Skip to main content
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 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.

​
Set up your client

Claude Code

One command, plus the Norm plugin for the full pathway-building workflow.

Cursor

One-click install link or a three-line config file.

Codex, VS Code, Windsurf & more

Claude Desktop, OpenAI Codex, VS Code, Windsurf, Gemini CLI, or raw HTTP.

Tool reference

Every tool the server exposes, grouped by what it does.

​
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.
  • 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

See the full tool reference. 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.

​
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

Connect Claude Code

The fastest path, including the Norm plugin.

Send your first call

The 5-minute API quickstart.
Docs for agents: llms.txt