mcpbeat Sign in

Deskhand MCP Server

by grain64-deskhand Your server? Claim it
answering

Deskhand is answering right now. Last checked 4 min ago.

Hosted CRM and task desk for AI agents: per-agent keys, scopes, pause and audit log.

Uptime history 7 hours of history
7 hours agonow
100.0%
Uptime 24h
22 of 22 checks
—
Tools
hidden behind auth
149 ms
Response time
average over 24h
API key
Access
streamable-http

Nothing serious here today

Today is the operative word: we check Deskhand every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.

run in your terminal
claude mcp add deskhand --transport http https://deskhand.grain64.com/api/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "deskhand": {
      "url": "https://deskhand.grain64.com/api/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.deskhand]
url = "https://deskhand.grain64.com/api/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "deskhand": {
      "url": "https://deskhand.grain64.com/api/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "deskhand": {
      "url": "https://deskhand.grain64.com/api/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, but you need an API key from its owner to call it.

Endpoints

URLTransportStateLatencyChecked
https://deskhand.grain64.com/api/mcp streamable-http needs key 109 ms 4 min ago

Alternatives to Deskhand

same job, measured the same way
Agentvault
by bch1212

Credential vault for AI agents — Fernet-encrypted keys, per-agent budgets, audit logs.

20 installs/wk local only
Queryshield
by bch1212

Secure SQL proxy for AI agents — NL→SQL, AST safety, per-agent RLS, audit log.

72 installs/wk local only
Sandbox Env MCP
by hs3434

Persistent Docker/SSH sandbox for AI agents: shell exec, file ops, audit log.

113 installs/wk local only
agentguard — policy proxy for agent tool calls
by agentwares

Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.

7 tools answering
Holster MCP
by nautaai

Local-first secret scanning, rotation, vault, and audit-log tools for AI agents.

102 installs/wk local only
Log
by rog0x

Log parse, filter, analyze for AI agents

34 installs/wk local only
T
TrustNotch
by trustnotch

Tamper-evident audit logs for AI agents: submit, fetch, and verify cryptographic proof bundles.

86 installs/wk local only
Kakunin
by nqzai

X.509 identity, risk scoring, and audit logging for AI agents. MiCA + EU AI Act compliant.

59 installs/wk local only

Deskhand — questions

Answers built from our own checks of this server.

Why is there no tool list for Deskhand?
The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 100.0% of checks in the last 24 hours got a reply.
Is Deskhand working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 22 of 22 checks got a reply (100.0%), average response time 149 ms. The bar chart above shows every period we have measured.
How do I connect Deskhand?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You will need your own key: it refuses anonymous clients.
Does Deskhand need an API key?
Yes. Every time we knock, Deskhand answers with an authorization challenge instead of its tool list — that is how we know it is running and gated rather than broken. Bring your own credentials and it will talk.
How fast is Deskhand?
It answers our handshake in 149 ms on average, which is faster than 73% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.