@ai-dossier/mcp-server 1.6.3 → 1.6.4-next.543.1

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.
Files changed (2) hide show
  1. package/README.md +5 -1
  2. package/package.json +10 -12
package/README.md CHANGED
@@ -4,7 +4,11 @@
4
4
  [![npm downloads](https://img.shields.io/npm/dm/@ai-dossier/mcp-server)](https://www.npmjs.com/package/@ai-dossier/mcp-server)
5
5
  [![License: AGPL-3.0](https://img.shields.io/badge/License-AGPL--3.0-blue.svg)](https://github.com/imboard-ai/ai-dossier/blob/main/LICENSE)
6
6
 
7
- MCP server that lets any MCP-capable LLM discover, verify, and run dossiers — portable, signed skills — through the [Model Context Protocol](https://modelcontextprotocol.io/). If you've used Claude Code skills, dossiers will feel familiar: they're skills you can verify, version, and pull from a registry.
7
+ **Use one portable AI-agent skill across Claude Code, Codex, OpenCode, and MCP-compatible workflows.**
8
+
9
+ `@ai-dossier/mcp-server` is for teams that want their MCP clients to discover, verify, and run trusted skills through the [Model Context Protocol](https://modelcontextprotocol.io/). Dossiers are portable, signed, versioned skills: familiar to Claude Code users, but verifiable and registry-backed for any compatible LLM tool.
10
+
11
+ > **Part of the ai-dossier ecosystem**: use [`@ai-dossier/cli`](../cli/README.md) to author and install skills, [`@ai-dossier/core`](../packages/core/README.md) for verification, and the [ai-dossier project](https://github.com/imboard-ai/ai-dossier) for the complete platform.
8
12
 
9
13
  ## Installation
10
14
 
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "@ai-dossier/mcp-server",
3
- "version": "1.6.3",
4
- "description": "MCP server that lets any LLM discover, verify, and run dossiers (versioned, signed agent skills) via the Model Context Protocol.",
3
+ "version": "1.6.4-next.543.1",
4
+ "description": "Secure MCP server for discovering, verifying, and running portable AI-agent skills through the Model Context Protocol.",
5
5
  "main": "dist/index.js",
6
6
  "bin": {
7
7
  "dossier-mcp-server": "dist/index.js"
@@ -14,15 +14,13 @@
14
14
  "test": "vitest run"
15
15
  },
16
16
  "keywords": [
17
- "mcp",
18
- "dossier",
19
- "skill",
20
- "skills",
21
- "claude-code",
22
- "automation",
23
- "llm",
24
- "ai",
25
- "model-context-protocol"
17
+ "mcp-server",
18
+ "model-context-protocol",
19
+ "secure-mcp",
20
+ "claude-code-mcp",
21
+ "agent-skills",
22
+ "llm-workflows",
23
+ "skill-verification"
26
24
  ],
27
25
  "author": "Yuval Dimnik <yuval.dimnik@gmail.com>",
28
26
  "license": "AGPL-3.0-only",
@@ -49,7 +47,7 @@
49
47
  "registry": "https://registry.npmjs.org"
50
48
  },
51
49
  "dependencies": {
52
- "@ai-dossier/core": "^1.12.0",
50
+ "@ai-dossier/core": "1.14.4-next.543.1",
53
51
  "@modelcontextprotocol/sdk": "^1.21.0",
54
52
  "zod": "^3.25.76"
55
53
  },