# StackQL MCP Server (oci · docker.io/stackql/stackql-mcp:0.10.582)

SQL-native query and provisioning engine for cloud infrastructure, served over MCP.

- Trust score: 35/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- mcpb · `stackql-mcp-darwin-universal.mcpb`: 5/100, [markdown](https://verifymcp.io/servers/stackql-stackql-mcp/https-github-com-stackql-stackql-releases-download-v0-10-582-stackql-mcp-darwin.md), [page](https://verifymcp.io/servers/stackql-stackql-mcp/https-github-com-stackql-stackql-releases-download-v0-10-582-stackql-mcp-darwin)
- mcpb · `linux-arm64`: 13/100, [markdown](https://verifymcp.io/servers/stackql-stackql-mcp/https-github-com-stackql-stackql-releases-download-v0-10-582-stackql-mcp-linux-a.md), [page](https://verifymcp.io/servers/stackql-stackql-mcp/https-github-com-stackql-stackql-releases-download-v0-10-582-stackql-mcp-linux-a)
- mcpb · `linux-x64`: 13/100, [markdown](https://verifymcp.io/servers/stackql-stackql-mcp/https-github-com-stackql-stackql-releases-download-v0-10-582-stackql-mcp-linux-x.md), [page](https://verifymcp.io/servers/stackql-stackql-mcp/https-github-com-stackql-stackql-releases-download-v0-10-582-stackql-mcp-linux-x)
- mcpb · `win-x64`: 13/100, [markdown](https://verifymcp.io/servers/stackql-stackql-mcp/https-github-com-stackql-stackql-releases-download-v0-10-582-stackql-mcp-windows.md), [page](https://verifymcp.io/servers/stackql-stackql-mcp/https-github-com-stackql-stackql-releases-download-v0-10-582-stackql-mcp-windows)
- npm · `@stackql/mcp-server`: 30/100, [markdown](https://verifymcp.io/servers/stackql-stackql-mcp/stackql-mcp-server.md), [page](https://verifymcp.io/servers/stackql-stackql-mcp/stackql-mcp-server)
- oci · `docker.io/stackql/stackql-mcp:0.10.582`: 35/100 (this document), [markdown](https://verifymcp.io/servers/stackql-stackql-mcp/docker-io-stackql-stackql-mcp-0-10-582.md), [page](https://verifymcp.io/servers/stackql-stackql-mcp/docker-io-stackql-stackql-mcp-0-10-582)
- pypi · `stackql-mcp-server`: 21/100, [markdown](https://verifymcp.io/servers/stackql-stackql-mcp/stackql-mcp-server-2.md), [page](https://verifymcp.io/servers/stackql-stackql-mcp/stackql-mcp-server-2)

## Channel facts

- Registry: `oci`
- Package: `docker.io/stackql/stackql-mcp:0.10.582`
- 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 2026-08-03.

- **Supply Chain Security**: 0/100
  - Malware scan not yet available for this package.
  - CVE data not yet available for this package.
  - Install-script risk not yet assessed.
  - Dependency-health data not yet available.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 75/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 5234 tokens (~261/item across 20 items; 16 tools + 4 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 39% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

**Unverified: 2 categories.** Categories scored 0 because we could not verify them: 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

### Claude

```bash
claude mcp add stackql-stackql-mcp -- docker run --rm -i docker.io/stackql/stackql-mcp:0.10.582
```

### Codex

```bash
codex mcp add stackql-stackql-mcp -- docker run --rm -i docker.io/stackql/stackql-mcp:0.10.582
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "stackql-stackql-mcp": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "docker.io/stackql/stackql-mcp:0.10.582"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  stackql-stackql-mcp:
    command: "docker"
    args: ["run", "--rm", "-i", "docker.io/stackql/stackql-mcp:0.10.582"]
```

### Other

```json
{
  "mcpServers": {
    "stackql-stackql-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "docker.io/stackql/stackql-mcp:0.10.582"
      ]
    }
  }
}
```

## 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.

### 2026-08-01 (score 35, +24)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 11)

First indexed and scored.

## MCP tools (16)

### `describe_method` (~79 tokens)

Full I/O contract for one method. Requires provider, service, resource, method.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `method` (string)
- `provider` (string)
- `resource` (string)
- `row_limit` (integer)
- `service` (string)

Output parameters:

- `rows` (array)

### `describe_resource` (~79 tokens)

Output fields for a resource's primary read method. Requires provider, service, resource.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `method` (string)
- `provider` (string)
- `resource` (string)
- `row_limit` (integer)
- `service` (string)

Output parameters:

- `rows` (array)

### `list_methods` (~85 tokens)

Access methods (HTTP operations) for a resource. Call before writing any query. Requires provider, service, resource.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `method` (string)
- `provider` (string)
- `resource` (string)
- `row_limit` (integer)
- `service` (string)

Output parameters:

- `rows` (array)

### `list_providers` (~24 tokens)

Available cloud/SaaS providers (top of the hierarchy). No inputs.

