calls_send_to_meet
Dispatch a workspace AI agent into an active Google Meet call. The agent joins as a participant — it can hear the conversation, respond via TTS, see the shared screen (when vision is enabled on the agent), and answer questions about what's on screen. Use when the operator wants to delegate live m...
This record as markdown: /tools/io-github-saloprj-dialogbrain/calls-send-to-meet.md
What calls_send_to_meet does on Dialogbrain
AI agents invoke calls_send_to_meet to trigger actions in Dialogbrain. 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 |
|---|---|---|---|
silent | boolean | — | Silent translator dispatch — the translator NEVER speaks into the Meet call (participants hear no bot voice); translation audio + subtitles stay available insid |
agent_id | integer | Yes | ID of an active agent in this workspace. Get it from agents.list. Any active agent can be dispatched — a voice trigger is NOT required (the runner attaches the |
meet_url | string | Yes | Canonical Google Meet URL — must match https://meet.google.com/<3 letters>-<4 letters>-<3 letters>, e.g. https://meet.google.com/abc-defg-hij. lookup/ redirects |
tts_voice | string | — | Specific voice id for tts_provider (e.g. 'alena' for yandex, 'nova' for openai). OMIT for the provider's default voice. |
vision_mode | string | — | Screen-share capture mode. 'off' = no vision (default), 'on_demand' = the agent can call the vision_query tool for fine-detail reads, 'continuous_0_3fps' = the |
instructions | string | — | What the agent should do once it joins — its task brief, e.g. 'greet everyone and present the overview deck' or 'take notes and answer questions about the roadm |
tts_provider | string | — | Translator VOICE provider (the TTS the translator speaks with): cartesia, openai, yandex, deepgram, ... Only with translation_mode=true. OMIT for the workspace |
app_languages | array | — | Extra target languages translated for the APP ONLY (shown as subtitles + listenable audio in the inbox), never spoken into the Meet call. Operators switch betwe |
comeback_phrase | string | — | Optional phrase to trigger return to original language during translation (e.g. 'Back to English'). Only used with translation_mode=true. |
source_language | string | — | Spoken language of the meeting itself (any ISO code, e.g. 'en', 'ru', 'zh'). When set, speech recognition runs in that language's dedicated mode for better accu |
target_language | string | — | PRIMARY target language spoken INTO the Meet call when translation_mode=true (e.g. 'en', 'es', 'fr'). OMIT to not use translation. |
translation_mode | boolean | — | If true, pre-arm translator mode (auto-target language) on join with zero verbal trigger. Forces the original-speaker audio track to exist. Requires target_lang |
Parameters from the server's own tool schema.
Why calls_send_to_meet is rated High
This tool triggers an external operation by sending an AI agent into a live meeting as an active participant. It has real-time effects: the agent can listen, speak via TTS, and observe screen content.
From the tool's definition Dispatch a workspace AI agent into an active Google Meet call. The agent joins as a participant — it can hear the conversation, respond via TTS, see the shared screen
Risk signalsHigh parameter count (13 properties)
Attacks that exploit this kind of access
The rule that runs calls_send_to_meet safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Dialogbrain, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For calls_send_to_meet, this is the rule to start with:
calls_send_to_meet 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 Dialogbrain, apply this rule, and every calls_send_to_meet call is checked against it from then on.
Questions about calls_send_to_meet
Dispatch a workspace AI agent into an active Google Meet call. The agent joins as a participant — it can hear the conversation, respond via TTS, see the shared screen (when vision is enabled on the agent), and answer questions about what's on screen. Use when the operator wants to delegate live meeting attendance to an agent (notes, Q&A, summarization, real-time support). The Meet URL must be in canonical 3-4-3 form, e.g. https://meet.google.com/abc-defg-hij. Lookup-redirect URLs are not supported — operator must use the share-link form. It is categorised as a Execute tool in the Dialogbrain MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
calls_send_to_meet accepts 12 parameters: silent, agent_id, meet_url, tts_voice, vision_mode, instructions, tts_provider, app_languages, comeback_phrase, source_language, target_language, translation_mode. Required: agent_id, meet_url. The full parameter table on this page comes from the server's own tool schema.
Register the Dialogbrain MCP server in PolicyLayer and add a rule for calls_send_to_meet: 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 Dialogbrain. Nothing to install.
calls_send_to_meet 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 calls_send_to_meet 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 calls_send_to_meet. 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.
calls_send_to_meet is provided by the Dialogbrain MCP server (https://api.dialogbrain.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Dialogbrain, and thousands of servers like it.
Across the catalogue