Log inSubmit server
Dashclaw logo

Dashclaw

Govern AI agent actions with policy checks, approvals, signed decision records, and capability discovery.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Dashclaw

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "dashclaw": {
      "command": "npx",
      "args": [
        "-y",
        "dashclaw"
      ],
      "env": {
        "DASHCLAW_BASE_URL": "YOUR_VALUE_HERE",
        "DASHCLAW_API_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y dashclaw

Process exited before answering initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 13d ago.

Overview

The dashclaw MCP server connects agent tool calls to DashClaw governance for guarding, recording, invoking, and discovering capabilities. Supported enforcement seams can block destructive or expensive actions before execution, while ordinary MCP and SDK integrations rely on the caller to honor the verdict. Decisions are stored in a ledger, with remote approval available through the inbox, CLI, phone PWA, Telegram, or Discord. Reach for it when unattended coding agents need approval workflows and an auditable record of actions.

Use cases

  • Guard unattended coding-agent actions before they reach a repository or database
  • Route destructive tool calls to a remote approval inbox
  • Record agent decisions and outcomes for later review
  • Discover governed capabilities exposed to an agent

Key features

  • Pre-execution policy verdicts
  • Remote approval workflow
  • Signed decision records where issued
  • Prompt-injection scanning
  • Capability discovery and governed invocation
  • Enforcement liveness diagnostics

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

10/10 checks healthy over the last 50d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 12d ago via OSV.dev · dashclaw (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars313Stargazers on the source repository.
npm downloads784Package downloads in the last 30 days.
Last commit3d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Dashclaw works

What the dashclaw MCP server does

The dashclaw MCP server provides governance around agent capabilities and tool execution. Its core operations cover checking an action before it runs, recording the resulting decision, invoking an approved capability, and discovering available capabilities. The governance layer evaluates actions against policy, assigns a risk level, and can return an allow, warn, or block result.

At supported enforcement points, a blocked operation is stopped before the underlying tool executes. The documented enforcement paths include Claude Code, Codex, and Hermes hooks, the OpenClaw gateway, and dashclaw_invoke. Bare SDK, REST, and ordinary MCP callers are cooperative: they must follow the returned decision themselves.

The system is intended for unattended or long-running agent sessions working against real repositories and infrastructure. Examples in the project include recursive deletion, destructive database statements, force-pushing a protected branch, and attempts to extract credentials from an environment file.

How it works

An agent submits the intended action at the execution boundary. DashClaw classifies the request, checks configured policies, and reports the result before the action is carried out. High-confidence prompt-injection patterns can produce a block, while lower-confidence matches can produce a warning. The action, decision, and eventual resolution are written to a decision ledger.

Pending actions can be resolved from the /approvals inbox, CLI, phone PWA, Telegram, or Discord. Standing permissions can be created for eligible requests after reviewing their target and lease; high-risk, expired, self-approved, or otherwise ungrantable requests are rejected. Grants remain visible and can be revoked.

Decision records may include Ed25519 receipts and signed exports where the relevant evidence path issues them. A receipt verifies the signed contents, not whether an external side effect actually occurred. The system also separates authenticated identity from action-payload signing.

Setup and configuration

The documented local start command is:

Terminal
npx dashclaw up

For a non-interactive setup, use npx dashclaw up --yes --no-browser. The command stores the API key in ~/.dashclaw/instance.json. A local health check is available at GET http://localhost:3000/api/health, and npx dashclaw doctor checks the installation. The README identifies Node.js 20+ and Python 3.7+ platform support and provides both npm and PyPI packages.

SDK configuration uses a DashClaw base URL, an API key, and an agent ID. A JavaScript example passes DASHCLAW_BASE_URL and DASHCLAW_API_KEY to the client, then keeps the real effect inside a governed execution wrapper.

Tools and capabilities

The dashclaw MCP server supports these documented governance capabilities:

  • Guard an intended action and receive a policy verdict.
  • Record decisions and outcomes in a ledger.
  • Invoke a capability through the governed execution path.
  • Discover available capabilities.
  • Route pending requests for remote approval.
  • Scan for prompt-injection indicators during guarding.
  • Report enforcement liveness, runtime versions, and hook fingerprints as diagnostics.
  • Score declared agent confidence against reported outcomes.

Approval explanations lead with a plain-language description, identify potentially irreversible effects, and flag possible credential-bearing files. When policy cannot confidently interpret a command, the system reports that uncertainty instead of presenting a confident classification.

Limitations and notes

Enforcement is not universal. Hooks, the OpenClaw gateway, and dashclaw_invoke can cancel a call before execution; ordinary MCP, API, and bare SDK integrations cannot enforce the result unless their caller does so. Liveness diagnostics describe client-reported conditions and are not attestation.

Signed evidence is conditional on the eligible path issuing a receipt, and a valid receipt does not prove that an external effect happened. Hosting and provider usage may have separate plans or limits. The project is MIT licensed and can be run locally or self-hosted.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Dashclaw

dashclaw is an MCP server that connects AI agents and MCP tool calls to DashClaw governance. Its main tools guard actions, record decisions, invoke governed capabilities, and discover available capabilities. Supported hooks can block destructive or expensive calls before execution, while ordinary MCP callers must honor returned verdicts themselves.

Run `npx dashclaw up` to start a local instance. For a non-interactive shell, use `npx dashclaw up --yes --no-browser`. The API key is stored in `~/.dashclaw/instance.json`; verify the instance with the local health endpoint or `npx dashclaw doctor`.

It depends on the enforcement path. Claude Code, Codex, and Hermes hooks, the OpenClaw gateway, and `dashclaw_invoke` can cancel a blocked call before execution. Ordinary MCP, REST, and bare SDK integrations are cooperative and require the caller to enforce the returned decision.

The README names Claude Code, Codex, Hermes, and OpenClaw as supported runtimes or enforcement integrations. It also describes Node and Python SDKs, plain REST, and MCP integrations. Enforcement behavior differs by integration, so ordinary MCP and SDK callers must honor governance results themselves.

Related MCP servers

All in Developer Tools All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewDashclaw AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/dashclaw?style=directory)](https://allmcps.com/mcp/dashclaw)
HTML Embed
<a href="https://allmcps.com/mcp/dashclaw"><img src="https://allmcps.com/api/badge/dashclaw?style=directory" alt="Dashclaw on AllMCPs" /></a>