flowfigSAFE
Your coding agent draws animated diagrams from your code, and flowfig checks each box and arrow against that code. CI fails when a diagram drifts from the code. The output is one animated SVG with no script, for a README, PR or issue. Works with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Your coding agent draws the diagram from your code. flowfig checks it, and CI fails when the linked code is gone.
The problem
A diagram in a repo drifts from the code. Someone renames a function, and the diagram still shows the old name. No check fails, so no one sees the drift.
flowfig links each part of a diagram to the code that it draws. flowfig verify fails when a linked file or symbol is gone, and warns when the code does not make an edge. Run verify in CI, and a stale diagram fails the pull request.
Fail CI when the diagram drifts
A box, an edge or a message can name the code that it draws:
{ "id": "verify", "label": "verifyPassword", "source": "src/auth/login.ts#verifyPassword" }Rename verifyPassword to checkPassword. Then verify fails with exit code 1:
$ npx flowfig verify login.svg error missing-sy
54ac4a815679OBSERVED · 2026-10-11Connect
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 flowfig -- npx -y [email protected]
{
"mcpServers": {
"flowfig": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (5)
4 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
check | read | List the faults of a figure: unknown ids, text overflow, crossings, label overlap, small text, low contrast. Fix every error before render. |
diff | read | The spec changes between two figures, as a Markdown list. |
docs | read | The flowfig guide. Read it before the first render. A topic gives the detail for one kind of figure. |
render | write | Check a figure, then write it as one animated SVG file. Returns the check lines and the path. On an error, writes nothing. |
verify | read | Check the code links (source) of one or more figures: the file and the symbol must exist under root. |
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 | PASS |
| 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
- none-observed
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
.oxlintrc.json
assert.deepEqual(rules(verify(figWith('/etc/hosts'), { root })), ['missing-file']);- run: npm ci && npm run build && mkdir -p node_modules/.bin && ln -sf ../../dist/cli.js node_modules/.bin/flowfig
['bom.py', 'def login():\n pass\n', 'login'],
@types/node, @types/react, @types/react-dom, @vitejs/plugin-react, playwright, prettier, react, react-dom
Gates applied: no_behavioural_pass.
54ac4a815679full audit observations/trust-audit/mcp-server/iamalvisng__flowfig.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 | 54ac4a815679 | SAFE | B | 89 | first audit |
Questions
What is the flowfig MCP server?
Your coding agent draws animated diagrams from your code, and flowfig checks each box and arrow against that code. CI fails when a diagram drifts from the code. The output is one animated SVG with no script, for a README, PR or issue. Works with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI
What tools does flowfig expose?
5 in total: 4 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is flowfig 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 flowfig need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (54ac4a815679), read on 2026-10-11. The repository is watched and re-audited when it changes.