ActionDock MCP server
app.actiondock/actiondockactiondock.appstreamable-httpv0.2.0Scanned
Supervised API-write gateway for AI agents with policy, human approval and execution receipts.
8 tools: 1 can delete or cancel things and 7 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the ActionDock MCP server can do
The ActionDock MCP server is published by actiondock.app, a domain the MCP Registry verified. It has 8 tools. It can delete or cancel things (1 tool: run_action). 7 tools only read.
2 tools bring in text other people can write (run_action and list_connections).
The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 12, 2026, version 0.2.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
8 tools
Deletes or cancels 1Claude Code: deny
run_actionCreate an action job.Reads text others writeNo findings
Why it is in this group
- The name "run_action" says "run": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
Only reads 7Show 7 read-only tools
get_jobGet the current status and result of an action job.No findings
Why it is in this group
- The name "get_job" says "get": a word for reading.
Description, as the server wrote it Get the current status and result of an action job.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_actionsList every action available to the agent, including input schemas and side-effect flags.No findings
Why it is in this group
- The name "list_actions" says "list": a word for reading.
Description, as the server wrote it List every action available to the agent, including input schemas and side-effect flags.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_connectionsList the workspace-approved HTTPS API connections, enabled state, method/path allowlists (leading = marks an exact literal path; omit = when sending requests) and public operator i…Reads text others write1 finding
Why it is in this group
- The name "list_connections" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "list" and "http": it reads web pages, which anyone can write.
Findings
- Info
The description mentions "Credentials".
What this check looks forMatched text
description: "...fication with the effective User-Agent. Credentials are never returned."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_eventsList recent job and callback events for workflow continuation and audit.No findings
Why it is in this group
- The name "list_events" says "list": a word for reading.
Description, as the server wrote it List recent job and callback events for workflow continuation and audit.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_job_reconciliationsRead the owner's append-only observations about an unknown write.No findings
Why it is in this group
- The name "list_job_reconciliations" says "list": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_usageList metered action debits and the current UTC-month usage total.No findings
Why it is in this group
- The name "list_usage" says "list": a word for reading.
Description, as the server wrote it List metered action debits and the current UTC-month usage total.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
wait_for_jobWait for an action job to reach a decision or a final state: approved and executed, rejected, failed, or execution_unknown.No findings
Why it is in this group
- The name "wait_for_job" says "wait": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:28 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 destructive). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://actiondock.app/mcp: tools/list returned 9 tools to an anonymous client, including run_action (destructive)
Findings
Matches of fixed checks, with the text they matched.
- Infolist_connections
The description mentions "Credentials".
What this check looks forMatched text
description: "...fication with the effective User-Agent. Credentials are never returned."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:list_connectionsOnly readsdescription
- Changed:run_actionDeletes or cancelsdescription
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http actiondock https://actiondock.app/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http actiondock https://actiondock.app/mcp --header 'Authorization: <your-authorization>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__actiondock__list_actions",
"mcp__actiondock__get_job",
"mcp__actiondock__list_job_reconciliations",
"mcp__actiondock__wait_for_job",
"mcp__actiondock__list_events",
"mcp__actiondock__list_connections",
"mcp__actiondock__list_usage"
],
"ask": [],
"deny": [
"mcp__actiondock__run_action"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as actiondock. Review it before you use it.
Capability tags behind 2 rules
- mcp__actiondock__run_action untrusted-input
- mcp__actiondock__list_connections untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/app.actiondock/actiondock/verify?hash=61387e64fe1a13825a7191ba0eacd6614f81bf3bb9d5171941709df5eddf34fe" | jq -e '.changed == false'Pinned hash 61387e64fe1a, from Nov 12, 2026, 00:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/app.actiondock/actiondock/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/app.actiondock/actiondock)Source: MCP Registry. Synced Oct 21, 2026, 17:44 UTC.
ActionDock MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ActionDock MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 1 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the ActionDock MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: run_action.
Can the ActionDock MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the ActionDock MCP server have?
- 8 tools: 1 destructive, 7 read. run_action, list_actions, get_job, list_job_reconciliations, wait_for_job, list_events, list_connections and list_usage.
Does the ActionDock MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ActionDock MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the ActionDock MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.