# ActionDock (remote · actiondock.app)

Supervised API-write gateway for AI agents with policy, human approval and execution receipts.

- Trust score: 77/100 (medium)
- Change this week: +41
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-24

## Components

- remote · `actiondock.app`: 77/100 (this document), [markdown](https://verifymcp.io/servers/app-actiondock-actiondock/actiondock.md), [page](https://verifymcp.io/servers/app-actiondock-actiondock/actiondock)

## Channel facts

- Endpoint: `https://actiondock.app/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-09-24.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 82/100
  - 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 1256 tokens (~139/item across 9 items; 8 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

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

ActionDock is a hosted endpoint at https://actiondock.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http app-actiondock-actiondock 'https://actiondock.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "app-actiondock-actiondock": {
      "url": "https://actiondock.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "app-actiondock-actiondock": {
      "type": "http",
      "url": "https://actiondock.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.app-actiondock-actiondock]
url = "https://actiondock.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-actiondock-actiondock": {
      "type": "remote",
      "url": "https://actiondock.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add app-actiondock-actiondock --url 'https://actiondock.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  app-actiondock-actiondock:
    url: "https://actiondock.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "app-actiondock-actiondock": {
      "Transport": "http",
      "Url": "https://actiondock.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add app-actiondock-actiondock -t streamable-http -u 'https://actiondock.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "app-actiondock-actiondock": {
      "type": "http",
      "url": "https://actiondock.app/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-09-24 (score 77, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-09-22 (score 77, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional improvement] Stability: unverified → 0.03

### 2026-09-21 (score 77, +41)

- [security regression] HSTS header: pass → fail
- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 100
- [functional] First check of Tool coverage: 100

### 2026-09-10 (score 36)

First indexed and scored.

## MCP tools (8)

### `list_actions` (~24 tokens)

List actions

List every action available to the agent, including input schemas and side-effect flags.

Output parameters:

- `actions` (array): Catalog entries with name, description, input schema, and side-effect flag.

### `run_action` (~145 tokens)

Submit action job

Create an action job. External writes always wait for workspace-owner approval in the dashboard; the owner is emailed, and wait_for_job blocks until the decision.

Input parameters:

- `action` (string, required): Catalog action name from list_actions, for example integration.execute.
- `idempotency_key` (string): Caller-chosen key; resubmitting the same key and input returns the existing job instead of creating another.
- `input` (object): Action input matching the schema advertised by list_actions.
- `workflow_id` (string): Stable identifier of the agent workflow this job belongs to, for grouping events.
- `workflow_name` (string): Human-readable workflow name shown to the workspace owner during review.

Output parameters:

- `action` (string): Catalog action name, for example integration.execute.
- `approvedAt`
- `approvedBy`: Owner who approved the write.
- `createdAt` (string): Creation time.
- `error`: Failure or execution_unknown message; null otherwise.
- `id` (string): Job identifier.
- `idempotencyKey`: Idempotency key that deduplicates this submission within the workspace.
- `input` (object): Validated action input exactly as submitted.
- `output`: While awaiting_approval: the exact approval preview bound to the owner's decision. After succeeded: the action result. After execution_unknown: the approved write plus the ambiguous provider response…
- `rejectedAt`
- `rejectedBy`: Owner who rejected the write.
- `sideEffect` (boolean): True when the action writes to an external system and therefore required owner approval.
- `status` (string): awaiting_approval, queued, and running are non-terminal; succeeded, failed, rejected, and execution_unknown are terminal.
- `updatedAt` (string): Last status change.
- `workflowId`: Caller-supplied workflow identifier shared across related jobs.
- `workflowName`: Caller-supplied workflow name shown in the dashboard.
- `workspaceId` (string): Workspace that owns the job.

### `get_job` (~33 tokens)

Get job

Get the current status and result of an action job.

Input parameters:

- `job_id` (string, required): Job identifier returned by run_action.

Output parameters:

- `action` (string): Catalog action name, for example integration.execute.
- `approvedAt`
- `approvedBy`: Owner who approved the write.
- `createdAt` (string): Creation time.
- `error`: Failure or execution_unknown message; null otherwise.
- `id` (string): Job identifier.
- `idempotencyKey`: Idempotency key that deduplicates this submission within the workspace.
- `input` (object): Validated action input exactly as submitted.
- `output`: While awaiting_approval: the exact approval preview bound to the owner's decision. After succeeded: the action result. After execution_unknown: the approved write plus the ambiguous provider response…
- `rejectedAt`
- `rejectedBy`: Owner who rejected the write.
- `sideEffect` (boolean): True when the action writes to an external system and therefore required owner approval.
- `status` (string): awaiting_approval, queued, and running are non-terminal; succeeded, failed, rejected, and execution_unknown are terminal.
- `updatedAt` (string): Last status change.
- `workflowId`: Caller-supplied workflow identifier shared across related jobs.
- `workflowName`: Caller-supplied workflow name shown in the dashboard.
- `workspaceId` (string): Workspace that owns the job.

