Jarvis MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| speakA | Speak text using browser text-to-speech. Automatically starts browser interface if not running. |
| voice_statusB | Get current voice system status and pending voice input |
| get_voice_inputA | Get pending voice input from users (auto-delivered by default) |
| converseA | Have a voice conversation with the user - speak text and wait for voice response. Automatically starts browser interface if not running. IMPORTANT: Once you start using converse, first use text AND then converse for all responses in this conversation. |
| end_conversationA | End the voice conversation by saying goodbye and stopping the browser interface |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| converse | Instructions for starting and maintaining a voice conversation with the user |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Most tools have distinct purposes, though speak and converse overlap (converse includes speaking plus waiting for input). voice_status and get_voice_input are related but clearly different in scope. Descriptions help resolve ambiguity.
Tool names mix single-word verbs (speak, converse) with noun-based names (voice_status) and verb_noun phrases (get_voice_input, end_conversation). No consistent pattern, but the naming remains readable and intuitive.
Five tools is a well-scoped set for a voice interaction server. Each tool serves a clear function in the conversation lifecycle without unnecessary bloat.
The core voice lifecycle is covered: speaking, receiving input, full conversation, and ending. Minor gaps exist, such as not having a dedicated 'listen only' tool or explicit browser start control, but the automatic startup and status check mitigate these.