@zhixuan92/multi-model-agent-mcp 1.1.0 → 1.1.1
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 +34 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -6,12 +6,45 @@ Works with Claude Code, Codex CLI, Cursor, Gemini CLI, and Claude Desktop.
|
|
|
6
6
|
|
|
7
7
|
## Install
|
|
8
8
|
|
|
9
|
+
Requires Node >= 22, a config file, and API keys for your chosen providers.
|
|
10
|
+
|
|
11
|
+
**1. Create config** — define your two agent slots:
|
|
12
|
+
|
|
13
|
+
```bash
|
|
14
|
+
mkdir -p ~/.multi-model && cat > ~/.multi-model/config.json << 'EOF'
|
|
15
|
+
{
|
|
16
|
+
"agents": {
|
|
17
|
+
"standard": {
|
|
18
|
+
"type": "openai-compatible",
|
|
19
|
+
"model": "MiniMax-M2",
|
|
20
|
+
"baseUrl": "https://api.minimax.io/v1",
|
|
21
|
+
"apiKeyEnv": "MINIMAX_API_KEY"
|
|
22
|
+
},
|
|
23
|
+
"complex": {
|
|
24
|
+
"type": "openai-compatible",
|
|
25
|
+
"model": "gpt-5",
|
|
26
|
+
"baseUrl": "https://api.openai.com/v1",
|
|
27
|
+
"apiKeyEnv": "OPENAI_API_KEY"
|
|
28
|
+
}
|
|
29
|
+
},
|
|
30
|
+
"defaults": { "maxTurns": 200, "timeoutMs": 600000, "tools": "full" }
|
|
31
|
+
}
|
|
32
|
+
EOF
|
|
33
|
+
```
|
|
34
|
+
|
|
35
|
+
Any OpenAI-compatible endpoint works in either slot. For `claude` type agents, set up local Claude auth or `ANTHROPIC_API_KEY`. For `codex` type, run `codex login` first or set `OPENAI_API_KEY`.
|
|
36
|
+
|
|
37
|
+
**2. Register the MCP server** — pass your API keys as env vars:
|
|
38
|
+
|
|
9
39
|
```bash
|
|
10
40
|
claude mcp add multi-model-agent -s user \
|
|
41
|
+
-e MINIMAX_API_KEY=... -e OPENAI_API_KEY=... \
|
|
11
42
|
-- npx -y @zhixuan92/multi-model-agent-mcp serve
|
|
12
43
|
```
|
|
13
44
|
|
|
14
|
-
No install step, no long-running process. Your MCP client spawns it on demand via `npx`.
|
|
45
|
+
No install step, no long-running process. Your MCP client spawns it on demand via `npx`.
|
|
46
|
+
|
|
47
|
+
For Codex CLI, Claude Desktop, and Cursor setup, see the [full guide](https://github.com/zhixuan312/multi-model-agent#quick-start).
|
|
15
48
|
|
|
16
49
|
## What you get
|
|
17
50
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@zhixuan92/multi-model-agent-mcp",
|
|
3
|
-
"version": "1.1.
|
|
3
|
+
"version": "1.1.1",
|
|
4
4
|
"type": "module",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"description": "MCP server for multi-model-agent. Exposes a delegate_tasks tool that routes work to Claude, Codex, or OpenAI-compatible sub-agents based on capability, quality tier, and cost.",
|