@peerlm/mcp 0.1.0 → 0.1.1
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 +61 -0
- package/package.json +1 -1
package/README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
1
|
+
# @peerlm/mcp
|
|
2
|
+
|
|
3
|
+
MCP server for [PeerLM](https://peerlm.com) — run LLM evaluations from Claude Desktop, Cursor, or any MCP-compatible client.
|
|
4
|
+
|
|
5
|
+
## Setup
|
|
6
|
+
|
|
7
|
+
1. Get an API key at [peerlm.com/settings/api-keys](https://app.peerlm.com/settings/api-keys)
|
|
8
|
+
2. Add the server to your MCP client config:
|
|
9
|
+
|
|
10
|
+
```json
|
|
11
|
+
{
|
|
12
|
+
"mcpServers": {
|
|
13
|
+
"peerlm": {
|
|
14
|
+
"command": "npx",
|
|
15
|
+
"args": ["-y", "@peerlm/mcp"],
|
|
16
|
+
"env": {
|
|
17
|
+
"PEERLM_API_KEY": "plm_live_..."
|
|
18
|
+
}
|
|
19
|
+
}
|
|
20
|
+
}
|
|
21
|
+
}
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
### Config file locations
|
|
25
|
+
|
|
26
|
+
| Client | Path |
|
|
27
|
+
|--------|------|
|
|
28
|
+
| Claude Desktop | `~/Library/Application Support/Claude/claude_desktop_config.json` |
|
|
29
|
+
| Cursor | `~/.cursor/mcp.json` |
|
|
30
|
+
| Claude Code | `~/.claude.json` |
|
|
31
|
+
|
|
32
|
+
## Tools
|
|
33
|
+
|
|
34
|
+
| Tool | Description |
|
|
35
|
+
|------|-------------|
|
|
36
|
+
| `list_suites` | List all evaluation suites in your workspace |
|
|
37
|
+
| `get_suite` | Get details of a specific suite by ID |
|
|
38
|
+
| `create_suite` | Create a new evaluation suite with models, prompts, and criteria |
|
|
39
|
+
| `run_eval` | Trigger an evaluation run on a suite |
|
|
40
|
+
| `get_results` | Get results and leaderboard for a completed run |
|
|
41
|
+
| `list_models` | List available LLM models (filter by provider or tier) |
|
|
42
|
+
| `get_usage` | View your credit balance and plan details |
|
|
43
|
+
| `create_system_prompt` | Create a new system prompt in your library |
|
|
44
|
+
| `create_test_prompt` | Create a new test prompt in your library |
|
|
45
|
+
|
|
46
|
+
## Environment variables
|
|
47
|
+
|
|
48
|
+
| Variable | Required | Description |
|
|
49
|
+
|----------|----------|-------------|
|
|
50
|
+
| `PEERLM_API_KEY` | Yes | Your PeerLM API key (`plm_live_...`) |
|
|
51
|
+
| `PEERLM_BASE_URL` | No | API base URL (default: `https://app.peerlm.com`) |
|
|
52
|
+
|
|
53
|
+
## Links
|
|
54
|
+
|
|
55
|
+
- [PeerLM](https://peerlm.com) — LLM evaluation platform
|
|
56
|
+
- [Documentation](https://peerlm.com/docs)
|
|
57
|
+
- [Get an API key](https://app.peerlm.com/settings/api-keys)
|
|
58
|
+
|
|
59
|
+
## License
|
|
60
|
+
|
|
61
|
+
MIT — built by [PeerLM](https://peerlm.com)
|