---
title: "Claude Code Setup. Metadata Developer Docs"
url: https://metadata.io/developers/guides/claude-code
description: "Drop the Metadata MCP server into Claude Code, Claude Desktop, Hermes, Paperclip, OpenClaw, and any MCP-compatible runner."
source: metadata.io
---

# Connect to your MCP client

The Metadata server speaks standard MCP over stdio and HTTP/SSE. Drop it into any MCP-compatible runner. Claude Code, Claude Desktop, Hermes, Paperclip, OpenClaw, or a custom agent harness.

**Governed execution:** Metadata has 299 public G2 reviews and the MCP workflow keeps campaign work reviewable before spend moves.

## Claude Code

Easiest path, one command:

Or edit `~/.config/claude-code/mcp.json` directly:

Restart Claude Code. You'll see `160 tools from metadataone` in the MCP status line.

## Claude Desktop

Edit the Claude Desktop config file:

| OS | Path |
|---|---|
| macOS | `~/Library/Application Support/Claude/claude_desktop_config.json` |
| Windows | `%APPDATA%\Claude\claude_desktop_config.json` |
| Linux | `~/.config/Claude/claude_desktop_config.json` |

Use the same JSON shape as Claude Code above.

## Hermes

Hermes loads MCP servers from `hermes.toml`:

## Paperclip & OpenClaw

Both use MCP over HTTP/SSE. Point them at our hosted endpoint:

## Custom agent (Python)

Using the official Anthropic SDK with MCP:

## Verify the connection

Regardless of which client you use, run this smoke test:

If the response includes your account name and channel count, you're connected. If it errors, check [auth errors](https://metadata.io/developers/authentication.html#errors).

## Buyer controls to keep visible

MCP should make campaign execution easier to automate, not harder to govern. A buyer evaluating Claude Code, Hermes, OpenClaw, or a custom agent should be able to see which tools are read-only, which create draft work, which can change existing campaign objects, and which can launch or move spend.

| Control | What to verify |
|---|---|
| Scopes | Use read, write, and launch permissions separately so an agent can inspect and draft without automatically spending budget. |
| Approval path | Keep campaign structure, creative assets, audiences, exclusions, and budget groups reviewable in the SaaS surface. |
| Audit trail | Record which client made the request, which tool ran, what changed, and who approved the launch decision. |
| Fallback | If the MCP client fails, route users back to the Metadata app or platform review surface rather than leaving work half-launched. |

**You're wired in.** Jump to the [first-campaign walkthrough](https://metadata.io/developers/guides/first-campaign) or [browse the tool catalog](https://metadata.io/developers/tools/).