Vobiz MCP Server

Official

by vobiz-ai

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

Start recording a conference

start_conference_recording

Destructive

Record a live Vobiz conference room's mixed audio in MP3 or WAV. Use when you need to capture a meeting; the recording file appears in list_recordings after the room ends.

Instructions

Start recording the mixed audio of a live Vobiz conference room (POST /Conference/{name}/Record/) in mp3 (default) or wav. Recording may require consent from every participant in your jurisdiction, so confirm with the user first (consider announcing it). Vobiz queues the recording; the reply carries no recording ID or file URL, and the file appears in list_recordings after the room ends. Stop with stop_conference_recording. Requires confirm: true. A room that is not running returns the not_found error.

Input Schema

TableJSON Schema

Name	Required	Description
`confirm`	Yes	Must be true, set only after the user explicitly asked to record this conference.
`file_format`	No	Audio format of the file: mp3 (default, smaller) or wav (uncompressed).
`conference_name`	Yes	Conference room name, exactly as used in the <Conference> XML element.

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	No	True on success; false when the result is an error (then error, message and retryable are set).
`note`	No	Where to find the file later.
`recording`	No	Always true: recording was queued.
`file_format`	No	Format that will be produced: mp3 or wav.
`http_status`	No	HTTP status Vobiz answered with (202 = accepted, 204 = done).
`backend_message`	No	Vobiz's own status message, or null.
`conference_name`	No	Room the action was applied to.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.4.2Oct 21, 2026

changedInput schema / properties / file_format / description

Previous value: -"Recording format (default mp3)."New value: +"Audio format of the file: mp3 (default, smaller) or wav (uncompressed)."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "backend_message": {
+      "description": "Vobiz's own status message, or null."
+    },
+    "conference_name": {
+      "description": "Room the action was applied to.",
+      "type": "string"
+    },
+    "file_format": {
+      "description": "Format that will be produced: mp3 or wav.",
+      "type": "string"
+    },
+    "http_status": {
+      "description": "HTTP status Vobiz answered with (202 = accepted, 204 = done).",
+      "type": "number"
+    },
+    "note": {
+      "description": "Where to find the file later.",
+      "type": "string"
+    },
+    "ok": {
+      "description": "True on success; false when the result is an error (then error, message and retryable are set).",
+      "type": "boolean"
+    },
+    "recording": {
+      "const": true,
+      "description": "Always true: recording was queued.",
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

First observedv1.1.1Oct 19, 2026

TDQS

A4.4/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare destructiveHint=true and non-idempotent, but the description adds crucial async behavior: recording is queued, the reply carries no recording ID or file URL, and the file appears in list_recordings after the room ends. It also includes legal consent guidance and the required confirm flag, which go well beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Information-dense but every sentence contributes: purpose, consent warning, async behavior, stop tool, confirm requirement, and error case. Front-loaded with the core action. Slightly long but not padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description correctly avoids detailing return values but highlights the important absence of a recording ID or file URL in the immediate reply. It covers the async lifecycle, stopping sibling, consent prerequisites, and the not_found error condition—complete for this complex operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all three parameters are fully documented in the schema (confirm must be true, file_format enum, conference_name pattern). The description reiterates formats and the confirm requirement but adds no syntax or constraints beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (start), resource (conference room recording), scope (live Vobiz conference), and format options. Distinguishes from start_recording by specifying 'conference room' and from stop_conference_recording by naming it as the stop counterpart.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear when-to-use context (live conference room) and prerequisites (consent, confirm: true). Names stop_conference_recording as the way to stop, and notes not_found error for non-running rooms. Lacks explicit comparison to start_recording for calls, but that distinction is implied by 'conference room'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server