You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: sources/platform/integrations/ai/mcp.md
+7-7Lines changed: 7 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,7 +8,7 @@ slug: /integrations/mcp
8
8
9
9
<!-- markdownlint-disable MD024 -->
10
10
11
-
The Apify Model Context Protocol (MCP) server allows AI agents and frameworks compatible with the MCP standard to connect with the extensive library of Actors available on the [Apify Store](https://apify.com/store).
11
+
The Apify Model Context Protocol (MCP) server allows AI agents and frameworks compatible with the MCP standard to connect with the extensive library of Actors available on [Apify Store](https://apify.com/store).
12
12
13
13
## Why use MCP with Apify?
14
14
@@ -25,10 +25,10 @@ The Apify Model Context Protocol (MCP) server allows AI agents and frameworks co
25
25
26
26
## Prerequisites
27
27
28
-
Before you start, ensure you have the following:
28
+
Before you start, make sure you have the following:
29
29
30
30
1._Apify account_: You need an active account on the Apify platform.
31
-
2._API Token_: Get your personal API token from the **Integrations** section in the [Apify Console](https://console.apify.com/account#/integrations).
31
+
2._API Token_: Get your personal API token from the **Integrations** section in [Apify Console](https://console.apify.com/account#/integrations).
32
32
33
33
## Connection methods
34
34
@@ -39,15 +39,15 @@ Apify provides two main ways to connect your MCP client to Actors:
39
39
40
40
### Option 1: Use the main Actors MCP server
41
41
42
-
This method offers the most flexibility, allowing access to the entire Apify Store dynamically or by specifying Actors at connection time.
42
+
This method offers the most flexibility, allowing access to all of Apify Store dynamically or by specifying Actors at connection time.
- Dynamic discovery: Agents can use MCP operations like `discover-actors` to search the Apify Store for tools.
50
+
- Dynamic discovery: Agents can use MCP operations like `discover-actors` to search Apify Store for tools.
51
51
- Dynamic registration: Agents can use the `add-actor-to-tools` operation to add discovered Actors to their available toolset for the current session.
52
52
- Pre-registration via URL: You can make specific Actors available immediately by adding the `&actors=` query parameter to the connection URL (for example, `&actors=apify/rag-web-browser`).
- Tester MCP Client: Use the [Tester MCP Client](https://apify.com/jiri.spilka/tester-mcp-client) on Apify to interact with either MCP server type. Enter the appropriate server URL (for example, `https://actors-mcp-server.apify.actor/sse` or `https://rag-web-browser.apify.actor/sse`) in the Actor input field, configure your API token, run the client Actor, and interact through its user interface.
180
180
- Protocol information:
181
-
- MCP Documentation: For details on the protocol, see the [MCP Introduction](https://modelcontextprotocol.io/introduction).
182
-
- MCP Client Examples: Find example client implementations at [MCP Clients](https://modelcontextprotocol.io/clients).
181
+
- MCP documentation: For details on the protocol, see the [MCP Introduction](https://modelcontextprotocol.io/introduction).
182
+
- MCP client examples: Find example client implementations at [MCP Clients](https://modelcontextprotocol.io/clients).
183
183
- Further reading:
184
184
- Apify Blog: Read more about Apify's implementation in the post: [What is Anthropic's Model Context Protocol?](https://blog.apify.com/what-is-model-context-protocol/)
0 commit comments