Antenna MCP
Antenna provides a Model Context Protocol (MCP) server that lets AI assistants and agents query your engineering metrics directly. Use natural language prompts to explore contributor productivity, AI tool adoption, team trends, and more.
The MCP server exposes read-only tools scoped to your enterprise. All requests are authenticated with an Enterprise Access Token and return structured JSON responses.
Example Prompts
Once connected, you can ask your AI assistant natural language questions. The assistant will automatically select and call the appropriate MCP tools.
- “Who is spending the most on AI?”
- “Who used AI the most and least efficiently over the last 6 months?”
- “How can my team optimize AI spending?”
- “Whose PRs are taking the longest to be reviewed? Is there a correlation with PR size?”
- “Looking at the last 6 months, what are the biggest opportunities for improvement on my team?”
Prerequisites
- An Antenna enterprise account with the MCP feature enabled
- An Enterprise Access Token (generated in Settings > Access Tokens)
Generate an access token
- Sign in to app.antenna.dev as an enterprise admin.
- Go to your enterprise Settings > Access Tokens.
- Click Create token, give it a description (e.g., “MCP Server”), and copy the token.
The token is shown only once. Store it securely — you will need it for each MCP client configuration below.
Available Tools
The MCP server exposes the following read-only tools:
| Tool | Description |
|---|---|
contributor_metric_fields | Describe available metric fields, sort fields, date granularities, and result limits. |
enterprise_identity_groups | List identity groups (teams) available for filtering contributor metrics. |
enterprise_identity_search | Search enterprise identities by display name, username, email, or external account ID. |
contributor_metrics_list | Return contributor metrics for an enterprise over a bounded date range. |
contributor_metrics_trends | Return per-period contributor metrics for selected enterprise identities. |
Setup
The Antenna MCP server uses the Streamable HTTP transport. The endpoint is:
https://app.antenna.dev/api/mcp/enterpriseAll requests require an Authorization header with your enterprise access token:
Authorization: Bearer YOUR_ACCESS_TOKENJump to setup:
- Augment Code
- ChatGPT and Codex
- Claude Desktop and Claude Code
- Claude on AWS Bedrock
- Cursor
- Devin
- GitHub Copilot
- Kiro
Augment Code
Augment Code supports remote MCP servers through its Settings Panel by importing a JSON configuration.
Open the Augment Settings Panel
In the Augment panel (VS Code, JetBrains, or another supported editor), open the options menu in the upper right and click Settings. Scroll to the MCP servers section.
Add the Antenna server
Click Import from JSON and paste:
{
"mcpServers": {
"antenna": {
"type": "http",
"url": "https://app.antenna.dev/api/mcp/enterprise",
"headers": {
"Authorization": "Bearer YOUR_ACCESS_TOKEN"
}
}
}
}Verify the connection
The Antenna server appears in the MCP servers list. Start an Agent conversation and ask a question like “Who is spending the most on AI?” to confirm Augment can call the Antenna tools.
ChatGPT and Codex
The ChatGPT and Codex desktop apps, as well as the Codex CLI, share MCP configuration. You can add Antenna directly in the desktop app or by editing config.toml. For full OpenAI reference details, see the ChatGPT MCP documentation .
Antenna does not currently support the ChatGPT web app. Use the ChatGPT desktop app or Codex instead.
Open MCP settings
In the desktop app, go to Settings > Plugins > MCPs, then choose Add server.
Configure the server
Enter the following:
- Name:
Antenna - Type: Streamable HTTP
- URL:
https://app.antenna.dev/api/mcp/enterprise - Headers: Add a header with Key
Authorizationand ValueBearer YOUR_ACCESS_TOKEN
Save and verify
Click Save, then restart if prompted. In the composer, type /mcp to confirm Antenna is connected. Ask a question like “Who is spending the most on AI?” to verify the tools work.
Alternatively, add the server in ~/.codex/config.toml (or a project-scoped .codex/config.toml for trusted projects):
[mcp_servers.antenna]
url = "https://app.antenna.dev/api/mcp/enterprise"
http_headers = { "Authorization" = "Bearer YOUR_ACCESS_TOKEN" }The same config.toml is used by the ChatGPT and Codex desktop apps and Codex CLI, so you only need to configure Antenna once.
Claude Desktop and Claude Code
You can connect the Antenna MCP to the Claude desktop app or to Claude Code. Both use the same endpoint and access token.
The Claude desktop app configures MCP servers in claude_desktop_config.json. This setup uses mcp-remote via npx, so Node.js must be installed.
Open Claude settings
Open the Claude desktop app, go to Settings, and open the Developer tab.
Add the MCP server configuration
Click Edit Config to open claude_desktop_config.json. Add an entry under the mcpServers key:
{
"mcpServers": {
"antenna": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://app.antenna.dev/api/mcp/enterprise",
"--transport",
"http-only",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer YOUR_ACCESS_TOKEN"
}
}
}
}Restart and verify
Restart Claude for the changes to take effect. Ask Claude to list available Antenna tools, or try a question like “Who is spending the most on AI?” to confirm the connection.
