MCP.Market

Dashclaw MCP server

by ucsandman·io.github.ucsandman/dashclaw·v3.1.6·312 stars
No reviews yet

Policy checks, approvals, records, and governed HTTP capabilities for unattended agents.

B83/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Established

312 stars66 downloads/wk

Reviews

Write one

Nobody has reviewed Dashclaw yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Dashclaw tools (19, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • dashclaw_assumption_record

    Record an assumption you are acting on — something you treat as true but have not verified

  • dashclaw_capabilities_list

    List available capabilities registered in DashClaw. Use this to discover what external

  • dashclaw_decisions_recent

    Query the guardrail decisions ledger for recent governed actions. Filter by agent, action

  • dashclaw_guard

    Evaluate DashClaw governance policies before taking a risky action. Call this BEFORE

  • dashclaw_invoke

    Invoke a DashClaw-governed capability (external API). The capability is guarded

  • dashclaw_pair

    Enroll this agent's cryptographic identity with DashClaw (operator pairing requests

  • dashclaw_plan_status

    Check a submitted plan: overall status (pending | approved | partially_approved | denied |

  • dashclaw_plan_submitwrite action

    Submit a preflight plan — an ordered list of intended steps — for one-card operator

  • dashclaw_policies_list

    List active governance policies. Use this to understand what rules govern your actions

  • dashclaw_record

    Record a governed action in DashClaw's audit trail. Use this to log significant

  • dashclaw_session_end

    Close a DashClaw session and update its status. Call this when the task is complete

  • dashclaw_session_retro

    Fetch the per-session defensibility retro ("was I manipulated?"): injected-content flags,

  • dashclaw_session_start

    Register this agent session with DashClaw. Creates a session record that groups all

  • dashclaw_status

    Check DashClaw authoritative gate configuration and reachability.

  • dashclaw_task_createwrite action

    Create a Team Task — one record per multi-agent /team run. Groups the inter-agent

  • dashclaw_task_event

    Append one event to a Team Task timeline (delegation, reply, status, approval_needed,

  • dashclaw_task_updatewrite action

    Update a Team Task: status transitions (open → in_progress → awaiting_approval →

  • dashclaw_wait_for_approval

    Wait for a human to approve or deny a pending action in the DashClaw Approvals inbox.

  • export_dashclaw_evidence

    Export local audit entries that include DashClaw guard/evidence metadata.

Public scan report

scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it

no findings
  • Code scan36 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Dashclaw compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
83/100
higher than 65% of 48,243 servers
Tools
19
the typical server has 7
Tools that change things
16%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
312
more than 95% of 28,706 servers
Downloads a week
66
more than 51% of 12,306 servers with a package

What its tools let an agent do: 16 read · 3 change

Install Dashclaw in Claude Code, Cursor or VS Code

Runs npx -y @dashclaw/mcp-server on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add dashclaw -- npx -y @dashclaw/mcp-server
Add to Cursor

What the publisher says

From the Dashclaw repository's README, as published. We do not edit it. Read it on GitHub

DashClaw

With a supported enforcement integration, when your AI agent (OpenClaw, Hermes, Claude Code, Codex) tries something destructive or expensive, DashClaw catches it before it runs and asks you first, even when you are not at the keyboard. Every decision lands in a signed ledger.

Run agents unattended without giving them unconditional authority.

What you get  ·  What it stops  ·  The loop  ·  What it is not  ·  Quick start  ·  Connect an agent

npx dashclaw up      # no account, first caught action in minutes

AI agents: setting DashClaw up for your user? Run npx dashclaw up --yes --no-browser — the plain command prompts and will hang a non-interactive shell. The API key lands in ~/.dashclaw/instance.json; verify with GET http://localhost:3000/api/health and npx dashclaw doctor. Full runbook: dashclaw.io/llms.txt. Do not attempt the hosted trial headlessly — its captcha needs your human.

A hook-integrated agent tries a destructive tool call. DashClaw freezes it before it runs, routes it to the Approvals inbox, and writes a replayable decision record when you resolve it. This illustration shows the approval workflow. Explore the current interactive demo for the supported product surfaces.

What you get

A 10-second capability scan before the dense sections:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Dashclaw: common questions

Is Dashclaw MCP server safe?
Mostly: it is graded B (83/100). Read the Dashclaw safety report
How do I install Dashclaw?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Dashclaw need an API key?
Yes. The registry entry asks for DASHCLAW_API_KEY.
Is Dashclaw maintained?
The last commit was 22 days ago (2026-10-14). The latest release is v3.1.6.
What can I use instead of Dashclaw?
Servers from other publishers that do the same job: SSH — policy-gated remote access MCP server and Domain Liveness MCP server.
How does Dashclaw compare with other MCP servers?
safety score 83/100 (higher than 65% of 48,243 servers); tools 19 (the typical server has 7); tools that change things 16% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Dashclaw

Same job from other publishers: the closest match first, then the best rated.

  • SSH — policy-gated remote access
    Policy-gated, audited SSH for Linux and Windows hosts: roles, approvals, and an audit log.
    B
  • Domain Liveness
    Is this business's website still there? Checks apex and www, and DNS separately from HTTP.
    A