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
+7-9Lines changed: 7 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -25,7 +25,7 @@ Before connecting your AI to Apify, you'll need three things:
25
25
26
26
## Quick start
27
27
28
-
To get started with the Apify MCP server you have two options.
28
+
You can connect to the Apify MCP server in two ways: use our hosted service for a quick and easy setup, or run the server locally for development and testing.
29
29
30
30
### Streamable HTTP with OAuth (recommended)
31
31
@@ -154,23 +154,21 @@ This dynamic discovery means your AI can adapt to new tasks without manual confi
154
154
155
155
### Production best practices
156
156
157
-
For production deployments, explicitly specify which tools to load rather than relying on defaults. This ensures consistent behavior across updates:
157
+
-For production deployments, explicitly specify which tools to load rather than relying on defaults. This ensures consistent behavior across updates:
Always use the latest version of the server by appending `@latest` to your npm commands. Monitor your API usage through Apify Console to stay within your plan limits.
161
+
- Always use the latest version of the server by appending `@latest` to your npm commands.
162
+
- Monitor your API usage through Apify Console to stay within your plan limits.
163
+
- For optimal performance, batch related operations when possible and use Actor webhooks for long-running tasks instead of polling for results.
162
164
163
-
###Rate limits and performance
165
+
## Rate limits and performance
164
166
165
167
The Apify MCP server allows up to _30_ requests per second per user. This limit applies to all operations including Actor runs, storage access, and
166
168
documentation queries. If you exceed this limit, you'll receive a `429` response and should implement appropriate retry logic.
167
169
168
-
For optimal performance, batch related operations when possible and use Actor webhooks for long-running tasks instead of polling for results.
169
-
170
170
## Troubleshooting
171
171
172
-
This section covers common issues you might encounter while using the Apify MCP server.
173
-
174
172
### Authentication errors
175
173
176
174
-_Check your API token_: Verify that your Apify API token is correct. You can find it in the **Integrations** section of the [Apify Console](https://console.apify.com/account#/integrations). Without a valid token, the server cannot start Actor runs.
0 commit comments