# Tiger MCP (oci · ghcr.io/timescale/tiger-cli)

Provides programmatic access to Tiger Cloud services, databases, and documentation.

- Trust score: 50/100 (low)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- oci · `ghcr.io/timescale/tiger-cli`: 50/100 (this document), [markdown](https://verifymcp.io/servers/timescale-tiger-cli/ghcr-io-timescale-tiger-cli.md), [page](https://verifymcp.io/servers/timescale-tiger-cli/ghcr-io-timescale-tiger-cli)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/timescale/tiger-cli`
- Version: `0.27.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this image's dependency list comes from an SBOM its publisher attached, which nothing verifies, so we will not report it as a clean result.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this image's dependency list comes from an SBOM its publisher attached. It names packages and versions but not whether each is deprecated, still maintained or linked to its source, so there is nothing we can fairly grade.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 7 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3989 tokens (~221/item across 18 items; 18 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 19 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Tiger MCP server?

Tiger MCP runs locally as a container image, launched with docker run --rm -i -e TIGER_PUBLIC_KEY -e TIGER_SECRET_KEY ghcr.io/timescale/tiger-cli:0.27.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add timescale-tiger-cli -- docker run --rm -i -e TIGER_PUBLIC_KEY -e TIGER_SECRET_KEY ghcr.io/timescale/tiger-cli:0.27.0
```

This image reads TIGER_PUBLIC_KEY and TIGER_SECRET_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Cursor

```json
{
  "mcpServers": {
    "timescale-tiger-cli": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "TIGER_PUBLIC_KEY",
        "-e",
        "TIGER_SECRET_KEY",
        "ghcr.io/timescale/tiger-cli:0.27.0"
      ]
    }
  }
}
```

This image reads TIGER_PUBLIC_KEY and TIGER_SECRET_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### VS Code

```json
{
  "servers": {
    "timescale-tiger-cli": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "TIGER_PUBLIC_KEY",
        "-e",
        "TIGER_SECRET_KEY",
        "ghcr.io/timescale/tiger-cli:0.27.0"
      ]
    }
  }
}
```

This image reads TIGER_PUBLIC_KEY and TIGER_SECRET_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Codex

```bash
codex mcp add timescale-tiger-cli -- docker run --rm -i -e TIGER_PUBLIC_KEY -e TIGER_SECRET_KEY ghcr.io/timescale/tiger-cli:0.27.0
```

This image reads TIGER_PUBLIC_KEY and TIGER_SECRET_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "timescale-tiger-cli": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "-e",
        "TIGER_PUBLIC_KEY",
        "-e",
        "TIGER_SECRET_KEY",
        "ghcr.io/timescale/tiger-cli:0.27.0"
      ],
      "enabled": true
    }
  }
}
```

This image reads TIGER_PUBLIC_KEY and TIGER_SECRET_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Hermes

```yaml
mcp_servers:
  timescale-tiger-cli:
    command: "docker"
    args: ["run", "--rm", "-i", "-e", "TIGER_PUBLIC_KEY", "-e", "TIGER_SECRET_KEY", "ghcr.io/timescale/tiger-cli:0.27.0"]
```

This image reads TIGER_PUBLIC_KEY and TIGER_SECRET_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Netclaw

```json
{
  "McpServers": {
    "timescale-tiger-cli": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "-e",
        "TIGER_PUBLIC_KEY",
        "-e",
        "TIGER_SECRET_KEY",
        "ghcr.io/timescale/tiger-cli:0.27.0"
      ]
    }
  }
}
```

This image reads TIGER_PUBLIC_KEY and TIGER_SECRET_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Other

```json
{
  "mcpServers": {
    "timescale-tiger-cli": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "TIGER_PUBLIC_KEY",
        "-e",
        "TIGER_SECRET_KEY",
        "ghcr.io/timescale/tiger-cli:0.27.0"
      ]
    }
  }
}
```

This image reads TIGER_PUBLIC_KEY and TIGER_SECRET_KEY. Set them in your client's env block for this server; docker run -e passes each one through to the container.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-31 (score 50, 0)

- [security] Stability: 0.97 → pass

### 2026-10-30 (score 50, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 49, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 48, 0)

- [functional] Package version: 0.26.0 → 0.27.0

### 2026-10-26 (score 48, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 47, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 46, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 45, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (18)

### `db_extensions_list` (~125 tokens)

List Database Extensions

List the PostgreSQL extensions installed in a service database.

