Signalby Metrics Hive
Start

MCP

Connect Claude, ChatGPT, Claude Code, Codex, Cursor, VS Code, or another AI client to Signal.

Signal serves a Model Context Protocol endpoint at https://app.signal.metricshive.com/api/mcp, so an AI client can read your visibility data and manage prompts without you copying numbers between windows. MCP access is included on every plan.

The app documents the same connection at Organization Settings → MCP: the endpoint, snippets for the common clients, and the tools it offers.

There are two ways to connect. Signing in from the client is the quickest, and the connection then acts as you, in the workspaces you belong to. An API key is for a client that can't open a browser — a container, a scheduled job — and is also how you grant a client less than your own access.

Quick Setup

add-mcp finds the AI clients installed on your machine and adds Signal to each of them:

npx add-mcp https://app.signal.metricshive.com/api/mcp --name signal

Add -g to install it for every project rather than just the current one, and -y to skip the prompt. Each client then asks you to sign in the first time it uses Signal. To set up a single client by hand, or one add-mcp doesn't cover, follow its section below.

Sign In from the Client

Give the client the URL and it opens a browser for you to sign in. There is no application to register first.

Claude Code

claude mcp add --transport http signal https://app.signal.metricshive.com/api/mcp

Then run /mcp and choose Authenticate.

Claude.ai and Claude Desktop

Custom connectors are available on every Claude plan; the Free plan is limited to one.

  1. Open Customize → Connectors, choose + Add, then Add custom connector.
  2. Name it Signal, set the URL to https://app.signal.metricshive.com/api/mcp, and choose Continue.
  3. Review the detected authentication settings, choose Continue, and choose Add.
  4. Sign in to Signal when Claude asks.

On Team and Enterprise plans, an owner adds the connector first under Organization settings → Connectors, choosing Add, then Custom → Web. Members then find it under Customize → Connectors and choose Connect.

ChatGPT

Custom MCP servers are added from ChatGPT on the web, and workspace admins can restrict them.

  1. Open Plugins, choose +, then Add custom MCP server.
  2. Name it Signal, set the server URL to https://app.signal.metricshive.com/api/mcp, and choose OAuth for authentication.
  3. Confirm the warning with I understand and want to continue, then choose Create as a plugin.
  4. Install the plugin and sign in to Signal.

Codex

codex mcp add signal --url https://app.signal.metricshive.com/api/mcp
codex mcp login signal

Cursor

Add to Cursor

Or put it in ~/.cursor/mcp.json, or .cursor/mcp.json for a single project:

{
  "mcpServers": {
    "signal": { "url": "https://app.signal.metricshive.com/api/mcp" }
  }
}

Cursor shows the server as needing login; sign in from there. Older Cursor releases send a callback Signal can't accept, so if signing in fails, use an API key instead.

VS Code

Add to VS Code

Or from a terminal:

code --add-mcp '{"name":"signal","type":"http","url":"https://app.signal.metricshive.com/api/mcp"}'

Or run MCP: Add Server from the Command Palette, choose HTTP, and enter the URL. Or put it under servers in mcp.json:

{
  "servers": {
    "signal": { "type": "http", "url": "https://app.signal.metricshive.com/api/mcp" }
  }
}

VS Code asks you to sign in the first time it starts the server.

Devin Desktop

Devin Desktop, formerly Windsurf, shares its MCP servers with Devin CLI:

devin mcp add -s user signal https://app.signal.metricshive.com/api/mcp
devin mcp login signal

Or put it in ~/.config/devin/mcp_config.json:

{
  "mcpServers": {
    "signal": { "url": "https://app.signal.metricshive.com/api/mcp" }
  }
}

Antigravity

Antigravity's IDE and CLI, which replaced Gemini CLI, read ~/.gemini/config/mcp_config.json:

{
  "mcpServers": {
    "signal": { "serverUrl": "https://app.signal.metricshive.com/api/mcp" }
  }
}

To sign in, open Agent settings → Customizations and choose Authenticate next to Signal. After signing in, Antigravity shows a code in the browser; paste it back into the settings panel and choose Submit.

