# Bland AI — how to use (mcp.ai)

Connect your Bland AI account and use 10 tools for AI agents straight from your AI agent. Connect with your own API key. Bland AI is a conversational AI platform for building, operating, and evaluating voice agents, calls, messaging, and related communications workflows.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_bland_ai?ms=1787296080000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `bland_ai_create_pathway_folder`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/bland_ai`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/bland_ai/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/bland_ai/create/pathway/folder` — Create an empty pathway folder, optionally nested under an existing folder, without running calls or agents.
  - body: { name: string, parent_folder_id?: string }
- `POST https://api.mcp.ai/api/bland_ai/delete/pathway/folder` — Delete an empty pathway folder by ID; folders containing pathways or subfolders must be emptied first.
  - body: { folder_id: string }
- `POST https://api.mcp.ai/api/bland_ai/get/account/details` — Return the connected Bland AI account's status, call count, balance, and refill settings without changing the account.
- `POST https://api.mcp.ai/api/bland_ai/list/calls` — Search the connected account's existing inbound and outbound call history without placing or modifying calls.
  - body: { cursor?: string, inbound?: boolean, sort_by?: string, batch_id?: string, end_date?: string, timezone?: string, ascending?: boolean, completed?: boolean, to_number?: string, created_at?: string, start_date?: string, answered_by?: string, campaign_id?: string, duration_gt?: number, duration_lt?: number, from_number?: string, update_end_date?: string, update_start_date?: string }
- `POST https://api.mcp.ai/api/bland_ai/list/contacts` — Return organization contacts and their identifiers and memory records one page at a time.
  - body: { limit?: integer, cursor?: string }
- `POST https://api.mcp.ai/api/bland_ai/list/knowledge/bases` — Return one page of the connected Bland AI organization's knowledge bases, including processing status, source details, and file metadata.
  - body: { limit?: integer, cursor?: string }
- `POST https://api.mcp.ai/api/bland_ai/list/pathway/folders` — Return all pathway folders and their parent relationships from Bland's US regional pathway service.
- `POST https://api.mcp.ai/api/bland_ai/list/pathways` — Return all conversational pathways, including their names, descriptions, nodes, and edges.
- `POST https://api.mcp.ai/api/bland_ai/list/tools` — Search and page through the active or draft tools configured for Bland agents.
  - body: { limit?: integer, cursor?: string, search?: string, order_by?: string, order_direction?: string }
- `POST https://api.mcp.ai/api/bland_ai/rename/pathway/folder` — Rename an existing pathway folder without moving or changing any pathways inside it.
  - body: { name: string, folder_id: string }

## Example prompts
- "What can I do in Bland AI?"
- "Show me a summary of my Bland AI account"

## More
- Page: https://mcp.ai/bland_ai
- Agent spec (llms.txt): https://mcp.ai/bland_ai/llms.txt
- Postman collection: https://mcp.ai/bland_ai/postman.json