@mcpskillsio/server 2.4.0 → 2.4.1
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 +12 -4
- package/index.js +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
Trust-score any AI skill or MCP server from inside Claude Code, Cursor, or any MCP client.
|
|
4
4
|
|
|
5
|
-
|
|
5
|
+
13 standard signals (15 in Skills Mode) across 4 dimensions with safety scanning for prompt injection, credential theft, and supply chain attacks.
|
|
6
6
|
|
|
7
7
|
## Install
|
|
8
8
|
|
|
@@ -100,11 +100,19 @@ Get a boolean go/no-go decision with reasoning.
|
|
|
100
100
|
"Should I install this MCP server? 21st-dev/magic-mcp"
|
|
101
101
|
```
|
|
102
102
|
|
|
103
|
+
### `build_stack`
|
|
104
|
+
|
|
105
|
+
Recommend a vetted, pre-scored stack from MCP Skills' curated packages.
|
|
106
|
+
|
|
107
|
+
```
|
|
108
|
+
"Build me a stack: auth + payments + email"
|
|
109
|
+
```
|
|
110
|
+
|
|
103
111
|
## Full Reports
|
|
104
112
|
|
|
105
113
|
Free tier returns trust tier + dimension scores (same as mcpskills.io free scans).
|
|
106
114
|
|
|
107
|
-
For full
|
|
115
|
+
For full reports (13 standard / 15 Skills Mode signals + safety findings) inside your IDE, set your API key:
|
|
108
116
|
|
|
109
117
|
```bash
|
|
110
118
|
export MCPSKILLS_API_KEY=your_key_here
|
|
@@ -117,8 +125,8 @@ Get your API key at [mcpskills.io/api](https://mcpskills.io/api).
|
|
|
117
125
|
The server calls the mcpskills.io trust scoring API, which:
|
|
118
126
|
|
|
119
127
|
1. Fetches repo data from GitHub API and OpenSSF Scorecard
|
|
120
|
-
2. Scores
|
|
121
|
-
3. Detects AI skills/MCP servers and activates Skills Mode (+2 bonus signals)
|
|
128
|
+
2. Scores 13 standard signals across 4 dimensions (Alive, Legit, Solid, Usable)
|
|
129
|
+
3. Detects AI skills/MCP servers and activates Skills Mode (+2 bonus signals — 15 total)
|
|
122
130
|
4. Runs 5 safety scans based on ClawHavoc and ToxicSkills attack patterns
|
|
123
131
|
5. Assigns a trust tier: Verified (>=7.0), Established (>=4.5), New, or Blocked
|
|
124
132
|
|
package/index.js
CHANGED
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@mcpskillsio/server",
|
|
3
|
-
"version": "2.4.
|
|
3
|
+
"version": "2.4.1",
|
|
4
4
|
"description": "Trust-score any AI skill or MCP server from inside Claude Code, Cursor, or any MCP client. Accepts GitHub repos, npm packages, Smithery URLs, and OpenClaw skills. 15 signals (incl. OSV/KEV/EPSS vulnerability intelligence), safety scanning, OpenClaw frontmatter parsing + transparency scoring, recommendations, badges, monitoring, batch checking, auto-gate decisions, and stack building from live trust data.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "index.js",
|