OpenCode

In opencode.json, or ~/.config/opencode/opencode.json for every project:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "signal": {
      "type": "remote",
      "url": "https://app.signal.metricshive.com/api/mcp",
      "enabled": true
    }
  }
}

Then opencode mcp auth signal.

Goose

Add to Goose

Or run goose configure, choose Add Extension → Remote Extension (Streamable HTTP), and enter the URL.

Other Clients

Any client that supports remote MCP servers over Streamable HTTP with OAuth can connect: give it https://app.signal.metricshive.com/api/mcp and sign in when it asks. A client that only runs local servers can reach Signal through mcp-remote:

{
  "mcpServers": {
    "signal": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://app.signal.metricshive.com/api/mcp"]
    }
  }
}

Or Use an API Key

Issue one from Organization Settings → API Keys — keys belong to the organization, so they are not found under a brand. Issue it read-only and optionally narrow it to selected brands.

Send it as a bearer token. ChatGPT only connects by signing in; Claude.ai and Claude Desktop take the key when you add the connector: choose No sign in under Authentication and add an Authorization: Bearer signal_... request header. add-mcp takes it as a header for every client it configures:

npx add-mcp https://app.signal.metricshive.com/api/mcp --name signal \
  --header "Authorization: Bearer signal_..."

Claude Code:

claude mcp add --transport http signal https://app.signal.metricshive.com/api/mcp \
  --header "Authorization: Bearer signal_..."

Codex, which reads the key from the environment rather than the config file:

codex mcp add signal --url https://app.signal.metricshive.com/api/mcp \
  --bearer-token-env-var SIGNAL_API_KEY

Cursor, in ~/.cursor/mcp.json:

{
  "mcpServers": {
    "signal": {
      "url": "https://app.signal.metricshive.com/api/mcp",
      "headers": { "Authorization": "Bearer signal_..." }
    }
  }
}

VS Code, in mcp.json:

{
  "servers": {
    "signal": {
      "type": "http",
      "url": "https://app.signal.metricshive.com/api/mcp",
      "headers": { "Authorization": "Bearer signal_..." }
    }
  }
}

Devin Desktop and Devin CLI, in ~/.config/devin/mcp_config.json:

{
  "mcpServers": {
    "signal": {
      "url": "https://app.signal.metricshive.com/api/mcp",
      "headers": { "Authorization": "Bearer signal_..." }
    }
  }
}

Antigravity, in ~/.gemini/config/mcp_config.json:

{
  "mcpServers": {
    "signal": {
      "serverUrl": "https://app.signal.metricshive.com/api/mcp",
      "headers": { "Authorization": "Bearer signal_..." }
    }
  }
}

OpenCode, in opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "signal": {
      "type": "remote",
      "url": "https://app.signal.metricshive.com/api/mcp",
      "enabled": true,
      "headers": { "Authorization": "Bearer signal_..." }
    }
  }
}

Try

What is the visibility and share of voice for each tagged prompt in Signal for <brand>?

What are some AEO opportunities for my <brand>?

Give me an example run for my <description> prompt.

Scopes

A connection is only offered the tools its scopes allow, so a client is never shown something it would then be refused:

ScopeMCP tool
(none)whoami, list_models
readlist_brands, get_brand, list_competitors, list_prompts, list_prompt_tags, get_analytics, get_prompt_performance, get_citations, get_query_fanout, get_opportunities, list_runs, get_run, get_billing
writecreate_prompts, update_prompt

A read-write key can create and edit prompts over MCP, but no tool deletes data and no tool changes billing — deleting a prompt isn't available to API keys at all, and billing can only be changed in the app.

A connection you signed in from acts as you and reaches everything you can, so scopes are a property of a key rather than of the sign-in.

View as Markdown·Get Help