MCP Server

Build and run your AI agents from Claude Code, Cursor or VS Code

ThinnestAI is an MCP server. Connect your coding assistant with one API key and it can build voice and WhatsApp agents, connect them to your own database, test them, run your inbox and build your dashboards — and nothing reaches a customer without your approval.

Get an API key Read the MCP docs

Ask for it in plain words

Your assistant works through the ThinnestAI API, so it can do exactly what its key can do — and nothing more.

“Create a support agent for our clinic that answers in Hindi and English, and teach it from our website.”

Creates the agent, writes its instructions, adds your pages as knowledge, then test-chats it.

“Connect it to our appointments API so it can check open slots.”

Adds an action pointing at your endpoint, tests it, and asks you before switching it on.

“What did customers ask this week that the agent couldn't answer?”

Reads the agent's analytics, groups the questions, and drafts knowledge for you to approve.

“Go through the conversations waiting for my team.”

Summarises each one, suggests reply, assign, take over or resolve — and does what you decide.

“Pause the Diwali broadcast — the offer code is wrong.”

Pauses the campaign. Messages already handed to Meta still complete; resuming asks for your approval.

“Build me a dashboard of yesterday's calls and what they cost.”

Writes the code against the API with a read-only key and sets up the webhooks to keep it live.

Connect in one line

Create a key in Settings → API keys. The console shows each client's config ready to copy, under Connect an AI assistant.

Claude Code

claude mcp add --transport http thinnestai \
  https://app.thinnest.ai/api/v1/mcp \
  --header "Authorization: Bearer ta_live_YOUR_KEY"

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "thinnestai": {
      "url": "https://app.thinnest.ai/api/v1/mcp",
      "headers": { "Authorization": "Bearer ta_live_YOUR_KEY" }
    }
  }
}

VS Code, Claude Desktop and Windsurf: see the connect guide. Then ask: “List my ThinnestAI agents.”

Choose what the key can do

The MCP server only shows the assistant the tools its key may use. Start with a Build key.

Build

Recommended

Build agents, connect your API, manage contacts and webhooks, resolve and assign conversations, pause and cancel campaigns, read everything, test-chat.

Message a customer, send a code or place a call — those tools are not even offered.

Read-only

Dashboards & reports

Read conversations, calls, contacts, analytics and settings.

Change anything.

Full access

When you want it to send

Everything, including sending, calling and resuming campaigns.

Do any of those without your approval in the conversation.

Safe to hand to an assistant

Customer messages are treated as information, never as instructions — and the checks hold even when the assistant is wrong.

Nothing reaches a customer without your yes

Tools that message, call, delete or decide where customer data is sent are marked destructive, and refuse to run until the assistant confirms you approved — even in a client set to auto-approve.

The key is the boundary

The assistant can do exactly what its API key can do over the API — same checks, same limits. Revoke the key and its access ends immediately.

Nobody is contacted twice

Sending and calling tools need a retry key, so an assistant that retries after a timeout gets the first answer back instead of a second message.

See what an assistant did

Settings → API keys lists the changes assistants made through your keys, newest first, and every time one was stopped to ask — the tool and the outcome, never what it was asked.

Test the agent without leaving the editor

test_chat talks to your real agent — same instructions, model, knowledge and actions — and returns its reply with every tool it used and what went in and out.

Anything that would phone, message, email or send a code to a person, or change a booking, is switched off. The agent says what it would have done instead, so you see the behaviour and nobody is contacted.

Keep your records in your own database

Instead of uploading CSVs, give the agent small endpoints of yours — “find this order”, “check this slot”. It asks for one answer at a time, mid-conversation, and your records stay where they are. Leads, escalations and call results come back to you by webhook.

What we do keep: the conversation history, stored in India, so the agent can continue it — and what each action was called with, as an audit trail. What stays where

More than 50 tools, one API key

Everything the console does for building and running agents — grouped the way you think about your workspace.

Agents

List, create, update and delete agents; models and voices; test chat.

Knowledge

Add website pages and text an agent answers from.

Actions

Connect your own HTTPS endpoints — create, test, enable.

Contacts

Look up, add and update contacts; record events.

Conversations

Read messages, filter by status; resolve, hand back, take over, assign (paid plans).

Templates, sequences, template sends and verification codes.

Calls

Place one call or a batch, read transcripts, cancel scheduled calls.

Webhooks

Create endpoints, send a test event, read the delivery history.

Campaigns

Results of broadcasts and calling campaigns; pause, resume, cancel.

Usage & analytics

Usage and balance, agent analytics, call totals, WhatsApp cost by category.

Every tool, and which key sees it →

Ready-made prompts

Type / in Claude Code to see them. Each is a worked plan, with the points where you approve written in.

build_agentCreate an agent for your business, teach it from your website, and test it.

connect_my_databaseLet an agent look things up in your own database through your API.

weekly_reportUsage, calls, WhatsApp and each agent's results for the last 7 days.

fix_unanswered_questionsFind what the agent could not answer and draft the knowledge for it.

triage_inboxSummarise conversations waiting for a person and propose what to do.

What works today

Works now

Claude Code, Cursor and VS Code — directly
Claude Desktop, Windsurf and other local-only clients — through mcp-remote
Any MCP client that can send an Authorization header

Not yet

Connectors inside claude.ai and ChatGPT — they sign in with OAuth, which is not available yet
Creating or launching a campaign from the assistant — that stays in the console

The ThinnestAI MCP server: build and run agents from your editor Let your AI agent use your own database without uploading it Give an AI assistant a key that cannot message your customers Run your WhatsApp inbox and campaigns from Claude Code Test an AI agent from your editor without contacting a customer Five MCP prompts that run your AI agents for you Build an AI agent analytics dashboard with Claude Code See what your AI assistant did: an activity log for every key

MCP server FAQs

What is the ThinnestAI MCP server?

A Model Context Protocol server at https://app.thinnest.ai/api/v1/mcp. Connect an AI assistant such as Claude Code, Cursor or VS Code to it with a ThinnestAI API key, and the assistant can build and run your voice and WhatsApp agents through the same API your own code would use.

Which AI assistants work with it?

Claude Code, Cursor and VS Code connect directly. Claude Desktop, Windsurf and other clients that only run local servers connect through the mcp-remote bridge. Connectors inside claude.ai and ChatGPT sign in with OAuth, which is not available yet.

Can the assistant message my customers without asking?

No. Every tool that messages a customer, places a call or deletes something refuses to run until you approve it in the conversation. With a Build or Read-only key, the sending and calling tools are not available at all.

Does my data stay in my own database?

Your records do. With actions, the agent asks your API for one answer at a time instead of you uploading your data. The conversation itself passes through ThinnestAI and the AI model, and we keep the conversation history (stored in India) so the agent can continue it.

Can the assistant create and launch a WhatsApp broadcast?

Not from the MCP server. Campaigns are created and started in the console; the assistant can read their results and pause, resume or cancel them.

Does it cost extra?

No separate charge for the MCP server. What the assistant does is billed as it would be from the console or the API — calls, messages, test chats and knowledge indexing use your plan as usual.