> For a complete page index, fetch https://docs.synthflow.ai/llms.txt. For full documentation content, fetch https://docs.synthflow.ai/llms-full.txt.

# Claude Code

> Connect Claude Code to the Synthflow MCP server to manage agents, calls, and knowledge bases from Claude Code.

![Synthflow AI Claude Code connector](https://storage.googleapis.com/granular-changelog/doc-images/claude_cover.svg)

The Claude Code connector lets you work with your Synthflow workspace directly from Claude Code. It connects Claude Code to the Synthflow MCP server, so you can create and manage agents, place and review calls, build knowledge bases, and run actions without leaving the tool you already use.

This is a good fit when your workflow lives in Claude Code and you want to manage Synthflow with natural-language prompts. If you prefer in-dashboard assistance with Memory, Learnings, and UI cards, use [Aurora](/aurora) instead. For the full list of available tools, see the [capabilities table](/aurora#capabilities).

## Setup instructions

You need a Synthflow [API key](/authentication). The Claude Code connector uses the Synthflow MCP server at:

* **URL**: `https://mcp.synthflow.ai/mcp`
* **Header**: `Authorization: Bearer <SYNTHFLOW_API_KEY>`

Type this prompt into Claude Code and let it add the server for you:

Add the Synthflow MCP server to Claude Code over HTTP transport by running this command, replacing `<SYNTHFLOW_API_KEY>` with my Synthflow API key:

`claude mcp add --transport http synthflow https://mcp.synthflow.ai/mcp --header "Authorization: Bearer <SYNTHFLOW_API_KEY>"`

![How to add the Synthflow MCP server in Claude Code](https://storage.googleapis.com/granular-changelog/doc-gifs/claude_mcp_how_to_compressed.gif)

## Example prompts

| Example prompt                                                                  |
| :------------------------------------------------------------------------------ |
| List my agents and summarize what each one does.                                |
| Create a new inbound sales qualification agent and publish it.                  |
| Show me the last 20 calls and flag any with negative sentiment.                 |
| Create a knowledge base from these sources, then attach it to my support agent. |
| Run a simulation where a prospect asks about pricing and implementation time.   |

## Security considerations

Connecting an LLM to operational tools introduces new risks. The primary risk class unique to LLM workflows is **prompt injection**: untrusted content (like call transcripts, user messages, or knowledge base documents) can include instructions that try to trick the model into taking unintended actions. Most clients support **confirm before running tools**. Keep that enabled and review tool calls carefully.

## FAQ

[Aurora](/aurora) is the in-dashboard agent: one chat thread in the Synthflow UI with Memory, Learnings, and rich UI cards. The Claude Code connector runs in Claude Code and authenticates with an API key. Both can manage agents, calls, and knowledge bases.

[MCP Connectors](/mcp-actions) let a **voice agent** call tools on an **external** MCP server during a live call. The Claude Code connector is the opposite direction: an **AI agent in Claude Code** calls tools to manage **your Synthflow workspace**.

Use the same API key you would use for REST. Generate and manage keys in **Admin** → **Workspace Settings** → **API Keys**. See [Authentication](/authentication) for setup and key-management practices.

The Claude Code connector operates within your own Claude Code account, so model and subscription charges are billed directly by Claude according to your plan. Synthflow bills only for the workspace usage your actions generate, such as calls, under your existing Synthflow plan.