ai-validation-mcp 0.1.0 → 0.1.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +87 -0
- package/package.json +2 -1
package/README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
1
|
+
# AI Validation MCP Server
|
|
2
|
+
|
|
3
|
+
Independent AI code validation service — analyzes your tests for bias, missing edge cases, and coverage gaps. Works as an MCP server for AI coding agents and IDEs.
|
|
4
|
+
|
|
5
|
+
## Why
|
|
6
|
+
|
|
7
|
+
AI-generated code increases production incidents 43% YoY. General-purpose assistants generate tests as a side effect, not as a core function. This server provides specialized, independent validation — a second opinion on your test quality.
|
|
8
|
+
|
|
9
|
+
## Installation
|
|
10
|
+
|
|
11
|
+
```bash
|
|
12
|
+
npm install ai-validation-mcp
|
|
13
|
+
```
|
|
14
|
+
|
|
15
|
+
## MCP Configuration
|
|
16
|
+
|
|
17
|
+
Add to your MCP client config (e.g. `claude_desktop_config.json`):
|
|
18
|
+
|
|
19
|
+
```json
|
|
20
|
+
{
|
|
21
|
+
"mcpServers": {
|
|
22
|
+
"ai-validation": {
|
|
23
|
+
"command": "npx",
|
|
24
|
+
"args": ["-y", "ai-validation-mcp"],
|
|
25
|
+
"env": {
|
|
26
|
+
"ANTHROPIC_API_KEY": "your-key-here"
|
|
27
|
+
}
|
|
28
|
+
}
|
|
29
|
+
}
|
|
30
|
+
}
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
Requires an Anthropic API key for analysis.
|
|
34
|
+
|
|
35
|
+
## Tools
|
|
36
|
+
|
|
37
|
+
### validate_tests
|
|
38
|
+
|
|
39
|
+
Analyze existing tests for bias, missing edge cases, and quality issues.
|
|
40
|
+
|
|
41
|
+
| Parameter | Type | Required | Description |
|
|
42
|
+
|------------|--------|----------|--------------------------------------|
|
|
43
|
+
| sourceCode | string | Yes | The source code to validate against |
|
|
44
|
+
| testCode | string | Yes | The existing test code to analyze |
|
|
45
|
+
| language | string | No | Programming language (default: typescript) |
|
|
46
|
+
|
|
47
|
+
Returns: bias warnings, missing edge case suggestions, overall quality score.
|
|
48
|
+
|
|
49
|
+
### suggest_edge_cases
|
|
50
|
+
|
|
51
|
+
Suggest comprehensive edge cases for a given function.
|
|
52
|
+
|
|
53
|
+
| Parameter | Type | Required | Description |
|
|
54
|
+
|------------|--------|----------|--------------------------------------|
|
|
55
|
+
| sourceCode | string | Yes | The source code to analyze |
|
|
56
|
+
| language | string | No | Programming language (default: typescript) |
|
|
57
|
+
|
|
58
|
+
Returns: categorized edge cases (happy path, error handling, boundary, type coercion, integration).
|
|
59
|
+
|
|
60
|
+
### coverage_gap_analysis
|
|
61
|
+
|
|
62
|
+
Identify untested code paths, branches, and logic gaps.
|
|
63
|
+
|
|
64
|
+
| Parameter | Type | Required | Description |
|
|
65
|
+
|------------|--------|----------|--------------------------------------|
|
|
66
|
+
| sourceCode | string | Yes | The source code to analyze |
|
|
67
|
+
| testCode | string | Yes | The existing test code to evaluate |
|
|
68
|
+
| language | string | No | Programming language (default: typescript) |
|
|
69
|
+
|
|
70
|
+
Returns: coverage score, gap details, suggested tests to close gaps.
|
|
71
|
+
|
|
72
|
+
## Modes
|
|
73
|
+
|
|
74
|
+
- **`--cached`** (default) — Uses saved responses from `./fixtures/`. No API calls.
|
|
75
|
+
- **`--live`** — Real Anthropic API calls. Overwrites fixtures.
|
|
76
|
+
|
|
77
|
+
## Development
|
|
78
|
+
|
|
79
|
+
```bash
|
|
80
|
+
npm install
|
|
81
|
+
npm run build
|
|
82
|
+
npm test
|
|
83
|
+
```
|
|
84
|
+
|
|
85
|
+
## License
|
|
86
|
+
|
|
87
|
+
MIT
|
package/package.json
CHANGED
|
@@ -1,6 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "ai-validation-mcp",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.2",
|
|
4
|
+
"mcpName": "io.github.ZUHcYa/ai-validation",
|
|
4
5
|
"description": "MCP Server for independent AI code validation - analyzes tests for bias, missing edge cases, and coverage gaps",
|
|
5
6
|
"type": "module",
|
|
6
7
|
"main": "dist/index.js",
|