ActionDock MCP server

• Registry nameapp.actiondock/actiondockverified in the MCP registry

The registry name sits under actiondock.app. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-24
• Tools8
• Server calls itselfactiondock
• Server version0.2.0
• Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 167 ms.

• Its tools do every use case we checked: hold an agent's API write until an owner approves it; send approved changes to a public REST API with server-held credentials.
• Checked on 3 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
• What an agent can do with it2 of 2 use cases
• Answeredmeasuring3 of the 7 daily checks it takes to print a share
• Median first answer532 ms
• Space in an agent's context≈ 1,182 tokensthe definitions of all its tools (8), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results8 of 8 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• list_actions

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

• run_action

  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.

• get_job

  Get the current status and result of an action job.

• list_job_reconciliations

  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.

• 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…

• list_events

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

• list_connections

  List the workspace-approved HTTPS API connections, method/path allowlists and public operator identification with the effective User-Agent. Credentials are never returned.

• list_usage

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