Claude Code configures MCP servers from the terminal.
Add the Antenna server
In your terminal, run:
claude mcp add --transport http antenna \
https://app.antenna.dev/api/mcp/enterprise \
--header "Authorization: Bearer YOUR_ACCESS_TOKEN"Verify the connection
Confirm the server is registered:
claude mcp listThen start a conversation with claude and ask a question like “Who is spending the most on AI?” to verify the tools work.
Claude on AWS Bedrock
When using Claude via AWS Bedrock with MCP support, configure the Antenna MCP server in your Bedrock agent or application code.
Define the MCP server in your agent configuration
When creating or updating a Bedrock agent with MCP tool use, add the Antenna server to your tool configuration:
{
"mcpServers": {
"antenna": {
"url": "https://app.antenna.dev/api/mcp/enterprise",
"transport": "streamable-http",
"headers": {
"Authorization": "Bearer YOUR_ACCESS_TOKEN"
}
}
}
}Configure in application code (Python example)
If you are invoking Claude on Bedrock programmatically with MCP tools, pass the server configuration when setting up your client:
mcp_servers = {
"antenna": {
"url": "https://app.antenna.dev/api/mcp/enterprise",
"transport": "streamable-http",
"headers": {
"Authorization": f"Bearer {ANTENNA_ACCESS_TOKEN}"
}
}
}Test the connection
Send a prompt that uses the Antenna tools (e.g., “List the identity groups in my enterprise”) to verify the integration is working.
AWS Bedrock MCP support may require specific agent configurations or SDK versions. Refer to the AWS Bedrock documentation for the latest MCP integration details.
Cursor
Cursor supports MCP servers through its settings.
Open Cursor settings
Go to Cursor Settings > MCP > Add new global MCP server.
Add the MCP server configuration
Select Type: Streamable HTTP and enter:
{
"mcpServers": {
"antenna": {
"url": "https://app.antenna.dev/api/mcp/enterprise",
"headers": {
"Authorization": "Bearer YOUR_ACCESS_TOKEN"
}
}
}
}Verify the connection
After saving, you should see the Antenna tools listed under the MCP section. Use Agent mode to ask questions about your engineering metrics.
Devin
Devin supports MCP servers through its web-based settings.
Open MCP settings
In the Devin web app, go to Settings > Connections > MCP servers and click Add a custom MCP.
Configure the server
Fill in the following fields:
- Server Name:
Antenna - Short Description:
Query engineering metrics from Antenna - Transport type: HTTP
- URL:
https://app.antenna.dev/api/mcp/enterprise - Headers: Add an
Authorizationheader with the valueBearer YOUR_ACCESS_TOKEN
Save and test
Click Save, then click Test listing tools to verify the connection. Devin will connect to the server and confirm it can discover the Antenna tools.
For more details on configuring MCP servers in Devin, see the Devin MCP documentation .
GitHub Copilot
GitHub Copilot supports MCP servers in agent mode within VS Code through a workspace configuration file.
Create the MCP configuration file
In your workspace, create a file at .vscode/mcp.json (or run MCP: Add Server from the Command Palette and choose HTTP).
Add the Antenna server
Add an entry under the servers key:
{
"servers": {
"antenna": {
"type": "http",
"url": "https://app.antenna.dev/api/mcp/enterprise",
"headers": {
"Authorization": "Bearer YOUR_ACCESS_TOKEN"
}
}
}
}Start the server and verify
Click Start above the server entry in .vscode/mcp.json, then open the Copilot Chat view and switch to Agent mode. Ask a question like “Who is spending the most on AI?” to confirm Copilot can call the Antenna tools.
MCP support in GitHub Copilot requires a recent version of VS Code and is available in agent mode. See the GitHub Copilot MCP documentation for the latest details.
Kiro
Kiro supports remote MCP servers through its MCP configuration file.
Open the MCP configuration
Open the Kiro panel, go to the MCP Servers view, and click Edit — or open the configuration file directly at .kiro/settings/mcp.json (workspace) or ~/.kiro/settings/mcp.json (user level).
Add the Antenna server
Add an entry under the mcpServers key:
{
"mcpServers": {
"antenna": {
"type": "http",
"url": "https://app.antenna.dev/api/mcp/enterprise",
"headers": {
"Authorization": "Bearer YOUR_ACCESS_TOKEN"
}
}
}
}Verify the connection
Save the file. Kiro reconnects automatically and the Antenna server appears in the MCP Servers view. Ask a question like “Who is spending the most on AI?” to confirm Kiro can call the Antenna tools.
Troubleshooting
| Issue | Solution |
|---|---|
401 Unauthorized | Verify your access token is correct and has not been revoked. Regenerate it in Settings > Access Tokens if needed. |
403 Forbidden | The MCP feature may not be enabled for your enterprise. Contact your Antenna account representative. |
| Tools not appearing | Restart your AI client after updating the configuration. Ensure the URL and headers are correct. |
| Empty results | Check your date range and filters. The default range is the last 6 months. Use contributor_metric_fields to see available options. |