support_start
Open a TeamViewer-style remote-support window on this machine. Returns a 6-char code, a scoped bearer token, and shareable URLs. A guest who redeems the code gets terminal / exec / file-browse access for the TTL. Revoke anytime with support_stop.
This record as markdown: /tools/io-github-kivanccakmak-yaver/support-start.md
What support_start does on Yaver
AI agents invoke support_start to trigger actions in Yaver. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
ttl | string | — | Duration string (e.g. "30m", "2h"). Default 30m. |
label | string | — | Optional tag — e.g. "cousin" or "support-ticket-1234" — shown in status. |
Parameters from the server's own tool schema.
Why support_start is rated High
This tool opens a remote-support session that gives a guest full terminal/exec/file-browse access to the host machine. While the session itself is reversible (can be stopped with support_stop), the act of granting arbitrary remote execution access to an external party represents an Execute-category action with critical blast radius: a misused or leaked 6-char code could result in complete machine compromise,…
From the tool's definition 'guest who redeems the code gets terminal / exec / file-browse access for the TTL' — grants remote terminal and execution access to an external party on the local machine
Attacks that exploit this kind of access
The rule that runs support_start 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 support_start, this is the rule to start with:
support_start stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. 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 support_start call is checked against it from then on.
Questions about support_start
Open a TeamViewer-style remote-support window on this machine. Returns a 6-char code, a scoped bearer token, and shareable URLs. A guest who redeems the code gets terminal / exec / file-browse access for the TTL. Revoke anytime with support_stop. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
support_start accepts 2 parameters: ttl, label. 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 support_start: 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.
support_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the support_start 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 support_start. 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.
support_start 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.
Across the catalogue