BuildSAFE
A complete walkthrough on how to build an MCP server to serve a trained Random Forest model and integrate it with Bee Framework for ReAct interactivity.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A complete walkthrough on how to build a MCP server to serve a trained Random Forest model and integrate it with Bee Framework for ReAct interactivity.
See it live and in action 📺
Startup MCP Server 🚀
- Clone this repo
git clone https://github.com/nicknochnack/BuildMCPServer - To run the MCP server\
cd BuildMCPServer\ uv venv\ source .venv/bin/activate\ uv add .\ uv add ".[dev]"\ uv run mcp dev server.py
- To run the agent, in a separate terminal, run:\
source .venv/bin/activate\ uv run singleflowagent.py
Startup FastAPI Hosted ML Server
git clone https://github.com/nicknochnack/CodeThat-FastML\ cd CodeThat-FastML\ pip install -r requirements.txt\ uvicorn mlapi:app --reload\ Detailed instructions on how to build it can also be found here
Other References 🔗
- Building MCP Clients (used in singleflow agent)
- Original Video where I build the ML server
Who, When, Why?
👨🏾💻 Author: Nick Renotte 📅 Version: 1.x 📜 License: This project is licensed under the MIT License
d0bbd983bbcdOBSERVED · 2026-10-08Connect
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.
claude mcp add employee -- uvx employee
{
"mcpServers": {
"employee": {
"command": "uvx",
"args": [
"employee"
]
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
PredictChurn | read | This tool predicts whether an employee will churn or not, pass through the input as a list of samples. |
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 (2 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
"http://127.0.0.1:8000",
Gates applied: no_behavioural_pass, no_license.
d0bbd983bbcdfull audit observations/trust-audit/mcp-server/nicknochnack__build.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 |
|---|---|---|---|---|---|
| 2026-10-08 | d0bbd983bbcd | SAFE | B | 89 | first audit |
Questions
What is the Build MCP server?
A complete walkthrough on how to build an MCP server to serve a trained Random Forest model and integrate it with Bee Framework for ReAct interactivity.
What tools does Build expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Build 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 Build need?
No credential environment variables were found in its source, so it appears to need none.
How does Build run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as employee.
How current is this page?
The grade is for one exact copy of the source (d0bbd983bbcd), read on 2026-10-08. The repository is watched and re-audited when it changes.