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

# Bland MCP Server

> Connect Claude Code, Cursor, Codex, and any MCP client to your Bland account

The Bland MCP server lets AI coding agents work with your Bland account through natural language: place and inspect calls, build and validate pathways, manage agents, query analytics, run evals, and search the Bland docs, all without leaving your editor.

It's a remote [Model Context Protocol](https://modelcontextprotocol.io) server hosted by Bland. There's nothing to run locally: point your client at the endpoint, authenticate with your API key, and your agent has the full toolset.

```
https://api.bland.ai/v1/mcp
```

## Set up your client

<CardGroup cols={2}>
  <Card title="Claude Code" icon="terminal" href="/integrations/mcp/claude-code">
    One command, plus the Norm plugin for the full pathway-building workflow.
  </Card>

  <Card title="Cursor" icon="arrow-pointer" href="/integrations/mcp/cursor">
    One-click install link or a three-line config file.
  </Card>

  <Card title="Codex, VS Code, Windsurf & more" icon="plug" href="/integrations/mcp/other-clients">
    Claude Desktop, OpenAI Codex, VS Code, Windsurf, Gemini CLI, or raw HTTP.
  </Card>

  <Card title="Tool reference" icon="wrench" href="/integrations/mcp/tools">
    Every tool the server exposes, grouped by what it does.
  </Card>
</CardGroup>

## How it works

* **Transport:** Streamable HTTP (the current MCP standard). The server is stateless, so there are no sessions to manage and any request can hit any node.
* **Authentication:** your Bland API key in the `Authorization` header (`Bearer org_...`). The key's organization scopes every tool: an agent connected with your key sees only your org's calls, pathways, and agents. Get a key from the [dashboard](https://app.bland.ai/dashboard/settings).
* **Rate limits:** 120 requests per minute per organization.
* **Safety:** every tool is annotated read-only or destructive, so well-behaved clients ask before the agent does anything with side effects (like placing a real phone call). Mutating tools additionally require an explicit confirmation argument.

## What your agent can do

| Category           | Highlights                                                                                                                                                                         |
| ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Calls**          | Place an outbound call (`create_call`), fetch a call's transcript, recording, and summary (`get_call_log`).                                                                        |
| **Pathways**       | Compile-check a pathway graph before saving (`validate_pathway`), fetch the authoritative schema (`get_pathway_schema`), and get deep node/edge semantics (`get_pathway_context`). |
| **Agents**         | Full lifecycle for the v2 agents model: create, version, branch, publish to staging, promote to production, manage environment variables.                                          |
| **Analytics**      | Structured call-analytics queries with grouping, filters, and time ranges (`query_analytics`).                                                                                     |
| **Evals**          | List and inspect LLM judges, kick off eval runs over batches of calls.                                                                                                             |
| **Docs**           | Search and read docs.bland.ai from inside the session (`search_bland_docs`, `get_bland_doc`).                                                                                      |
| **Full API reach** | Anything not covered by a dedicated tool: `bland_api_get` for any GET endpoint, `call_bland_api` for any mutating endpoint.                                                        |

See the full [tool reference](/integrations/mcp/tools).

The server also ships MCP **prompts**: `build_pathway` and `edit_pathway` appear as slash commands in clients that support them (like Claude Code) and load Bland's pathway-authoring doctrine into the session.

## One endpoint, three MCP surfaces

Bland has three MCP-related surfaces. If you're unsure, use the first one.

| Surface                        | What it is                                             | When to use it                                      |
| ------------------------------ | ------------------------------------------------------ | --------------------------------------------------- |
| `https://api.bland.ai/v1/mcp`  | **This server.** Remote, account-scoped, full toolset. | Building on Bland with an AI agent.                 |
| `bland mcp` ([CLI](/sdks/cli)) | A local stdio server bundled with the Bland CLI.       | You already use the CLI and prefer a local process. |
| `https://docs.bland.ai/mcp`    | The docs site's own MCP (search-only, no auth).        | You only want documentation search.                 |

## Security notes

* Treat your API key like a password. Use environment variables or your client's secret storage. Never commit it to a repo.
* Tools that spend money or touch live traffic (placing calls, publishing agents) are marked destructive and confirmation-gated, but review what your agent proposes before approving.
* MCP tool results can contain untrusted content (e.g. call transcripts of real conversations). Prompt-injection-aware clients like Claude Code treat tool output as data, but keep it in mind when building your own agent loops.

## Next steps

<CardGroup cols={2}>
  <Card title="Connect Claude Code" icon="terminal" href="/integrations/mcp/claude-code">
    The fastest path, including the Norm plugin.
  </Card>

  <Card title="Send your first call" icon="phone" href="/quickstart">
    The 5-minute API quickstart.
  </Card>
</CardGroup>

Docs for agents: [llms.txt](/llms.txt)