net_doctor
Deep internet-connectivity troubleshooting. Walks the whole stack in order — interface/DHCP, gateway, internet-by-IP, DNS, captive portal, HTTPS/TLS, quality, Yaver reachability — and returns the FIRST failing layer as the root cause plus plain-English remediation. Detects self-assigned IP (DHCP ...
This record as markdown: /tools/io-github-kivanccakmak-yaver/net-doctor.md
What net_doctor does on Yaver
AI agents call net_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 |
|---|---|---|---|
target | string | — | Optional host to verify end-to-end, e.g. github.com |
throughput | boolean | — | Also measure download throughput (slower). |
Parameters from the server's own tool schema.
Why net_doctor is rated Low
The tool performs diagnostic reads across network stack layers (interface, DHCP, gateway, DNS, TLS, etc.) and returns diagnostic information. It is explicitly described as a replacement for running ping/dns_lookup/wifi_info — all read-only operations. There is no indication it modifies any configuration or triggers external side effects; it only observes and reports.
From the tool's definition Deep internet-connectivity troubleshooting... returns the FIRST failing layer as the root cause plus plain-English remediation... Detects self-assigned IP, Wi-Fi vs ethernet, captive portals, and DNS-only outages
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
The rule that runs net_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 net_doctor, this is the rule to start with:
net_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 net_doctor call is checked against it from then on.
Questions about net_doctor
Deep internet-connectivity troubleshooting. Walks the whole stack in order — interface/DHCP, gateway, internet-by-IP, DNS, captive portal, HTTPS/TLS, quality, Yaver reachability — and returns the FIRST failing layer as the root cause plus plain-English remediation. Detects self-assigned IP (DHCP failure), Wi-Fi vs ethernet vs iPhone/Android hotspot, captive portals, and DNS-only outages ("connected but nothing loads"). Use this instead of running ping/dns_lookup/wifi_info one by one when asked why the internet is broken or slow. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
net_doctor accepts 2 parameters: target, throughput. 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 net_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.
net_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 net_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 net_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.
net_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