Connects to a PostgreSQL/TimescaleDB service in Tiger Cloud and returns each installed extension's name, version, schema, and description. The connection is opened in immutable read-only mode.

Input parameters:

- `role` (string): Database role/username to connect as
- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs. A read replica set ID is also accepted here — passing one lists the extensions on that read…

Output parameters:

- `extensions` (null|array): The extensions installed in the database, ordered by name.

### `db_query` (~390 tokens)

Execute SQL Query

Execute SQL queries against a service database.

Connects to a PostgreSQL database service in Tiger Cloud and executes the provided SQL query, returning the results with column information, row data, and execution metadata. Pass the SQL as 'query', or point 'file' at a .sql file on disk to run its contents.

Multi-statement queries (semicolon-separated) are supported when no parameters are provided. All result sets are returned. By default, statements execute in an implicit transaction that automatically commits on success or rolls back on error. Explicit transactions (opened with BEGIN) must be explicitly committed with COMMIT, or they roll back when the connection closes.

Process data in the database, not in your context: aggregate, filter, sort/limit, and join in SQL rather than fetching raw rows.

WARNING: Can execute any SQL statement including INSERT, UPDATE, DELETE, and DDL commands. Always review queries before execution.

Input parameters:

- `file` (string): Path to a SQL file on disk to execute, instead of passing its contents as 'query'. Exactly one of 'query' or 'file' must be provided.
- `parameters` (null|array): Query parameters. Values are substituted for $1, $2, etc. placeholders in the query. Only supported for single-statement queries.
- `pooled` (boolean): Use connection pooling (if available)
- `query` (string): PostgreSQL query to execute. Exactly one of 'query' or 'file' must be provided.
- `role` (string): Database role/username to connect as
- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs. A read replica set ID is also accepted here — passing one runs the query against that read r…
- `timeout_seconds` (integer): Query timeout in seconds

Output parameters:

- `execution_time` (string): Execution time as a human-readable duration string
- `notice` (string): Present only when results were truncated. Actionable guidance for getting the needed data via SQL (aggregate, filter, paginate) instead of re-running the query.
- `result_sets` (null|array): Array of result sets returned. For single-statement queries, this array will contain one element. For multi-statement queries, this array will contain one element per statement.
- `truncated` (boolean): True when any result set was truncated to limit the amount of data returned. See notice for guidance.
- `warning` (string): Present when connection pooling was requested for a read replica that has none; the query ran over a direct connection instead.

### `db_schema` (~282 tokens)

Show Database Schema

Display the schema of a service database.

Connects to a PostgreSQL/TimescaleDB service in Tiger Cloud and returns its schema as readable text: tables (regular, partitioned, and foreign), views, materialized views, enum types, functions, procedures, indexes, triggers, and TimescaleDB hypertable and continuous aggregate metadata. Only objects the connecting role can access are returned.

By default only user-facing schemas and objects are shown; view/routine definitions and object comments are omitted unless requested. The connection is opened in immutable read-only mode.

