falcon mcp connectors

src/lib/navigation.ts

@@ -146,6 +146,7 @@ export const tabNavigation: NavTab[] = [
             items: [
               { title: 'Using Falcon AI', href: '/docs/falcon-ai/features/chat' },
               { title: 'Skill Builder', href: '/docs/falcon-ai/features/skills' },
+              { title: 'MCP Connectors', href: '/docs/falcon-ai/features/mcp-connectors' },
             ]
           },
         ]

src/pages/docs/falcon-ai/features/mcp-connectors.mdx

@@ -0,0 +1,51 @@
+---
+title: "MCP Connectors"
+description: "Connect external MCP servers to Falcon AI so it can use tools from third-party services like Linear, Slack, GitHub, and custom APIs."
+---
+
+## About
+
+Falcon AI comes with built-in tools for the Future AGI platform, but many workflows involve external services like project trackers, communication tools, or internal APIs. MCP Connectors extend Falcon AI by connecting it to any external MCP server. Once connected, Falcon AI discovers the server's tools and can call them directly during conversations. This means tasks like "create a Linear ticket for this failing evaluation" or "post this cost report to Slack" happen inside Falcon AI without switching tools.
+
+---
+
+## When to use
+
+- **Connect project management tools**: Link Linear, Jira, or other trackers so Falcon AI can create and update issues from evaluation or trace analysis.
+- **Integrate communication tools**: Connect Slack or email so Falcon AI can share reports and alerts directly.
+- **Use custom internal APIs**: Connect internal MCP servers that expose domain-specific tools.
+
+---
+
+## How to
+
+<Steps>
+  <Step title="Add a connector">
+    Open Falcon AI settings and go to the **Connectors** section. Click **Add Connector** and fill in the fields:
+    ![Add connector form](/screenshot/product/falcon/9.png)
+
+    | Field | Description |
+    |-------|-------------|
+    | **Name** | Display name for the connector (e.g., "Linear", "Slack") |
+    | **Server URL** | The MCP server endpoint URL |
+    | **Transport** | `streamable_http` (default) or `sse` |
+    | **Auth type** | `none`, `api_key`, `bearer`, or `oauth` |
+    | **Auth header name** | Header name for authentication (default: `Authorization`) |
+    | **Auth header value** | The API key, bearer token, or OAuth token |
+  </Step>
+
+  <Step title="Discover tools">
+    After saving, Falcon AI connects to the MCP server and discovers available tools. The connector shows the number of discovered tools and the last discovery timestamp. If the connection fails, the error message is displayed.
+  </Step>
+
+  <Step title="Enable tools">
+    Not all discovered tools need to be active. Select which tools Falcon AI should have access to from the discovered list. Only enabled tools appear in conversations.
+  </Step>
+
+  <Step title="Use connector tools in chat">
+    Once enabled, connector tools are available in Falcon AI conversations alongside built-in platform tools. Falcon AI decides when to use them based on the request.
+
+    For example, after connecting Linear:
+    > "Create a Linear ticket for the faithfulness regression we found in the last evaluation run."
+  </Step>
+</Steps>