
fork_strategyFork 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 service. Defaults to {source-service-name}-fork.
cpu_memory-CPU and memory allocation combination. Inherits from source service 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 service to be fully ready before returning. Default: false.
timeout_minutes-Set the timeout in minutes to wait for forked service to be ready. Only used when wait=true. Default: 30 minutes
set_default-By default, the forked service is set as the default for following commands in CLI. Set to false to keep the previous service as the default.
with_password-Set to true to include the password for the forked service 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 service. The password change takes effect immediately and may terminate existing connections.
service_idThe unique identifier of the service you want to update the password for.
passwordThe new password for the tsdbadmin user.
db_execute_query--Execute a single SQL query against a service. 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_idThe unique identifier of the service. Use tiger_service_list to find service IDs.
queryThe 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 service role/username to connect as. Default: tsdbadmin.
pooled-Use connection pooling. This is only available if you have already enabled it for the service. Default: false.

You can use the following Tiger CLI commands to run Tiger MCP:

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

CommandSubcommandDescription
mcpManage Tiger MCP
install [client]Install and configure Tiger MCP 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
startStart Tiger MCP. This is the same as tiger mcp start stdio
start stdioStart Tiger MCP with stdio transport
start httpStart Tiger MCP with HTTP transport. This option is for users who wish to access Tiger MCP without using stdio. For example, your AI Assistant does not support stdio, or you do not want to run CLI on your device.
Flags are:
  • --port <port number>: the default is 8000
  • --host <hostname>: the default is localhost

You can use the following Tiger CLI global flags when you run Tiger MCP:

FlagDefaultDescription
--analyticstrueSet to false to disable usage analytics
--color trueSet to false to disable colored output
--config-dir string~/.config/tigerSet the directory that holds config.yaml
--debugNo debuggingEnable debug logging
--help-Print help about the current command. For example, tiger service --help
--password-storage stringkeyringSet the password storage method. Options are keyring, pgpass, or none
--service-id string-Set the Tiger Cloud service to manage
--skip-update-check-Do not check if a new version of Tiger CLI is available

Keywords

Found an issue on this page?Report an issue or Edit this page in GitHub.