Input parameters:

- `comments` (boolean): Include object comments (COMMENT ON text).
- `definitions` (boolean): Include full object definitions (view SELECTs, function/procedure bodies).
- `internal` (boolean): Include system schemas (pg_*, information_schema, TimescaleDB internals) and extension-owned objects.
- `pooled` (boolean): Use connection pooling (if available)
- `role` (string): Database role/username to connect as
- `schema` (string): Restrict output to a single schema (namespace). When omitted, all accessible schemas are returned.
- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs. A read replica set ID is also accepted here — passing one introspects that read replica inst…

Output parameters:

- `schema` (string): The database schema rendered as human-readable text, grouped under a SCHEMA header per namespace.
- `warning` (string): Present when connection pooling was requested for a read replica that has none; the schema was read over a direct connection instead.

### `feedback` (~100 tokens)

Submit Feedback

Submit feedback or a bug report to the Tiger Data team.

The message reaches a person, so confirm the wording with the user before sending. This opens no support case and returns no ticket to track; for anything that needs a tracked response, point the user at the support URL returned in the output.

Input parameters:

- `message` (string, required): The feedback or bug report to send. Describe what the user was trying to do and what happened. At most 3000 characters.

Output parameters:

- `success` (boolean): Whether the feedback was submitted.
- `support_url` (string): The Tiger Cloud console page where the user opens a tracked support ticket.

### `service_create` (~377 tokens)

Create Database Service

Create a new database service in Tiger Cloud with specified type, compute resources, region, and HA options.

The default type of service created depends on the user's plan:
\- Free plan: Creates a service with shared CPU/memory and the 'time-series' add-on
\- Paid plans: Creates a service with 0.5 CPU / 2 GB memory and the 'time-series' add-on

WARNING: Creates billable resources.

Input parameters:

- `addons` (null|array): Array of addons to enable for the service. 'time-series' enables TimescaleDB. Use empty array for PostgreSQL-only.
- `cpu_memory` (string): CPU and memory allocation combination.
- `environment` (string): Environment tag for the new service. Use 'PROD' only for production workloads — under read-only mode for production services, creating a PROD service is refused, and deleting a PROD service always re…
- `name` (string): Human-readable name for the service (auto-generated if not provided)
- `region` (null|string): AWS region where the service will be deployed. Choose the region closest to your users for optimal performance.
- `replicas` (integer): Number of high-availability replicas for fault tolerance. Higher replica counts increase cost but improve availability.
- `set_default` (boolean): Whether to set the newly created service as the default service. When true, the service will be set as the default for future commands.
- `wait` (boolean): Whether to wait for the service to be fully ready before returning. Default is false (recommended). Only set to true if your next steps require connecting to or querying this database. When true, wai…
- `with_password` (boolean): Whether to include the password in the response. NEVER set to true unless the user explicitly asks for the password.

Output parameters:

- `message` (string)
- `password_storage` (null|object)
- `service` (object)

### `service_delete` (~123 tokens)

Delete Database Service

Delete a database service permanently.

This operation is irreversible: the service and all of its data are destroyed. Deleting a service tagged PROD automatically prompts the user, via an elicitation request through the MCP client, to confirm the deletion before it proceeds, so agents don't need to ask the user for confirmation themselves; if the client cannot prompt, the deletion is refused and the user must run 'tiger service delete' from the CLI instead.

Input parameters:

- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs.

Output parameters:

- `deleted` (boolean): Whether the service was deleted. False when the user declined the confirmation prompt for a PROD service; do not retry unless the user asks again.
- `message` (string): Human-readable outcome of the operation
- `service_id` (string): Identifier of the service the deletion targeted

### `service_fork` (~472 tokens)

Fork Database Service

Fork an existing database service to create a new independent copy.

You must specify a fork strategy:
\- 'NOW': Fork at the current database state (creates new snapshot or uses WAL replay)
\- 'LAST_SNAPSHOT': Fork at the last existing snapshot (faster fork)
\- 'PITR': Fork at a specific point in time (requires target_time parameter)

By default:
\- Name will be auto-generated from the source service name
\- CPU and memory will be inherited from the source service
\- The forked service will be set as the default service

WARNING: Creates billable resources.

