Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Read-only search over the Vocenya AI receptionist API docs and endpoints, with code samples.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://vocenya.com/mcp/docsRun this in your terminal
claude mcp add --transport http docs https://vocenya.com/mcp/docsPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"docs": {
"url": "https://vocenya.com/mcp/docs"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"docs": {
"type": "http",
"url": "https://vocenya.com/mcp/docs"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://vocenya.com/mcp/docsMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified against the domain vocenya.com (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.0.0) reached the registry 33 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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
| Server | URL | Auth | What it does |
|---|---|---|---|
| Vocenya Docs | https://vocenya.com/mcp/docs | None | Search the Vocenya developer docs and get every REST endpoint with code samples. Read-only. |
| Vocenya (platform) | https://vocenya.com/mcp/platform | OAuth or API key | One business account's calls, leads, bookings and chats; add leads, queue outbound AI calls, update the Do Not Call list. |
| Vocenya Site | https://vocenya.com/mcp/site | None | Answers about Vocenya itself from vocenya.com: plans and prices, products, industries, locations, guides. Read-only. |
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.
| Tool | What it does |
|---|---|
search_docs | Search guides (authentication, webhooks, pagination, outbound calling rules, live chat, MCP) and every API endpoint. |
get_doc_page | One docs page as Markdown, for example quickstart, webhooks or reference/leads. |
list_endpoints | REST endpoints with method, path, summary and required scope, grouped by resource. |
get_endpoint | One endpoint in full: scope, parameters, request body, responses and code samples in cURL, Node, PHP and Python. |
| Tool | Scope | What it does |
|---|---|---|
list_calls | calls:read | Calls handled by the AI, GH Live agents or the team, newest first. |
get_call | calls:read | One call with its leads; AI summary and transcript unless the account is in HIPAA mode. |
list_leads | leads:read | Leads from calls, chats and forms. |
get_lead | leads:read | One lead with contact details, reason, urgency and source. |
create_lead | leads:write (+ outbound:write for an AI callback) | Add a lead from another system; optionally ask the AI to call back. |
list_bookings | bookings:read | Appointments the AI booked into the business calendar. |
list_chats | chats:read | Website live chat conversations. |
queue_outbound_call | outbound:write | Ask the AI to call someone who consented. Compliance is checked first; refusals return the reason. |
add_do_not_call | dnc:write | Add a number to the business's Do Not Call list. |
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.
get_pricing, get_service, search_industries, get_industry, list_locations, search_articles, get_article, and the resource vocenya://llms.txt.
Authorization: Bearer vk_live_... (or vk_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.# Docs (no key)
claude mcp add --transport http vocenya-docs https://vocenya.com/mcp/docs
claude mcp add --transport http vocenya https://vocenya.com/mcp/platform
claude mcp add --transport http vocenya https://vocenya.com/mcp/platform \ --header "Authorization: Bearer $VOCENYA_API_KEY"
Or install the plugin from this repository, which adds the docs server and two skills (REST API and webhooks, website live chat install):
claude plugin marketplace add gadyamedia/vocenya-mcp
claude plugin install vocenya@vocenya
Docs server: Settings > Connectors > Add custom connector, URL https://vocenya.com/mcp/docs, no authentication.
Platform server: add a custom connector with the URL https://vocenya.com/mcp/platform and sign in with your Vocenya owner account (OAuth).
Or, with an API key, through the mcp-remote bridge in claude_desktop_config.json:
{
"mcpServers": { "vocenya": { "command": "npx", "args": [ "-y", "mcp-remote", "https://vocenya.com/mcp/platform", "--header", "Authorization:${VOCENYA_AUTH}" ], "env": { "VOCENYA_AUTH": "Bearer paste-your-key-here" } } } }
~/.cursor/mcp.json:
{
"mcpServers": { "vocenya-docs": { "url": "https://vocenya.com/mcp/docs" }, "vocenya": { "url": "https://vocenya.com/mcp/platform", "headers": { "Authorization": "Bearer ${env:VOCENYA_API_KEY}" } } } }
.vscode/mcp.json (VS Code asks for the key once and stores it securely):
{
"inputs": [ { "type": "promptString", "id": "vocenya-key", "description": "Vocenya API key (vk_live_... or vk_test_...)", "password": true } ], "servers": { "vocenya-docs": { "type": "http", "url": "https://vocenya.com/mcp/docs" }, "vocenya": { "type": "http", "url": "https://vocenya.com/mcp/platform", "headers": { "Authorization": "Bearer ${input:vocenya-key}" } } } }
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.
On Grok Business and Enterprise, add https://vocenya.com/mcp/platform as a custom MCP connector ("Bring your own MCP") and sign in with OAuth, or use an API key with read scopes only. The plugins/vocenya-grok folder packages both servers with a daily front-desk review skill for a Grok Bot: it summarizes calls, chats and leads and drafts follow-ups, and never contacts a customer without approval.
Any client that supports Streamable HTTP works. For the platform server, sign in with OAuth, or send Authorization: Bearer .
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).
The docs and site servers are read-only and ca
Only the beginning is shown; read the rest in the repo