session_intent
Classify a natural-language utterance as a session-lifecycle intent (English or Turkish) — 'start a new session', 'close the session', 'which sessions are running', 'switch to codex', 'yeni bir oturum başlat', 'tüm oturumları kapat'. Returns the parsed intent {action, runner?, sessionName?, needs...
This record as markdown: /tools/io-github-kivanccakmak-yaver/session-intent.md
What session_intent does on Yaver
AI agents call session_intent 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 |
|---|---|---|---|
text | string | Yes | The spoken or typed utterance to classify (English or Turkish). |
Parameters from the server's own tool schema.
Why session_intent is rated Low
Tool only parses and classifies text input, returning structured intent with no side effects.
From the tool's definition Classify a natural-language utterance as a session-lifecycle intent
Attacks that exploit this kind of access
The rule that runs session_intent 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 session_intent, this is the rule to start with:
session_intent 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 session_intent call is checked against it from then on.
Questions about session_intent
Classify a natural-language utterance as a session-lifecycle intent (English or Turkish) — 'start a new session', 'close the session', 'which sessions are running', 'switch to codex', 'yeni bir oturum başlat', 'tüm oturumları kapat'. Returns the parsed intent {action, runner?, sessionName?, needsChoice?, reason?} or nothing when the text is a coding prompt (which should be sent to a session via runner_turn). Use this from a voice/car/watch surface before routing speech to a runner, so lifecycle commands never get typed as prompts. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
session_intent accepts 1 parameter: text. Required: text. 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 session_intent: 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.
session_intent 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 session_intent 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 session_intent. 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.
session_intent 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