Input parameters:

- `cpu_memory` (string): CPU and memory allocation combination. If not specified, inherits from source service.
- `environment` (string): Environment tag for the fork, which is independent of the source service's tag. Use 'PROD' only for production workloads — under read-only mode for production services, forking a PROD source into a D…
- `fork_strategy` (string, required): Fork strategy: 'NOW' creates fork at current state, 'LAST_SNAPSHOT' uses last existing snapshot (faster), 'PITR' allows point-in-time recovery to specific timestamp (requires target_time parameter)
- `name` (string): Human-readable name for the forked service (auto-generated if not provided)
- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs.
- `set_default` (boolean): Whether to set the newly forked service as the default service. When true, the forked service will be set as the default for future commands.
- `target_time` (null|string): Target timestamp for point-in-time recovery (RFC3339 format). Only used when fork_strategy is 'PITR'.
- `wait` (boolean): Whether to wait for the forked service to be fully ready before returning. Default is false (recommended). Only set to true if your next steps require connecting to or querying this database. When tr…
- `with_password` (boolean): Whether to include the password in the response. NEVER set to true unless the user explicitly asks for the password.

Output parameters:

- `message` (string)
- `password_storage` (null|object)
- `service` (object)

### `service_get` (~89 tokens)

Get Service Details

Get detailed information for a specific database service. Returns connection endpoints, replica configuration, resource allocation, creation time, and status.

Input parameters:

- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs.
- `with_password` (boolean): Whether to include the password in the response. NEVER set to true unless the user explicitly asks for the password.

Output parameters:

- `service` (object)

### `service_list` (~31 tokens)

List Database Services

List all database services in your Tiger Cloud project. Returns services with status, type, region, and resource allocation.

Output parameters:

- `services` (null|array)

### `service_logs` (~201 tokens)

Get Service Logs

View logs for a database service.

Fetches and displays logs from the specified service. By default, shows the last 100 log entries.

Supports filtering by time (via since/until parameters) and node (for services with HA replicas).

Input parameters:

- `node` (null|integer): Specific service node to fetch logs from (for services with HA replicas). If not provided, logs from the primary node will be fetched.
- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs.
- `since` (null|string): Fetch logs after this timestamp (RFC3339 format). If not provided, only the tail parameter limits how far back logs are fetched.
- `tail` (integer): Number of log lines to return. Defaults to 100.
- `until` (null|string): Fetch logs before this timestamp (RFC3339 format). If not provided, fetches logs up to the current time.

Output parameters:

- `logs` (null|array): Log lines ordered from oldest to newest. Each line is prefixed with an RFC3339 timestamp followed by the log message.

### `service_metrics_available` (~123 tokens)

List Available Metric Series

List the names of all metric series available for a service, for monitoring, debugging, and performance investigation. Available metrics span hardware/resource usage (CPU, memory, disk, network), PostgreSQL settings, PgBouncer connection-pool stats, PostgreSQL activity/locks/replication, and TimescaleDB internals (compression, chunks, background jobs). Call this first to discover what metrics exist before fetching data with service_metrics_series.

Input parameters:

- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs.

Output parameters:

- `series` (null|array)

### `service_metrics_details` (~251 tokens)

Get Metric Details

Get descriptive metadata for a metric: what it measures, its type, default
aggregation function, and available labels. Use this to understand a metric
before querying it for monitoring, debugging, or performance investigation.

Use service_metrics_available to discover metric names, this tool to inspect
one, then service_metrics_series to fetch its data.

These metrics have no richer metadata (returns just the name, with type,
default aggregation, description, and labels all empty): timescale_cloud_system_cpu_total_millicores, timescale_cloud_system_cpu_usage_millicores, timescale_cloud_system_disk_io_read_bytes, timescale_cloud_system_disk_io_read_ops, timescale_cloud_system_disk_io_total_bytes, timescale_cloud_system_disk_io_total_ops, timescale_cloud_system_disk_io_write_bytes, timescale_cloud_system_disk_io_write_ops, timescale_cloud_system_disk_usage_bytes, timescale_cloud_system_memory_total_bytes, timescale_cloud_system_memory_usage_bytes.

