quillm-pluginSAFE
Connect your agent to Quillm: dashboards, trackers and docs your agents build and keep current. Claude, Cursor, Codex and Grok Build plugin, plus the MCP Registry entry.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Quillm keeps the small tools your agents build for your team: dashboards, trackers, decision docs and calculators. Each page lives at one address your team opens like a doc, with no AI account needed. The numbers live in datasets apart from the page, so an agent keeps a page current by adding rows, run after run, without rewriting it. Every save is test-rendered before readers see it, every revision is kept, and every change is signed by the agent that made it.
This repository connects your agent to Quillm. It holds:
- the connection to Quillm's hosted MCP server,
https://quillm.ai/mcp, which you sign in to with OAuth in your browser; - one skill,
skills/quillm/SKILL.md, that teaches the agent the habits that keep pages useful for months, including how a scheduled agent should add each run's numbers without touching the page.
The server itself is hosted by Streamfog and is not part of this repository.
Install
Step-by-step instructions for each app: https://quillm.ai/connect
The first time a tool is used, a browser window asks you to sign in to Quillm with Google, choose a workspace (or name a new one), and decide whether the agent may change things or only read. The agent then appears on the workspace's Agents page, where an admin can l
830386b45ea1OBSERVED · 2026-10-11Trust 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 | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
streamable-http
Gates applied: no_behavioural_pass.
830386b45ea1full audit observations/trust-audit/mcp-server/streamfog__quillm-plugin.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 |
|---|---|---|---|---|---|
| 2026-10-11 | 830386b45ea1 | SAFE | B | 89 | first audit |
Questions
What is the quillm-plugin MCP server?
Connect your agent to Quillm: dashboards, trackers and docs your agents build and keep current. Claude, Cursor, Codex and Grok Build plugin, plus the MCP Registry entry.
Is quillm-plugin 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 quillm-plugin need?
No credential environment variables were found in its source, so it appears to need none.
How does quillm-plugin run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (830386b45ea1), read on 2026-10-11. The repository is watched and re-audited when it changes.