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
- Other clients at [https://modelcontextprotocol.io/clients](https://modelcontextprotocol.io/clients)
77
76
- More clients at [https://glama.ai/mcp/clients](https://glama.ai/mcp/clients)
@@ -83,7 +82,7 @@ With MCP server integrated, you can ask your AI assistant things like:
83
82
- "Provide a step-by-step guide on using the Model Context Protocol, including source URLs."
84
83
- "What Apify Actors can I use?"
85
84
86
-
### Supported Clients Matrix
85
+
### Supported clients matrix
87
86
88
87
The following table outlines the tested MCP clients and their level of support for key features.
89
88
@@ -92,12 +91,19 @@ The following table outlines the tested MCP clients and their level of support f
92
91
|**Claude.ai (web)**| ✅ Full ||
93
92
|**Claude Desktop**| 🟡 Partial | Tools may need to be reloaded manually in the client. |
94
93
|**VS Code (Genie)**| ✅ Full ||
95
-
|**LibreChat**| ❓ Untested ||
96
94
|**Apify Tester MCP Client**| ✅ Full | Designed for testing Apify MCP servers. |
97
95
98
-
*This matrix is a work in progress. If you have tested other clients, please consider contributing to this documentation.*
96
+
Apify MCP Server is compatible with any MCP client that adheres to the [Model Context Protocol](https://modelcontextprotocol.org/), but the level of support for dynamic tool discovery and other features may vary between clients. Therefore, the server uses [mcp-client-capabilities](https://github.com/apify/mcp-client-capabilities)to detect client capabilities and adjust its behavior accordingly.
99
97
100
-
# 🪄 Try Apify MCP Instantly
98
+
**Smart tool selection based on client capabilities:**
99
+
100
+
When the `actors` tool category is requested, the server intelligently selects the most appropriate Actor-related tools based on the client's capabilities:
101
+
102
+
-**Clients with dynamic tool support** (e.g., Claude.ai web, VS Code Genie): The server provides the `add-actor` tool instead of `call-actor`. This allows for a better user experience where users can dynamically discover and add new Actors as tools during their conversation.
103
+
104
+
-**Clients with limited dynamic tool support** (e.g., Claude Desktop): The server provides the standard `call-actor` tool along with other Actor category tools, ensuring compatibility while maintaining functionality.
105
+
106
+
# 🪄 Try Apify MCP instantly
101
107
102
108
Want to try Apify MCP without any setup?
103
109
@@ -106,7 +112,7 @@ Check out [Apify Tester MCP Client](https://apify.com/jiri.spilka/tester-mcp-cli
106
112
This interactive, chat-like interface provides an easy way to explore the capabilities of Apify MCP without any local setup.
107
113
Just sign in with your Apify account and start experimenting with web scraping, data extraction, and automation tools!
108
114
109
-
Or use the Anthropic Desktop extension file (dxt) for one-click installation: [Apify MCP server dxt file](https://github.com/apify/apify-mcp-server/releases/latest/download/apify-mcp-server.dxt)
115
+
Or use the MCP bundle file (formerly known as Anthropic Desktop extension file, or DXT) for one-click installation: [Apify MCP server MCPB file](https://github.com/apify/apify-mcp-server/releases/latest/download/apify-mcp-server.mcpb)
110
116
111
117
# 🛠️ Tools, resources, and prompts
112
118
@@ -172,6 +178,8 @@ Here is an overview list of all the tools provided by the Apify MCP Server.
172
178
173
179
> **Note:**
174
180
>
181
+
> When using the `actors` tool category, clients that support dynamic tool discovery (like Claude.ai web and VS Code) automatically receive the `add-actor` tool instead of `call-actor` for enhanced Actor discovery capabilities.
182
+
175
183
> The `get-actor-output` tool is automatically included with any Actor-related tool, such as `call-actor`, `add-actor`, or any specific Actor tool like `apify-slash-rag-web-browser`. When you call an Actor - either through the `call-actor` tool or directly via an Actor tool (e.g., `apify-slash-rag-web-browser`) - you receive a preview of the output. The preview depends on the Actor's output format and length; for some Actors and runs, it may include the entire output, while for others, only a limited version is returned to avoid overwhelming the LLM. To retrieve the full output of an Actor run, use the `get-actor-output` tool (supports limit, offset, and field filtering) with the `datasetId` provided by the Actor call.
0 commit comments