Use the Speak AI MCP server tool generate_voice_agent_config to run the same
prompt-to-config generation as create_voice_agent_from_prompt, but against an
existing agent instead of creating a new one.
What does it do?
Run the same prompt-to-config generation as create_voice_agent_from_prompt, but
against an existing agent instead of creating a new one. Requires the OWNER or ADMIN
role. On success the generated config is saved onto the agent immediately,
overwriting its current name, personality, instructions, chat settings, and voice,
speech-to-text, and LLM settings. If the prompt is too thin and manualInstructions
was not sent, the response has needsFollowUp: true with a follow-up question
instead. Call this again with more detail.
Parameters
generate_voice_agent_config takes 3 parameters, 2 of them required.
| Name | Type | Required | Description |
|---|---|---|---|
agentId |
string | Yes | ID of the existing voice agent to generate config for (from list_voice_agents) |
prompt |
string | Yes | Plain-English description of what the agent should do. |
manualInstructions |
string | No | Requirements the generated instructions must include. Generation still runs; when this is sent, no follow-up question is returned even if the prompt is vague. |
Behaviour
The Speak AI MCP server publishes these behaviour hints for
generate_voice_agent_config.
- Can change data in your workspace.
- Can delete or overwrite data. Use with care.
- Repeating an identical call can have an extra effect.
- Stays inside Speak AI. Does not reach other systems.
Related
- Voice agents lists the rest of the Voice agents category.
- Tool reference lists every Speak AI MCP server tool.
- MCP server covers setup, supported clients, and what agents can do once connected.