Integration

Tiger Cloud integration

Tiger Cloud (formerly Timescale Cloud) is Tiger Data's managed PostgreSQL and TimescaleDB service. With this API an agent can create, fork, resize, start, stop, rename and delete database services, set their password, environment, high availability, connection pooler and data tiering, manage read replica sets, VPCs and VPC peerings, and read service logs and metrics. It manages the cloud resources, it does not run SQL. Logout and the preview or internal routes (branches, exporters, IP allow lists, backups) are not exposed, and the initial password returned on creation is withheld. Authentication is HTTP Basic with client credentials from Tiger Console: the public key as username and the secret key as password.

Connect Tiger Cloud How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Tiger Cloud.Built from the 39 Tiger Cloud tools below, on the connection you add once.

What you can do with Tiger Cloud

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Service, 13 operations

attach_service_to_vpcAttach service to vpcPOSTAssociates a service with a VPC.
create_serviceCreate servicePOSTCreates a database service (PostgreSQL, with TimescaleDB when addons includes time-series). Provisions compute charged to the project; returns at once with status QUEUED. Set the password with update_service_password.
delete_serviceDelete serviceDELETEDeletes a database service and its data (asynchronous, irreversible).
detach_service_from_vpcDetach service from vpcPOSTDisassociates a service from its VPC.
fork_serviceFork servicePOSTCreates a new, independent service from a snapshot of this one (fork_strategy LAST_SNAPSHOT, NOW, or PITR with target_time). The fork is new billed compute and inherits the parent's size unless set.
get_serviceGet serviceGETRetrieves the details of a specific service by its ID.
list_servicesList servicesGETRetrieves a list of all services within a specific project.
rename_serviceRename servicePOSTUpdates the name of a specific service.
resize_serviceResize servicePOSTChanges the CPU and memory of a service (asynchronous). A larger size raises the bill; send only the values to change.
set_service_environmentSet service environmentPOSTSets the environment type for the service.
set_service_haSet service haPOSTChanges the high-availability replicas of a service (asynchronous). Each replica is billed compute.
start_serviceStart servicePOSTStarts a stopped service (asynchronous); poll get_service until status is READY.
stop_serviceStop servicePOSTStops a running service (asynchronous). Start it again with start_service.

Replica set, 5 operations

create_read_replica_setCreate read replica setPOSTCreates a read replica set for a service (asynchronous). name, nodes, cpu_millis and memory_gbs are required; every node is billed compute.
delete_read_replica_setDelete read replica setDELETEDeletes a specific read replica set. This is an asynchronous operation.
list_read_replica_setsList read replica setsGETRetrieves a list of all read replica sets associated with a primary service within a project.
resize_read_replica_setResize read replica setPOSTChanges the CPU and memory of a read replica set. A larger size raises the bill; send only the values to change.
set_replica_environmentSet replica environmentPOSTSets the environment type for the read replica set.

Vpc, 5 operations

create_vpcCreate vpcPOSTCreates a VPC (asynchronous) with a name, an IPv4 CIDR block and a region; attach services to it with attach_service_to_vpc.
delete_vpcDelete vpcDELETEDeletes a specific VPC. This is an asynchronous operation.
get_vpcGet vpcGETRetrieves the details of a specific VPC by its ID.
list_vpcsList vpcsGETRetrieves a list of all Virtual Private Clouds (VPCs).
rename_vpcRename vpcPOSTUpdates the name of a specific VPC.

Connection pooler, 4 operations

disable_connection_poolerDisable connection poolerPOSTDeactivates the connection pooler for a specific service within a project.
disable_replica_connection_poolerDisable replica connection poolerPOSTDeactivates the connection pooler for a specific read replica set.
enable_connection_poolerEnable connection poolerPOSTActivates the connection pooler for a specific service within a project.
enable_replica_connection_poolerEnable replica connection poolerPOSTActivates the connection pooler for a specific read replica set.

Peering, 4 operations

create_vpc_peeringCreate vpc peeringPOSTRequests a peering between a Tiger Cloud VPC and your own cloud VPC (asynchronous); poll get_vpc_peering for its status.
delete_vpc_peeringDelete vpc peeringDELETEDeletes a specific VPC peering connection. This is an asynchronous operation.
get_vpc_peeringGet vpc peeringGETRetrieves the details of a specific VPC peering connection.
list_vpc_peeringsList vpc peeringsGETRetrieves a list of all VPC peering connections for a given VPC.

Metric, 3 operations

get_metric_detailsGet metric detailsGETDescribes one metric: what it measures, its type, default aggregation and every label it can be filtered or grouped by (its own plus region, role and ordinal). Find names with list_metric_series.
get_metric_seriesGet metric seriesPOSTReturns time-series data points of one metric for a service over a time window (from, to), as one series per label set. Find metric names with list_metric_series and their labels with get_metric_details.
list_metric_seriesList metric seriesGETReturns the names of all metric series available for a service.

Credential, 1 operation

get_auth_infoGet auth infoGETReturns the identity behind the credentials: for client credentials, the key name, public key, project and issuing user. Useful to find the project id.

Data tiering, 1 operation

enable_data_tieringEnable data tieringPOSTTurns on tiered storage: tiering policies move older data to low-cost object storage, where it stays queryable but read-only. It cannot be turned off through the API (only Tiger Data support can).

Log, 1 operation

get_service_logsGet service logsGETReturns up to 500 log entries of a service, newest first, filtered by time, search terms and severities. Page back with cursor set to the last_cursor of the previous response.

Project, 1 operation

list_projectsList projectsGETLists the projects the credentials can access (client credentials see only the project they belong to). Use the id as project_id.

Service password, 1 operation

update_service_passwordUpdate service passwordPOSTSets a new master password for the service's database. Returns no content on success.

Use Tiger Cloud from Claude Code, Cursor or Codex

Connect Tiger Cloud in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Tiger Cloud operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Tiger Cloud

Create your workspace
Sign up free. Nothing to install.
Connect Tiger Cloud once
Add your Tiger Cloud connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.