Local Ollama MCP side-channel for Grok Bot

Draft MCP server so Grok Bot can ask a LAN/Tailscale Ollama model for drafts and output-only DLP without replacing its cloud brain.

View source ↗
SafeScan verdict · score 62/100
Coverage
full
Checks run
Rule-based pattern scan
Files checked
6
Findings
2
Scanned
2026-11-01

Badges are rule-based checks, not guarantees: Safe means our rules found no obvious threat in the code we could read. Review code before installing.

View source ↗
Botlens score · 8 factors
62/100

Each factor is 0, ½ or 1, computed only from catalog fields (scan result, coverage, findings, script files, commit/SHA, author, last seen, install link). A heuristic summary, not a guarantee.

Scan verdict1/1Safe
Code coverage1/1full
Rule findings0/12 matched
No executable scripts0.5/12 script file(s) of 6
Pinned source1/1commit/SHA-256 recorded
Named author0/1unknown
Recently seen1/1last seen 2026-10-30
Install path0.5/1source URL only

Scan details

Findings
  • reads environment variables (where API keys live) in src/index.js: "…em } from "./redact.js"; const BASE = (process.env.OLLAMA_BASE_URL || "http://127.0.0.1:11…"
  • uploads data to a remote server in src/index.js: "…rompt }); const data = await ollamaFetch("/api/chat", { method: "POST", body: { model: useModel…"
Content SHA-256
6b0878f85354d8ee…
Commit
95ee058ae3
Files
.gitignore
LICENSE
README.md
package.json
src/index.js
src/redact.js

About

Author
primal79 ↗
Listed on
github:RongleCat/awesome-grok-bot ↗
Category (approx.)
agentops
First seen
2026-10-30
Last seen
2026-10-30
URL
github.com ↗
Get the Botlens skill