Output parameters:

- `rows` (array)

### `list_registry` (~75 tokens)

Providers (and their versions) available in the configured registry. Distinct from list_providers, which lists only providers already pulled. Optional provider arg lists versions for that provider.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `provider` (string)
- `version` (string)

Output parameters:

- `rows` (array)

### `list_resources` (~73 tokens)

Resources under a provider.service. Requires provider and service.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `method` (string)
- `provider` (string)
- `resource` (string)
- `row_limit` (integer)
- `service` (string)

Output parameters:

- `rows` (array)

### `list_services` (~70 tokens)

Services under a provider. Requires provider.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `method` (string)
- `provider` (string)
- `resource` (string)
- `row_limit` (integer)
- `service` (string)

Output parameters:

- `rows` (array)

### `pull_provider` (~81 tokens)

Install a single provider from the registry into the local approot cache. Requires provider; version is optional (latest published is pulled when empty). Writes only local cache state; no cloud control/data plane effect.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `provider` (string)
- `version` (string)

### `query_library_get` (~130 tokens)

Retrieve a query library entry by id. Without params: returns the raw template, param declarations and notes (adapt from it when no exact match exists). With params: the server validates values and returns rendered SQL plus which tool to execute it with (run_select_query or run_mutation_query). Read-only, no credentials.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `id` (string, required): query id from search results, eg aws/ec2/regions-enabled
- `params` (object): parameter values; when supplied the server validates and returns rendered SQL

Output parameters:

- `auth` (array): env vars the template's providers need resolved
- `cost` (null|object)
- `description` (string)
- `doc_url` (string)
- `errors` (array)
- `id` (string)
- `missing_params` (array)
- `mutation` (boolean)
- `next_tool` (string): run_select_query, run_mutation_query or run_lifecycle_operation
- `notes` (string)
- `outputs` (array)
- `params` (array)
- `permissions` (array): provider-native permissions or actions required to execute the template (eg iam:ListUsers)
- `related` (array): related library entry ids
- `rendered` (boolean)
- `source_tier` (string)
- `source_url` (string): citation: URL or embedded path the document was loaded from
- `sql` (string): rendered SQL, present when rendered and valid
- `stale` (boolean)
- `template` (string): raw template with {{param}} placeholders
- `title` (string)
- `unknown_params` (array)
- `valid` (boolean)
- `verb` (string): select, mutation or lifecycle

### `query_library_search` (~147 tokens)

Search the curated StackQL query library by natural-language intent. Returns ranked template ids with required param names. Consult this before composing SQL from scratch; follow up with query_library_get. Read-only, no credentials.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `include_mutations` (boolean)
- `intent` (string, required): natural language description of what the user wants
- `limit` (integer): max hits, default 5, max 20
- `provider` (string): filter by provider, eg aws
- `service` (string): filter by service, eg ec2
- `tags` (array): filter by tags

Output parameters:

- `guidance` (string): authoring guidance returned on the miss path
- `hits` (array)
- `miss` (boolean): true when no hit cleared the score threshold
- `source_tier` (string): primary, fallback or snapshot
- `source_url` (string): citation: URL or embedded path the catalogue was loaded from
- `stale` (boolean): true when served from cache or snapshot after fetch failure

### `reload_credentials` (~91 tokens)

Re-source provider credentials from the server's configured env file into the process environment, then report per-provider credential resolution status. Call after fixing or rotating credentials (eg a query failed with a credential resolution error), then retry the query. Never returns secret values. Optional provider arg scopes the report.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `provider` (string)

Output parameters:

- `env_file` (string): configured dotenv file path, empty when none configured
- `env_file_sourced` (boolean): true when the env file was found and sourced on this call
- `providers` (array)
- `sourced_vars` (array): names of environment variables set from the env file (values are never returned)

### `run_lifecycle_operation` (~84 tokens)

Execute a stackql EXEC lifecycle operation. Returns {messages, timestamp}. Gated by server mode.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `row_limit` (integer)
- `source` (string): query library id when the SQL originated from a library entry; attribution only
- `sql` (string, required)

### `run_mutation_query` (~122 tokens)

Execute INSERT/UPDATE/REPLACE/DELETE against the provider. Real side effects. Returns {messages, timestamp}. Gated by server mode. Consult query_library_search for a vetted template before composing SQL from scratch; when the SQL came from a library entry, pass its id as source.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `row_limit` (integer)
- `source` (string): query library id when the SQL originated from a library entry; attribution only
- `sql` (string, required)

### `run_select_query` (~103 tokens)

Execute a SELECT. Returns {rows}. Reads only. Consult query_library_search for a vetted template before composing SQL from scratch; when the SQL came from a library entry, pass its id as source.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `row_limit` (integer)
- `source` (string): query library id when the SQL originated from a library entry; attribution only
- `sql` (string, required)

Output parameters:

- `rows` (array)

### `server_info` (~38 tokens)

Get server identity and runtime: stackql version, backing SQL engine, provider registry location, mode, read-only flag. Call once at session start.

Output parameters:

- `build_date` (string)
- `commit` (string)
- `is_read_only` (boolean)
- `mode` (string)
- `platform` (string)
- `provider_registry` (string)
- `sql_backend` (string)
- `transport` (string)
- `version` (string)

### `validate_select_query` (~80 tokens)

Parse and plan a SELECT without executing. Returns {valid, errors}. SELECT only.

Input parameters:

- `format` (string): text content render format: markdown (default) or json
- `row_limit` (integer)
- `source` (string): query library id when the SQL originated from a library entry; attribution only
- `sql` (string, required)

Output parameters:

- `errors` (array)
- `valid` (boolean)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/stackql-stackql-mcp/docker-io-stackql-stackql-mcp-0-10-582#diagnostics

## Score history

- 2026-08-03: 35
- 2026-08-02: 35
- 2026-08-01: 35
- 2026-07-31: 11

## Links

- Repository: https://github.com/stackql/stackql
- Website: https://stackql.io/
- Changelog RSS feed: https://verifymcp.io/servers/stackql-stackql-mcp/docker-io-stackql-stackql-mcp-0-10-582/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/stackql-stackql-mcp/docker-io-stackql-stackql-mcp-0-10-582/changelog.json
- HTML version of this page: https://verifymcp.io/servers/stackql-stackql-mcp/docker-io-stackql-stackql-mcp-0-10-582