Vocenya Docs
com.vocenyav1.0.0Updated Oct 5, 2026
Read-only search over the Vocenya AI receptionist API docs and endpoints, with code samples.
Overview
Read-only search of the Vocenya AI receptionist developer documentation, returning REST endpoints and code samples.
- What it does
- This remote server exposes the Vocenya developer docs to an assistant. Tools include search_docs for guides and API endpoints, get_doc_page for a single page as Markdown, list_endpoints for REST endpoints grouped by resource with method, path, summary and required scope, and get_endpoint for one endpoint in full with parameters, request body, responses and code samples in cURL, Node, PHP and Python. It is read-only and cannot see any customer account.
- When to use it
- Use it when an assistant needs to answer questions about the Vocenya API, such as how to verify a webhook signature, which scope is needed to create a lead, or what a request body looks like. It suits developers integrating with Vocenya who want documentation and code samples without leaving the assistant.
- Requirements
- A client that supports Streamable HTTP, pointed at the Vocenya docs endpoint. No installation, account, API key or authentication is required. The public servers allow 60 requests a minute per IP address.
Installation
In SourceWeft
- Open Vocenya Docs in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"docs": {
"type": "http",
"url": "https://vocenya.com/mcp/docs"
}
}
}README
Vocenya MCP servers
[Vocenya Site on AllMCPs] [Vocenya on AllMCPs] [Vocenya Docs on AllMCPs]
Connect Claude, ChatGPT, Cursor, VS Code and other AI assistants to Vocenya, the AI receptionist for small businesses made by GH Business Solutions, and to its developer docs.
Vocenya answers phone calls and website chats 24/7, books appointments, captures leads, hands calls to trained people and places outbound AI calls with Do Not Call, consent and calling-hours checks. It runs three remote Model Context Protocol servers over Streamable HTTP. Nothing to install: point your client at a URL.
Full guide: https://vocenya.com/docs/mcp
The public servers allow 60 requests a minute per IP address. The platform server shares the API key's REST limit (120 requests a minute per key by default).
This repository holds the official MCP Registry entries, a Claude Code plugin and these instructions. The servers are hosted by Vocenya; their code is not here.
Tools
Vocenya Docs (no key, read-only)
Vocenya platform (OAuth or API key)
Each tool checks its own scope (the API key's, or the scopes an owner approved when connecting with OAuth), so a key with only leads:read can read leads but cannot queue calls. Test keys (vk_test_...) work on separate sample data and never ring anyone. Accounts in HIPAA mode never return transcripts, AI summaries or chat messages through MCP.
Vocenya Site (no key, read-only)
get_pricing, get_service, search_industries, get_industry, list_locations, search_articles, get_article, and the resource vocenya://llms.txt.
Authentication
- Docs and Site: none.
- Platform, OAuth (no key): clients that sign in with OAuth (Claude Code, Claude connectors, ChatGPT developer mode and others) just need the URL. The client registers itself, then an account owner signs in to Vocenya and chooses the account, live or test data, and the permissions (the same scopes as API keys). Owners see and disconnect connected apps on the Developers page: https://vocenya.com/app/developers. The server supports OAuth 2.1 authorization code with PKCE (S256) and dynamic client registration.
- Platform, API key:
Authorization: Bearer vk_live_...(orvk_test_...for test data). The account owner creates keys, each with its own scopes, on the same Developers page. Keep keys in environment variables; never paste them into a chat or commit them.
Connect
Claude Code
Or install the plugin from this repository, which adds the docs server and two skills (REST API and webhooks, website live chat install):
Claude Desktop and claude.ai
Docs server: Settings > Connectors > Add custom connector, URL https://vocenya.com/mcp/docs, no authentication.
Platform server: add a custom connector with the URL https://vocenya.com/mcp/platform and sign in with your Vocenya owner account (OAuth).
Or, with an API key, through the mcp-remote bridge in claude_desktop_config.json:
Cursor
~/.cursor/mcp.json:
VS Code
.vscode/mcp.json (VS Code asks for the key once and stores it securely):
ChatGPT
Turn on developer mode, then add a custom connector with the URL https://vocenya.com/mcp/docs and no authentication. For your account data, add https://vocenya.com/mcp/platform with OAuth and sign in with your Vocenya owner account.
Any other client
Any client that supports Streamable HTTP works. For the platform server, sign in with OAuth, or send Authorization: Bearer <your key>.
Example prompts
- "Using the Vocenya docs, how do I verify a webhook signature? Show Node code."
- "Which scope do I need to create a lead, and what does the request body look like?"
- "Show the leads my AI receptionist captured this week." (platform)
- "What appointments did the AI book for next Monday?" (platform)
- "How much does Vocenya cost and how many AI minutes does each plan include?" (site)
Official MCP Registry
The files in registry/ are the entries published to the official MCP Registry under the com.vocenya namespace (com.vocenya/docs, com.vocenya/platform, com.vocenya/site).
Links
- MCP guide: https://vocenya.com/docs/mcp
- Developer docs: https://vocenya.com/docs
- API reference: https://vocenya.com/docs/reference (OpenAPI: https://vocenya.com/docs/api.json)
- Test mode: https://vocenya.com/docs/test-mode
- Docs for LLMs: https://vocenya.com/docs/llms.txt and https://vocenya.com/docs/llms-full.txt
- Pricing: https://vocenya.com/pricing
- Privacy: https://vocenya.com/privacy · Terms: https://vocenya.com/terms
Privacy
The docs and site servers are read-only and cannot see any customer account. The platform server sees only the one business account that owns the API key (or that an owner chose when connecting with OAuth), and only what the approved scopes allow. HIPAA mode is a paid add-on with a signed BAA; connecting an AI client does not make that client covered by the BAA, so only send patient data to AI tools you have your own agreements with. Full policy: https://vocenya.com/privacy
Support, security and license
- Questions and corrections: open an issue, or email [email protected]
- Security reports: see SECURITY.md
- License: MIT for the contents of this repository. The Vocenya service itself is a hosted commercial product under the Vocenya terms.
Copyright (c) 2026 DRAKB LLC dba GH Business Solutions.
Source: README.md at commit 8d0aaaa
Tools
0Version history
1- v1.0.0LatestOct 5, 2026


