Train in SilenceSAFE
The first Task-Aware MCP server and automated VRAM calculator for LLM fine-tuning. Instantly snipe the cheapest, fastest GPUs across 10+ cloud providers.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Train in Silence The first Task-Aware MCP server for LLM fine-tuning. Stop comparing GPU prices. Start training.
中文
You want to fine-tune an LLM. You open Vast.ai, RunPod, AWS, etc. -- a dozen tabs, a dozen pricing models, a dozen different ways to describe a GPU. Which option can run your code, and do so more cheaply and quickly? An hour later you're still in a spreadsheet and haven't written a single line of training code.
Train in Silence is the first Task-Aware MCP server for LLM fine-tuning. It doesn't just list prices; it understands your workload. Describe your training job once, and it calculates the required VRAM/FLOPs to return the cheapest, fastest, and most balanced hardware options across a dozen cloud providers -- in seconds.
Quickstart
Option A: Ask Claude Code (recommended)
Install the library and register it as a tool in Claude Code:
pip install train-in-silence claude mcp add tis --scope user -- tis-mcp
Then just ask in natural language:
> I want to run the fine-tune code in my current directory, and finish it within 20 hours. Find me the best GPU options across Vast.ai, RunPod, and Lambda.
Claude Code calls TIS behind the scenes and returns a structured recommendation -- no YAML, no config files, no manual comparison.
Option B: CLI
pip install train-in-silence tis recommend examples/request.yaml
$ tis recommend examples/request.yaml Found 5 viable configurations L
94536d16a9faOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add train-in-silence --env RUNPOD_API_KEY=${RUNPOD_API_KEY} --env VAST_API_KEY=${VAST_API_KEY} -- uvx train-in-silence{
"mcpServers": {
"train-in-silence": {
"command": "uvx",
"args": [
"train-in-silence"
],
"env": {
"RUNPOD_API_KEY": "${RUNPOD_API_KEY}",
"VAST_API_KEY": "${VAST_API_KEY}"
}
}
}
}Exposed tools (6)
6 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
dump_market_offers | read | return plugin.dump_offers(payload) |
list_providers | read | return plugin.providers(constraints) |
planner_metadata | read | return MCPMetadata() |
probe_market | read | return plugin.probe_market(payload) |
recommend_hardware | read | return plugin.recommend(payload) |
validate_request | read | return plugin.validate(payload) |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (4 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
mod = importlib.import_module(module_name)
By default, it runs at `http://127.0.0.1:8000`.
默认情况下,服务运行在 `http://127.0.0.1:8000`。
Gates applied: no_behavioural_pass.
94536d16a9fafull audit observations/trust-audit/mcp-server/hlpun__train-in-silence.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 94536d16a9fa | SAFE | B | 89 | first audit |
Questions
What is the Train in Silence MCP server?
The first Task-Aware MCP server and automated VRAM calculator for LLM fine-tuning. Instantly snipe the cheapest, fastest GPUs across 10+ cloud providers.
What tools does Train in Silence expose?
6 in total: 6 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Train in Silence safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Train in Silence need?
It reads RUNPOD_API_KEY and VAST_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Train in Silence run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on PyPI as train-in-silence.
How current is this page?
The grade is for one exact copy of the source (94536d16a9fa), read on 2026-10-07. The repository is watched and re-audited when it changes.