# Forge MCP

> Ask your own agent about your services, rankings, buyers, and health.

Source: https://docs.forgeintel.co/forge-mcp

Forge runs an MCP server, so the agent you already use (Claude, Cursor, Codex, and others) can read the same data you see in the dashboard, and run a check when you ask.

```text Server URL
https://mcp.forgeintel.co/mcp
```

The first time your agent connects, a browser window asks you to sign in to Forge and approve access. Your agent sees only the services in your account.

## Connect your agent

  #### Claude Code

```bash
claude mcp add --transport http forge https://mcp.forgeintel.co/mcp
```

  #### Claude Desktop

Open **Customize**, then **Connectors**. Select **Add custom connector**, name it Forge, and paste the server URL. On Team and Enterprise plans, an owner adds it under **Organization settings**, then **Connectors**.

  #### Cursor

```json .cursor/mcp.json
{
  "mcpServers": {
    "forge": { "url": "https://mcp.forgeintel.co/mcp" }
  }
}
```

  #### Codex

```bash
codex mcp add forge --url "https://mcp.forgeintel.co/mcp"
```

  #### VS Code

```bash
code --add-mcp '{"name":"forge","type":"http","url":"https://mcp.forgeintel.co/mcp"}'
```

**Connect agent** in the Forge sidebar has the same instructions for more clients, including Hermes, GitHub Copilot and OpenCode.

## Try asking

- "What needs my attention across my services this week?"
- "Which of my routes dropped in the rankings, and who passed them?"
- "Why is the weather route failing its health check, and how do I fix it?"
- "Which agents paid for my API in the last 30 days, and how did they rate it?"

## Tools

| Tool | What it returns |
|---|---|
| `get_brief` | Workspace status: services, health, the largest ranking moves, payment totals, and what needs attention. |
| `list_services` | The services on your account. |
| `list_endpoints` | Every active endpoint on a service, paid and unpaid. |
| `get_visibility` | Each route as listed, missing, or ineligible per marketplace, with next actions. |
| `get_rankings` | Current rank and change since the last scan, with optional history. |
| `get_ranking_results` | The top ten for one query on one surface. |
| `get_product_competitors` | How you do head to head against the products agents pick instead of you, and why they choose someone else. |
| `get_competitors` | Who outranks one of your routes, with counts and evidence. |
| `get_competitor` | A side-by-side comparison with one competitor. |
| `get_activity` | Calls, payments and sources for a service or your whole account. |
| `get_health` | Health checks, open incidents, and suggested fixes. |
| `refresh_visibility` | Queue a marketplace recheck. |
| `run_health_check` | Queue a health check. |
| `refresh_rankings` | Queue a ranking scan. |
| `regenerate_queries` | Replace the generated ranking queries and scan again. |

The last four are available when you grant Forge's `forge:operate` permission at sign-in. They change nothing about your service; they queue the same scans as the buttons in the dashboard.

> This is different from the [docs MCP](https://docs.forgeintel.co/docs-for-agents), which lets an agent read this documentation.