machine_doctor
Deep remote-machine connectivity doctor. For a deviceId/name/alias, checks Convex heartbeat freshness, local+target Tailscale state, raw ICMP ping per candidate, Yaver HTTP /info reachability, relay/tunnel/LAN candidate verdicts, runner auth, and CPU/RAM/disk. Use this when a remote box is online...
This record as markdown: /tools/io-github-kivanccakmak-yaver/machine-doctor.md
What machine_doctor does on Yaver
AI agents call machine_doctor to retrieve information from Yaver without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
device | string | — | Device selector alias. |
deviceId | string | — | Camel-case alias for mobile callers. |
device_id | string | — | Device ID, unique prefix, alias, or exact/partial device name. Omit or pass local for this machine. |
timeout_ms | integer | — | Per-candidate probe timeout. Default 4000. Candidates run concurrently. |
Parameters from the server's own tool schema.
Why machine_doctor is rated Low
machine_doctor is a diagnostic/monitoring tool that retrieves connectivity and system status information. It gathers data about remote machine health, network state, and availability through passive checks (heartbeats, ping responses, HTTP info endpoints) and resource queries (CPU/RAM/disk). No state changes, no deployments, no command execution occur as a result of this tool's operation.
From the tool's definition The tool 'checks' and 'reachability' — it performs diagnostic queries (heartbeat freshness, Tailscale state, ICMP ping, HTTP reachability, resource metrics) without modifying any state or executing commands on target machines.
Attacks that exploit this kind of access
The rule that runs machine_doctor safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For machine_doctor, this is the rule to start with:
machine_doctor is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every machine_doctor call is checked against it from then on.
Questions about machine_doctor
Deep remote-machine connectivity doctor. For a deviceId/name/alias, checks Convex heartbeat freshness, local+target Tailscale state, raw ICMP ping per candidate, Yaver HTTP /info reachability, relay/tunnel/LAN candidate verdicts, runner auth, and CPU/RAM/disk. Use this when a remote box is online in Convex but not reachable from PC/mobile, or when Tailscale hides a relay/free-relay failure. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
machine_doctor accepts 4 parameters: device, deviceId, device_id, timeout_ms. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for machine_doctor: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yaver. Nothing to install.
machine_doctor is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the machine_doctor rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for machine_doctor. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
machine_doctor is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
This server
Across the catalogue