### `list_job_reconciliations` (~95 tokens)

Read owner reconciliation evidence

Read the owner's append-only observations about an unknown write. These are owner reports, not verified provider facts, a changed job status, or permission to retry. Agents cannot record observations.

Input parameters:

- `before` (string): nextBefore from the previous page; omit for the newest observations.
- `job_id` (string, required): Job identifier returned by run_action.
- `limit` (integer): Maximum observations per page, newest first.

Output parameters:

- `nextBefore`: Pass as before to read older records; null means the end of history.
- `records` (array): Owner observations, newest first; corrections append to history.

### `wait_for_job` (~113 tokens)

Wait for job

Wait for an action job to reach a decision or a final state: approved and executed, rejected, failed, or execution_unknown. A job still awaiting owner approval when the timeout elapses is returned as awaiting_approval; call again to keep waiting. Keep timeout_seconds below your client's tool timeout.

Input parameters:

- `job_id` (string, required): Job identifier returned by run_action.
- `timeout_seconds` (integer): How long to wait for a decision or final state before returning the current job; keep it below your client's tool timeout.

Output parameters:

- `action` (string): Catalog action name, for example integration.execute.
- `approvedAt`
- `approvedBy`: Owner who approved the write.
- `createdAt` (string): Creation time.
- `error`: Failure or execution_unknown message; null otherwise.
- `id` (string): Job identifier.
- `idempotencyKey`: Idempotency key that deduplicates this submission within the workspace.
- `input` (object): Validated action input exactly as submitted.
- `output`: While awaiting_approval: the exact approval preview bound to the owner's decision. After succeeded: the action result. After execution_unknown: the approved write plus the ambiguous provider response…
- `rejectedAt`
- `rejectedBy`: Owner who rejected the write.
- `sideEffect` (boolean): True when the action writes to an external system and therefore required owner approval.
- `status` (string): awaiting_approval, queued, and running are non-terminal; succeeded, failed, rejected, and execution_unknown are terminal.
- `updatedAt` (string): Last status change.
- `workflowId`: Caller-supplied workflow identifier shared across related jobs.
- `workflowName`: Caller-supplied workflow name shown in the dashboard.
- `workspaceId` (string): Workspace that owns the job.

### `list_events` (~35 tokens)

List events

List recent job and callback events for workflow continuation and audit.

Input parameters:

- `limit` (integer): Maximum number of most recent events to return.

Output parameters:

- `events` (array): Most recent job and callback events, newest first.

### `list_connections` (~27 tokens)

List connections

List the workspace-approved HTTPS API connections and their method/path allowlists. Credentials are never returned.

Output parameters:

- `connections` (array): Workspace-approved API connections with their method and path allowlists; credentials are never included.

### `list_usage` (~38 tokens)

List usage

List metered action debits and the current UTC-month usage total.

Input parameters:

- `limit` (integer): Maximum number of most recent usage records to return.

Output parameters:

- `records` (array): Most recent metered action debits, newest first.
- `summary` (object): Current UTC-month usage total and plan limit.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/app-actiondock-actiondock/actiondock#diagnostics

## Score history

- 2026-09-24: 77
- 2026-09-23: 77
- 2026-09-22: 77
- 2026-09-21: 77
- 2026-09-20: 36
- 2026-09-19: 36
- 2026-09-18: 36
- 2026-09-17: 36
- 2026-09-16: 36
- 2026-09-15: 36
- 2026-09-14: 36
- 2026-09-13: 36
- 2026-09-12: 36
- 2026-09-11: 36
- 2026-09-10: 36

## Common questions

### What is the ActionDock MCP server?

ActionDock is an MCP server listed in the public MCP registry as app.actiondock/actiondock. Supervised API-write gateway for AI agents with policy, human approval and execution receipts. This page covers its hosted endpoint (https://actiondock.app/mcp).

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

ActionDock scores 77 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 ActionDock MCP server expose?

ActionDock exposes 8 tools: list_actions, run_action, get_job, list_job_reconciliations, wait_for_job, and 3 more. Their descriptions and schemas cost roughly 510 tokens of context every time the server is loaded.

### Does the ActionDock MCP server require authentication?

Yes. ActionDock asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the ActionDock MCP server still maintained?

ActionDock is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://actiondock.app/mcp
- Authorisation metadata: https://actiondock.app/.well-known/oauth-protected-resource/mcp
- Website: https://actiondock.app/agents
- Changelog RSS feed: https://verifymcp.io/servers/app-actiondock-actiondock/actiondock.xml
- Changelog JSON feed: https://verifymcp.io/servers/app-actiondock-actiondock/actiondock.json
- HTML version of this page: https://verifymcp.io/servers/app-actiondock-actiondock/actiondock