Input parameters:

- `metric_name` (string, required): Name of the metric to describe. Use service_metrics_available to discover valid names.
- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs.

Output parameters:

- `details` (object)

### `service_metrics_series` (~615 tokens)

Get Metric Series Data

Fetch time-series data for a named metric over a specified time window, for monitoring, debugging, and performance investigation.

Use service_metrics_available first to discover valid metric names.

The response groups data points by their label set — a single request may
return multiple labeled series (e.g. one per replica, one per worker ordinal).
Each series contains its full list of raw data points. Use group_by to
control which label keys define that grouping.

Input parameters:

- `bucket_seconds` (integer): Aggregation bucket size in seconds. Omit unless a specific resolution is needed: the server then picks a default matched to the window (roughly 1m for windows up to 1h, 1h for up to 30d, 1d beyond th…
- `filters` (null|array): Arbitrary label filters applied to the series query. Recognized label names depend on the metric.
- `fn` (string): Aggregation function applied per bucket. Not accepted on these metrics (returns INVALID_REQUEST): timescale_cloud_system_cpu_total_millicores, timescale_cloud_system_cpu_usage_millicores, timescale_c…
- `from` (string, required): Start of the time window (RFC3339 format). Derive it from the current time; the examples are placeholders.
- `group_by` (null|array): Label keys to break the result into one series per distinct value combination. Not accepted on the same metrics that reject fn (returns INVALID_REQUEST). Omit, or pass an empty list, to collapse all…
- `metric_name` (string, required): Name of the metric series to fetch. Must be a name returned by service_metrics_available; do not guess names.
- `role` (string): Convenience filter for the 'role' label. Omit to include all roles. Equivalent to passing {key:"role", value:"primary"|"replica"} via filters.
- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs.
- `to` (string, required): End of the time window (RFC3339 format). Must not be in the future; use the current time to get the latest data.

Output parameters:

- `series` (null|array)

### `service_rename` (~80 tokens)

Rename Database Service

Rename a database service. Only the display name changes: the service ID, endpoints, and data are untouched, so existing connections and connection strings keep working.

Input parameters:

- `name` (string, required): The new name for the service.
- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs.

Output parameters:

- `message` (string): Human-readable result of the rename operation
- `name` (string): Name of the service as stored after the rename
- `service_id` (string): Unique identifier of the renamed service, unchanged by the rename

### `service_resize` (~149 tokens)

Resize Database Service

Resize a database service by changing its CPU and memory allocation.

This tool changes the compute resources allocated to your database service. The service
may be temporarily unavailable during the resize operation.

WARNING: Creates billable resource changes. Increasing resources will increase costs.

Input parameters:

- `cpu_memory` (string, required): CPU and memory allocation combination.
- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs.
- `wait` (boolean): Whether to wait for the service to be done resizing before returning. Default is false (recommended). Only set to true if your next steps require connecting to or querying this database. When true, w…

Output parameters:

- `message` (string)
- `resources` (null|object)
- `status` (string): Current service status after resize operation

### `service_start` (~121 tokens)

Start Database Service

Start a stopped database service.

This operation starts a service that is currently in a stopped/paused state. The service will transition to a ready state and become available for connections.

Input parameters:

- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs.
- `wait` (boolean): Whether to wait for the service to be fully started before returning. Default is false (recommended). Only set to true if your next steps require connecting to or querying this database. When true, w…

Output parameters:

- `message` (string)
- `status` (string): Current service status after start operation

### `service_stop` (~119 tokens)

Stop Database Service

Stop a running database service.

This operation stops a service that is currently running. The service will transition to a stopped/paused state and will no longer accept connections.

