ActionDock
Server Details
Supervised API-write gateway for AI agents with policy, human approval and execution receipts.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
Most tools target clearly distinct resources or actions: the list_* family covers actions, connections, events, reconciliations, and usage, while run_action creates jobs. The only mild overlap is get_job vs wait_for_job, both reading job state, but the descriptions make the snapshot-vs-blocking distinction explicit.
Every tool follows a consistent snake_case verb_noun pattern (get_job, list_actions, run_action, wait_for_job, etc.). Verbs are used semantically — list_* for collections, get_* for single reads, run_/wait_ for operations.
Eight tools is well within the sweet spot for an approval-gated action-execution proxy. Each tool maps to a distinct concern (catalog, connections, execution, job polling, audit events, reconciliations, usage) with no filler.
The lifecycle is largely covered: discover actions, create a job, poll or wait, and audit via events, reconciliations, and usage. The notable gap is the absence of any cancel/abort tool for a pending or in-flight job, and connection inspection is read-only list-level only.
Publisher details
- Operator
- ActionDock · Publisher source
- Operator website
- https://actiondock.app
- Vendor relationship
- First-party
- Documentation
- https://actiondock.app/agents
- Trust center
- Not available
- Restrictions
- A paid workspace plan is required for tool calls (Launch $49/month and up, 14-day unconditional refund); the workspace API key is created in the ActionDock dashboard. initialize and tools/list work without a key. No OAuth; the key is sent as Authorization: Bearer or X-ActionDock-API-Key. · Publisher source
Available Tools
8 toolsget_jobGet jobBRead-onlyIdempotentInspect
Get the current status and result of an action job.
Inputs: job_id (required). Returns: id, error, input, action, +14 more
list_actionsList actionsARead-onlyIdempotentInspect
List every action available to the agent, including input schemas and side-effect flags.
Inputs: no named parameters. Returns: actions
list_connectionsList connectionsARead-onlyIdempotentInspect
List the workspace-approved HTTPS API connections, enabled state, method/path allowlists (leading = marks an exact literal path; omit = when sending requests) and public operator identification with the effective User-Agent. Credentials are never returned.
Inputs: no named parameters. Returns: connections
list_eventsList eventsARead-onlyIdempotentInspect
List recent job and callback events for workflow continuation and audit.
Inputs: limit. Returns: events
list_job_reconciliationsRead owner reconciliation evidenceARead-onlyIdempotentInspect
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.
Inputs: job_id (required), limit, before. Returns: records, nextBefore
list_usageList usageARead-onlyIdempotentInspect
List metered action debits and the current UTC-month usage total.
Inputs: limit. Returns: records, summary
run_actionSubmit action jobADestructiveInspect
Create an action job. External writes always wait for workspace-owner approval in the dashboard; share reviewUrl with the owner to open the exact job. The owner is also emailed, and wait_for_job can wait for the decision.
Inputs: action (required), input, workflow_id, workflow_name, +1 more. Returns: id, error, input, action, +14 more
wait_for_jobWait for jobARead-onlyIdempotentInspect
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.
Inputs: job_id (required), timeout_seconds. Returns: id, error, input, action, +14 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Authorize AI agent tool calls before they run: policy-as-code, human approval, signed receipts.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables controlled AI-agent access to enterprise-shaped tools with a deny-by-default gated write path, human approval, dry-run execution, and append-only audit logging.1-
- AlicenseNot gradedqualityCmaintenanceProvides a human-in-the-loop approval gateway for AI agents, enforcing policies and audit logging for MCP-compatible tool calls.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables MCP-compatible AI agents to safely act on business backends by enforcing per-agent permissions, autonomy thresholds, human approval with review-and-edit, and full audit trails.MIT
- AlicenseNot gradedqualityCmaintenanceEnables coding agents to call APIs without holding credentials by injecting keys locally, enforcing allow/deny/ask policies, holding risky calls for human approval, and recording requests.Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.