@modelcontextprotocol/server-everything 0.2.0 → 0.5.0
Sign up to get free protection for your applications and to get access to all the features.
- package/README.md +84 -2
- package/package.json +1 -1
package/README.md
CHANGED
@@ -1,3 +1,85 @@
|
|
1
|
-
# Everything
|
1
|
+
# Everything MCP Server
|
2
2
|
|
3
|
-
This MCP server attempts to exercise all the features of the MCP protocol. It is not intended to be a useful server, but rather a test server for builders of MCP clients.
|
3
|
+
This MCP server attempts to exercise all the features of the MCP protocol. It is not intended to be a useful server, but rather a test server for builders of MCP clients. It implements prompts, tools, resources, sampling, and more to showcase MCP capabilities.
|
4
|
+
|
5
|
+
## Components
|
6
|
+
|
7
|
+
### Tools
|
8
|
+
|
9
|
+
1. `echo`
|
10
|
+
- Simple tool to echo back input messages
|
11
|
+
- Input:
|
12
|
+
- `message` (string): Message to echo back
|
13
|
+
- Returns: Text content with echoed message
|
14
|
+
|
15
|
+
2. `add`
|
16
|
+
- Adds two numbers together
|
17
|
+
- Inputs:
|
18
|
+
- `a` (number): First number
|
19
|
+
- `b` (number): Second number
|
20
|
+
- Returns: Text result of the addition
|
21
|
+
|
22
|
+
3. `longRunningOperation`
|
23
|
+
- Demonstrates progress notifications for long operations
|
24
|
+
- Inputs:
|
25
|
+
- `duration` (number, default: 10): Duration in seconds
|
26
|
+
- `steps` (number, default: 5): Number of progress steps
|
27
|
+
- Returns: Completion message with duration and steps
|
28
|
+
- Sends progress notifications during execution
|
29
|
+
|
30
|
+
4. `sampleLLM`
|
31
|
+
- Demonstrates LLM sampling capability using MCP sampling feature
|
32
|
+
- Inputs:
|
33
|
+
- `prompt` (string): The prompt to send to the LLM
|
34
|
+
- `maxTokens` (number, default: 100): Maximum tokens to generate
|
35
|
+
- Returns: Generated LLM response
|
36
|
+
|
37
|
+
5. `getTinyImage`
|
38
|
+
- Returns a small test image
|
39
|
+
- No inputs required
|
40
|
+
- Returns: Base64 encoded PNG image data
|
41
|
+
|
42
|
+
### Resources
|
43
|
+
|
44
|
+
The server provides 100 test resources in two formats:
|
45
|
+
- Even numbered resources:
|
46
|
+
- Plaintext format
|
47
|
+
- URI pattern: `test://static/resource/{even_number}`
|
48
|
+
- Content: Simple text description
|
49
|
+
|
50
|
+
- Odd numbered resources:
|
51
|
+
- Binary blob format
|
52
|
+
- URI pattern: `test://static/resource/{odd_number}`
|
53
|
+
- Content: Base64 encoded binary data
|
54
|
+
|
55
|
+
Resource features:
|
56
|
+
- Supports pagination (10 items per page)
|
57
|
+
- Allows subscribing to resource updates
|
58
|
+
- Demonstrates resource templates
|
59
|
+
- Auto-updates subscribed resources every 5 seconds
|
60
|
+
|
61
|
+
### Prompts
|
62
|
+
|
63
|
+
1. `simple_prompt`
|
64
|
+
- Basic prompt without arguments
|
65
|
+
- Returns: Single message exchange
|
66
|
+
|
67
|
+
2. `complex_prompt`
|
68
|
+
- Advanced prompt demonstrating argument handling
|
69
|
+
- Required arguments:
|
70
|
+
- `temperature` (number): Temperature setting
|
71
|
+
- Optional arguments:
|
72
|
+
- `style` (string): Output style preference
|
73
|
+
- Returns: Multi-turn conversation with images
|
74
|
+
|
75
|
+
## Usage with Claude Desktop
|
76
|
+
|
77
|
+
Add to your `claude_desktop_config.json`:
|
78
|
+
|
79
|
+
```json
|
80
|
+
{
|
81
|
+
"everything": {
|
82
|
+
"command": "npx",
|
83
|
+
"args": ["-y", "@modelcontextprotocol/server-everything"]
|
84
|
+
}
|
85
|
+
}
|
package/package.json
CHANGED