@zhixuan92/multi-model-agent-mcp 1.1.0 → 1.1.2
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 +61 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -6,12 +6,72 @@ Works with Claude Code, Codex CLI, Cursor, Gemini CLI, and Claude Desktop.
|
|
|
6
6
|
|
|
7
7
|
## Install
|
|
8
8
|
|
|
9
|
+
Requires Node >= 22 and a config file at `~/.multi-model/config.json`.
|
|
10
|
+
|
|
11
|
+
**1. Create config** — define your two agent slots. Three agent types are supported:
|
|
12
|
+
|
|
13
|
+
| Type | Auth | API key needed? |
|
|
14
|
+
|---|---|---|
|
|
15
|
+
| `claude` | Your existing Claude Code / Claude subscription | No — uses local OAuth |
|
|
16
|
+
| `codex` | Your existing Codex subscription (`codex login`) | No — reads `~/.codex/auth.json` |
|
|
17
|
+
| `openai-compatible` | Any OpenAI-compatible API (GPT, MiniMax, DeepSeek, Groq, local vLLM) | Yes — `apiKeyEnv` or `apiKey` |
|
|
18
|
+
|
|
19
|
+
**Example — Claude + Codex (no API keys):**
|
|
20
|
+
|
|
9
21
|
```bash
|
|
22
|
+
mkdir -p ~/.multi-model && cat > ~/.multi-model/config.json << 'EOF'
|
|
23
|
+
{
|
|
24
|
+
"agents": {
|
|
25
|
+
"standard": { "type": "codex", "model": "codex-mini-latest" },
|
|
26
|
+
"complex": { "type": "claude", "model": "claude-sonnet-4-20250514" }
|
|
27
|
+
},
|
|
28
|
+
"defaults": { "maxTurns": 200, "timeoutMs": 600000, "tools": "full" }
|
|
29
|
+
}
|
|
30
|
+
EOF
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
**Example — OpenAI-compatible endpoints (API keys required):**
|
|
34
|
+
|
|
35
|
+
```bash
|
|
36
|
+
mkdir -p ~/.multi-model && cat > ~/.multi-model/config.json << 'EOF'
|
|
37
|
+
{
|
|
38
|
+
"agents": {
|
|
39
|
+
"standard": {
|
|
40
|
+
"type": "openai-compatible",
|
|
41
|
+
"model": "MiniMax-M2",
|
|
42
|
+
"baseUrl": "https://api.minimax.io/v1",
|
|
43
|
+
"apiKeyEnv": "MINIMAX_API_KEY"
|
|
44
|
+
},
|
|
45
|
+
"complex": {
|
|
46
|
+
"type": "openai-compatible",
|
|
47
|
+
"model": "gpt-5",
|
|
48
|
+
"baseUrl": "https://api.openai.com/v1",
|
|
49
|
+
"apiKeyEnv": "OPENAI_API_KEY"
|
|
50
|
+
}
|
|
51
|
+
},
|
|
52
|
+
"defaults": { "maxTurns": 200, "timeoutMs": 600000, "tools": "full" }
|
|
53
|
+
}
|
|
54
|
+
EOF
|
|
55
|
+
```
|
|
56
|
+
|
|
57
|
+
Mix and match freely — e.g., `claude` for complex + `openai-compatible` for standard.
|
|
58
|
+
|
|
59
|
+
**2. Register the MCP server:**
|
|
60
|
+
|
|
61
|
+
```bash
|
|
62
|
+
# Claude/Codex agents (no env vars needed):
|
|
10
63
|
claude mcp add multi-model-agent -s user \
|
|
11
64
|
-- npx -y @zhixuan92/multi-model-agent-mcp serve
|
|
65
|
+
|
|
66
|
+
# OpenAI-compatible agents (pass API keys):
|
|
67
|
+
claude mcp add multi-model-agent -s user \
|
|
68
|
+
-e MINIMAX_API_KEY=... -e OPENAI_API_KEY=... \
|
|
69
|
+
-- npx -y @zhixuan92/multi-model-agent-mcp serve
|
|
12
70
|
```
|
|
13
71
|
|
|
14
|
-
No install step, no long-running process. Your MCP client spawns it on demand via `npx`.
|
|
72
|
+
No install step, no long-running process. Your MCP client spawns it on demand via `npx`.
|
|
73
|
+
|
|
74
|
+
For Codex CLI, Claude Desktop, and Cursor setup, see the [full guide](https://github.com/zhixuan312/multi-model-agent#quick-start).
|
|
15
75
|
|
|
16
76
|
## What you get
|
|
17
77
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@zhixuan92/multi-model-agent-mcp",
|
|
3
|
-
"version": "1.1.
|
|
3
|
+
"version": "1.1.2",
|
|
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.",
|