GrainulatorBLOCK
Research that compiles.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Grainulator
Evidence and verification for the model you already use.
Keep the evidence. Challenge the answer. Know what to do next. A shared workflow for research, engineering, and model-assisted work.
Quick start · Installation · Upgrading · Tools · Agent setup · Changelog
What it adds
Good models still need a way to keep track of evidence, revisit assumptions, and verify their work. Grainulator gives them that process, with a local ledger that stays with the task as it moves between models and sessions.
1feacb79e3d6OBSERVED · 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 barn --env CONFLUENCE_SPACE_KEY=${CONFLUENCE_SPACE_KEY} --env CONFLUENCE_TOKEN=${CONFLUENCE_TOKEN} --env OPENAI_API_KEY=${OPENAI_API_KEY} --env OPENROUTER_API_KEY=${OPENROUTER_API_KEY} -- npx -y @grainulation/[email protected]{
"mcpServers": {
"barn": {
"command": "npx",
"args": [
"-y",
"@grainulation/[email protected]"
],
"env": {
"CONFLUENCE_SPACE_KEY": "${CONFLUENCE_SPACE_KEY}",
"CONFLUENCE_TOKEN": "${CONFLUENCE_TOKEN}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"OPENROUTER_API_KEY": "${OPENROUTER_API_KEY}"
}
}
}
}Exposed tools (9)
8 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Researcher | write | Run research sprints, grow evidence, write briefs |
clipboard | read | Copy formatted output to system clipboard |
csv | read | Export claims JSON to CSV |
grainulation | read | Structured research for decisions that satisfice. |
json-ld | read | Export claims JSON to JSON-LD for semantic web |
markdown | read | Convert HTML artifacts to clean Markdown |
pdf | read | Export HTML or Markdown to PDF |
static | read | Generate a static site from sprint outputs |
wait | read | Synthetic interruption test: record that the call started, then wait until the host process is interrupted. No external effects. |
Trust audit
BLOCKgrade D · trust 65/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (6 observation(s))
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
["169.254.0.0", 16], // link-local (includes AWS IMDS 169.254.169.254)
/* IMPORTANT: Always include text label (e.g., "Critical", "High") inside the .sev span */
preview: 'grainulator preview\nStart the local playground preview on http://127.0.0.1:4517.',
const secret = 'synthetic-recovery-key-do-not-export';
JSON.stringify([{ secret: "outside-private-fixture" }]),{ secret: "outside-private-fixture" },- **farmer**: inline `style="color:#fff"` on branded `<strong>` wordmarks
.node-version
.prettierignore
.nojekyll
.prettierignore
.nojekyll
import { setVerbose, vlog as barnVlog } from "../../shared/lib/cli.js";import { findSprintFiles } from "../../shared/lib/sprints.js";import { tryReadStaticFile } from "../../shared/lib/fs-safe.cjs";import { resolveSafe } from "../../shared/lib/paths.js";sock.write("GET /../../etc/passwd HTTP/1.0\r\nHost: localhost\r\n\r\n");# Open http://127.0.0.1:4517/playground/ and choose Open session.
The preview server prints http://127.0.0.1:4517 (Grainulator) and http://127.0.0.1:4518 (Grainulation). Grainulator has a refreshed homepage and a configurable research playground at `/playground`. Th
Open http://127.0.0.1:4517/playground/ and import the session you exported. Enter a provider key locally or configure `OPENAI_API_KEY` / `OPENROUTER_API_KEY` in the preview server's environment.
Start `npm run dev`, then open http://127.0.0.1:4517/playground/. The playground uses a static background, the mascot wordmark, and a home link in the top-right corner. The older `/research.html` and
@grainulation/barn
@grainulation/barn
@grainulation/barn
@grainulation/barn
Gates applied: no_behavioural_pass.
1feacb79e3d6full audit observations/trust-audit/mcp-server/grainulation__grainulator.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 | 1feacb79e3d6 | BLOCK | D | 65 | first audit |
Questions
What is the Grainulator MCP server?
Research that compiles.
What tools does Grainulator expose?
9 in total: 8 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Grainulator safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (65/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Grainulator need?
It reads CONFLUENCE_SPACE_KEY, CONFLUENCE_TOKEN, OPENAI_API_KEY and OPENROUTER_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 current is this page?
The grade is for one exact copy of the source (1feacb79e3d6), read on 2026-10-07. The repository is watched and re-audited when it changes.