> ## Documentation Index
> Fetch the complete documentation index at: https://www.bolna.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Server

> Connect Claude, Cursor, Windsurf, or any MCP client to your Bolna account with the Bolna MCP server.

The Bolna MCP server connects your AI assistant directly to your Bolna account over the [Model Context Protocol](https://modelcontextprotocol.io). Once connected, you can list and inspect agents, pull call transcripts, check your wallet balance, create or update agents, and place real outbound calls — all from a chat window, no dashboard tab required.

It's hosted at **[mcp.bolna.ai](https://mcp.bolna.ai)** — there's nothing to install or run locally. Point your client at the URL with your API key and you're connected.

<Card title="Quickstart" icon="plug" href="/docs/build-with-ai/mcp-quickstart">
  Connect Claude, Cursor, Windsurf, Codex, Zed, or any other MCP client in under a minute
</Card>

## Who it's for

The same 11 tools serve two different ways of working — nothing about the server itself is coding-specific:

<CardGroup cols={2}>
  <Card title="Anyone on the team" icon="comments">
    Chat-only clients like **Claude Desktop** are enough. Check a wallet balance, look up an agent, pull a transcript, or fix a prompt — all in plain English, no dashboard needed.
  </Card>

  <Card title="Developers using a coding agent" icon="code">
    In **Claude Code, Cursor, or Windsurf**, the same tools ground the assistant in your real agent IDs and call data while it writes code against the [REST API](/docs/api-reference/introduction) — see the [dashboard example](/docs/build-with-ai/mcp-example-app).
  </Card>
</CardGroup>

## What you can do

<AccordionGroup>
  <Accordion title="Check on your account" icon="magnifying-glass">
    "List my agents", "what's my wallet balance?", "show me the numbers on my account" — quick lookups without opening the dashboard.
  </Accordion>

  <Accordion title="Debug a call" icon="bug">
    "Get the last 5 executions for agent X and show me the transcript for any that failed" — the assistant chains the lookups for you.
  </Accordion>

  <Accordion title="Build and change agents" icon="robot">
    "Create a Hindi lead-qualification agent using Sarvam and GPT-4o mini", "update agent X's welcome message" — describe the change, the assistant makes the API call.
  </Accordion>
</AccordionGroup>

## How it works

Your client sends your Bolna API key as a Bearer token to `https://mcp.bolna.ai/api/mcp`. The server checks the key, calls the matching [Bolna REST API](/docs/api-reference/introduction) endpoint, and hands back trimmed JSON your assistant can reason about.

```
Your client (Claude, Cursor, Windsurf...)
        │  Bearer <BOLNA_API_KEY>
        ▼
https://mcp.bolna.ai/api/mcp
        │
        ▼
https://api.bolna.ai  (agents · executions · calls · phone numbers · batches · account)
```

<Frame caption="How the Bolna MCP server connects your AI assistant to your account">
  <img src="https://mintcdn.com/bolna-54a2d4fe/TzYhw_uvJhz-N-Qn/images/changelog/mcp-diagram.svg?fit=max&auto=format&n=TzYhw_uvJhz-N-Qn&q=85&s=a957a5398c33cc73d4b4207c906fc589" alt="Diagram showing an MCP client connecting via Bearer token to mcp.bolna.ai, which calls api.bolna.ai for agents, calls, phone numbers, batches, and account" width="880" height="560" data-path="images/changelog/mcp-diagram.svg" />
</Frame>

No key is stored server-side — it travels with each request. The server is open source; see the [GitHub repo](https://github.com/bolna-ai/mcp) for the implementation.

## Confirm before it acts

`update_agent`, `delete_agent`, and `start_outbound_call` are flagged as destructive in their tool definitions. Most clients ask you to confirm before running them — `delete_agent` is irreversible, and `start_outbound_call` places a live call and spends account balance.

## Reference

<CardGroup cols={2}>
  <Card title="Tool List" icon="table-list" href="/docs/build-with-ai/mcp-tool-list">
    Every tool the server exposes, grouped by agents, calls, phone numbers, and account
  </Card>

  <Card title="Prompt Cheatsheet" icon="clipboard-list" href="/docs/build-with-ai/mcp-prompts">
    Copy-paste prompts for common tasks — works in any client, chat-only included
  </Card>
</CardGroup>

## For coding agents

<CardGroup cols={2}>
  <Card title="Example: Monitoring Dashboard" icon="gauge" href="/docs/build-with-ai/mcp-example-app">
    Requires Claude Code, Cursor, Windsurf, or another agent that can write and run files — use the MCP server to explore your data, then have it build a small dashboard around it
  </Card>

  <Card title="Bolna Skills" icon="wand-magic-sparkles" href="/docs/build-with-ai/skills">
    A code-native alternative — teaches the same operations to Claude Code, Cursor, and Codex directly, no MCP connection needed
  </Card>
</CardGroup>