Input parameters:

- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs.
- `wait` (boolean): Whether to wait for the service to be fully stopped before returning. Default is false (recommended). Only set to true if your next steps require confirmation that the service is stopped. When true,…

Output parameters:

- `message` (string)
- `status` (string): Current service status after stop operation

### `service_update_password` (~250 tokens)

Update Service Password

Update the master password for the 'tsdbadmin' user of a database service.

The tool generates a secure random password itself; it does not accept one. The change takes effect immediately and may terminate existing connections, and applications using the old password fail to authenticate until they are updated. The new password is saved to the configured password storage and is included in the result only if with_password is true.

If the user wants to set a specific password, tell them to run 'tiger service update-password' from the CLI instead, which keeps the password out of this conversation.

Updating the password of a service tagged PROD automatically prompts the user, via an elicitation request through the MCP client, to confirm the update before it proceeds, so agents don't need to ask the user for confirmation themselves; if the client cannot prompt, the update is refused and the user must run 'tiger service update-password' from the CLI instead.

Input parameters:

- `service_id` (string, required): Unique identifier of the service (10-character alphanumeric string). Use service_list to find service IDs.
- `with_password` (boolean): Whether to include the password in the response. NEVER set to true unless the user explicitly asks for the password.

Output parameters:

- `message` (string): Human-readable outcome of the operation
- `password` (string): The new password for the tsdbadmin user (only included if with_password=true)
- `password_storage` (null|object): Where the new password was saved locally, and whether saving it succeeded
- `updated` (boolean): Whether the password was updated. False when the user declined the confirmation prompt for a PROD service; do not retry unless the user asks again.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/timescale-tiger-cli/ghcr-io-timescale-tiger-cli#diagnostics

## Score history

- 2026-11-04: 50
- 2026-11-03: 50
- 2026-11-02: 50
- 2026-11-01: 50
- 2026-10-31: 50
- 2026-10-30: 50
- 2026-10-29: 49
- 2026-10-28: 49
- 2026-10-27: 48
- 2026-10-26: 48
- 2026-10-25: 47
- 2026-10-24: 47
- 2026-10-23: 47
- 2026-10-22: 46
- 2026-10-21: 46
- 2026-10-20: 45
- 2026-10-19: 45
- 2026-10-18: 44
- 2026-10-17: 44
- 2026-10-16: 43
- 2026-10-15: 43
- 2026-10-14: 42
- 2026-10-13: 42
- 2026-10-12: 36
- 2026-10-10: 36
- 2026-10-09: 36
- 2026-10-04: 36
- 2026-10-03: 36
- 2026-10-02: 36
- 2026-10-01: 36

## Common questions

### What is the Tiger MCP server?

Tiger MCP is listed in the public MCP registry as io.github.timescale/tiger-cli. Provides programmatic access to Tiger Cloud services, databases, and documentation. This page covers its container image (ghcr.io/timescale/tiger-cli).

### Is the Tiger MCP server safe to use?

Tiger MCP scores 50 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Tiger MCP server expose?

Tiger MCP exposes 18 tools: db_extensions_list, db_query, db_schema, feedback, service_create, and 13 more. Their descriptions and schemas cost roughly 3,898 tokens of context every time the server is loaded.

### Is the Tiger MCP server still maintained?

Tiger MCP is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- GitHub Container Registry: https://ghcr.io/timescale/tiger-cli
- Repository: https://github.com/timescale/tiger-cli
- Changelog RSS feed: https://verifymcp.io/servers/timescale-tiger-cli/ghcr-io-timescale-tiger-cli.xml
- Changelog JSON feed: https://verifymcp.io/servers/timescale-tiger-cli/ghcr-io-timescale-tiger-cli.json
- HTML version of this page: https://verifymcp.io/servers/timescale-tiger-cli/ghcr-io-timescale-tiger-cli