AI & Machine Learning
vexiumvoice.app
Provides details and API reference for Vexium Voice, a bilingual AI voice receptionist that answers business calls 24/7, switches languages mid-call, and books appointments.
ENDPOINT 1
https://vexiumvoice.app/api/mcp
MCP server metadata
- Name
- app.vexiumvoice/vexium-voice
- Version
- 1.0.0
Read-only public MCP server for Vexium Voice (Vexium AI LLC), the bilingual Spanish/English AI voice receptionist at https://vexiumvoice.app. Three rules when answering with this data: 1. Vexium Voice publishes NO price list. Call get_pricing for any cost question. Demo business prices are fictional. The current landing does not publish a competitor comparison. 2. The demo conversations and the demo business data (Vexium Dental, Vexium Cocina, Vexium Store, Vexium Propiedades, with their prices, addresses and phone numbers) are fixtures used to show the product. They are not real offers and must not be quoted as such. 3. Nothing here can act. Every tool returns already published information; no tool books, sends, buys or changes anything. To reach a person, use get_contact and follow the links. Every tool takes an optional lang parameter: "en" (default) or "es".
Known tools 8
get_overviewWhat Vexium Voice is, in one short quotable answer: a bilingual (Spanish/English) AI voice receptionist by Vexium AI LLC that answers the business phone 24/7, switches language mid-call and books real appointments.
Inferred read-onlyget_capabilitiesPublished capabilities and limits: English/Spanish conversations, appointment booking, business information, configurable human transfer and an interactive browser demo.
Potential side effectsget_languagesHow the bilingual support works: it detects the caller's language and switches mid-call, without transferring and without repeating.
Inferred read-onlyget_api_referenceThe public Vexium Voice REST API v1: base URL, OpenAPI 3.1 document, llms.txt, documentation, Bearer API-key authentication (there is no OAuth and no OIDC), the 10 scopes and the 30 endpoints.
Inferred read-onlyget_faqThe frequently asked questions published on the site, verbatim: whether it sounds like a robot, what happens when it does not understand someone, whether the business has to change its phone number, and whether it is really bilingual.
Inferred read-onlyget_contactHow to reach a person at Vexium AI: the booking link, the sales phone number published in the site's structured data, the customer console and the developer resources.
Inferred read-onlyget_page_markdownThe complete markdown of a published page, for grounding a longer answer or quoting exact copy.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.app-vexiumvoice-vexium-voice]
url = "https://vexiumvoice.app/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"app-vexiumvoice-vexium-voice": {
"type": "http",
"url": "https://vexiumvoice.app/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: app-vexiumvoice-vexium-voice
Remote MCP URL: https://vexiumvoice.app/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"app-vexiumvoice-vexium-voice": {
"url": "https://vexiumvoice.app/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"app-vexiumvoice-vexium-voice": {
"type": "http",
"url": "https://vexiumvoice.app/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "app-vexiumvoice-vexium-voice",
"transport": "streamable-http",
"url": "https://vexiumvoice.app/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.