POST
/v1/convai/mcp-servers/{mcp_server_id}/tool-configs
ElevenLabs APICreate Mcp Tool Configuration Override
- Base URL
- https://api.elevenlabs.io
- Auth
- xi-api-key: <ELEVENLABS_API_KEY>
- Last verified
- 2026-09-03 · upstream hash matched
Actions
Agents: curl -H "Accept: text/markdown" this URL
→ 212 tokens · Vary: Accept
→ 212 tokens · Vary: Accept
Critical gotchas
Authentication uses the non-standard xi-api-key header, not Authorization: Bearer. Sending a Bearer token returns HTTP 401.
Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (--output speech.mp3) rather than parsing it.
cURL
curl -X POST 'https://api.elevenlabs.io/v1/convai/mcp-servers/mcp-server-id/tool-configs?environment=production' \ -H "xi-api-key: $ELEVENLABS_API_KEY" \ -H 'Content-Type: application/json' \ -d '{ "force_pre_tool_speech": true, "pre_tool_speech": "auto", "disable_interruptions": true, "interruption_mode": "allow", "tool_call_sound": "typing", "tool_call_sound_behavior": "auto", "execution_mode": "immediate", "response_timeout_secs": 0, "assignments": [ { "dynamic_variable": "user_name", "preserve_native_type": false, "sanitize": false, "source": "response", "value_path": "user.name" } ], "input_overrides": {}, "response_mocks": [ { "parameter_conditions": [ { "eval": { "type": "[recursive or deeply nested schema]", "description": "[recursive or deeply nested schema]" }, "path": "string" } ], "mock_result": "string", "is_error": false } ], "tool_name": "string"}'Get a free ElevenLabs API key → sponsored
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| mcp_server_id | path | string | Yes | ID of the MCP Server. |
| environment | query | string | No | Environment whose values are used when the MCP server URL, headers, or auth connection reference environment variables. Mirrors the environment a conversation would run in; defaults to production. |
| force_pre_tool_speech | body | boolean | No | DEPRECATED: use `pre_tool_speech` instead. If set, overrides the server's force_pre_tool_speech setting for this tool. |
| pre_tool_speech | body | string | No | If set, overrides the server's pre_tool_speech setting for this tool. |
| disable_interruptions | body | boolean | No | DEPRECATED: use `interruption_mode` instead. If set, overrides the server's disable_interruptions setting for this tool. |
| interruption_mode | body | string | No | If set, overrides the server's interruption_mode setting for this tool. |
| tool_call_sound | body | string | No | Overrides the server's tool_call_sound setting for this tool. A sound name plays that sound; 'off' overrides to no sound (silence); null means do not override (inherit the server default). |
| tool_call_sound_behavior | body | string | No | If set, overrides the server's tool_call_sound_behavior setting for this tool |
| execution_mode | body | string | No | If set, overrides the server's execution_mode setting for this tool |
| response_timeout_secs | body | integer | No | If set, overrides the server's response timeout for this MCP tool. |
| assignments | body | object[] | No | Dynamic variable assignments for this MCP tool |
| input_overrides | body | object | No | Mapping of json path to input override configuration |
| response_mocks | body | object[] | No | Mock responses with optional parameter conditions. Evaluated top-to-bottom; first match wins. |
| tool_name | body | string | Yes | The name of the MCP tool |
Response 200 OK
{
"id": "string",
"config": {
"approval_policy": "require_approval_all",
"tool_approval_hashes": [
{
"tool_name": "string",
"tool_hash": "string",
"approval_policy": "requires_approval"
}
],
"transport": "SSE",
"url": "string",
"secret_token": {
"secret_id": "string"
},
"request_headers": {},
"request_meta": {},
"auth_connection": {
"auth_connection_id": "string"
},
"name": "string",
"description": "",
"force_pre_tool_speech": false,
"pre_tool_speech": "auto",
"disable_interruptions": false,
"interruption_mode": "allow",
"tool_call_sound": "typing",
"tool_call_sound_behavior": "auto",
"execution_mode": "immediate",
"response_timeout_secs": 30,
"tool_config_overrides": [
{
"tool_name": "string",
"force_pre_tool_speech": true,
"pre_tool_speech": "auto",
"disable_interruptions": true,
"interruption_mode": "allow",
"tool_call_sound": "typing",
"tool_call_sound_behavior": "auto",
"execution_mode": "immediate",
"response_timeout_secs": 0,
"assignments": [
{
"dynamic_variable": "user_name",
"preserve_native_type": false,
"sanitize": false,
"source": "response",
"value_path": "user.name"
}
],
"input_overrides": {},
"response_mocks": [
{
"parameter_conditions": "[recursive or deeply nested schema]",
"mock_result": "[recursive or deeply nested schema]",
"is_error": "[recursive or deeply nested schema]"
}
]
}
],
"disable_compression": false
},
"access_info": {
"access_source": "creator",
"creator_email": "john.doe@example.com",
"creator_name": "John Doe",
"is_creator": true,
"role": "admin"
},
"dependent_agents": [
{
"referenced_resource_ids": [
"string"
],
"id": "string",
"name": "string",
"type": "available",
"created_at_unix_secs": 0,
"access_level": "admin"
}
],
"metadata": {
"created_at": 0,
"owner_user_id": "string"
}
}