plumb-mcp (tathagat22/plumb-mcp) is an MCP server listed on the M8ven Trust Index. It scores 72 out of 100, grade C. It declares 28 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Caution
72/100

plumb-mcp

Local Figma MCP server with no REST rate limits, no metered tool-call quotas, and a verification loop. Drop-in alternative to Figma's Dev Mode MCP and Framelink for Claude Code, Cursor, Windsurf — works on every plan including Free.

→ tathagat22/plumb-mcp· listed on github_topic

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

tathagat22

Source: github_topic · also listed on Glama, github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHubGlamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Tool annotations don’t match behaviour
1 read-only tool performs write/delete/exec — plumb_query (line 220: /\s(\d+(?:\.\d+)?)px/.exec(tok))
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 3 credentials: ANTHROPIC_API_KEY, FIGMA_ACCESS_TOKEN, FIGMA_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes28 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

plumb_assets
plumb_audit
plumb_brand
plumb_components
plumb_describe
plumb_design
plumb_diff
plumb_emit_react
plumb_fig_outline
plumb_fig_node
plumb_fit
plumb_import_web
plumb_node
plumb_outline
plumb_query
plumb_review
plumb_scan_references
plumb_screenshot
plumb_search
plumb_selection
plumb_source
plumb_status
plumb_studio
plumb_studio_start
plumb_studio_kit
plumb_studio_page
plumb_tokens
plumb_verify
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretANTHROPIC_API_KEYplumb-mcp fit exits with a setup message
configCHROME_PATHAlias for PLUMB_CHROME, checked second —
🔐 secretFIGMA_ACCESS_TOKENAlias for FIGMA_TOKEN, checked second —
🔐 secretFIGMA_TOKENYes — FIGMA_TOKEN.
configPLUMB_ASSETS_DIR./plumb-assets/
configPLUMB_BRIDGE_PORTScans the 31337–31346 pool
configPLUMB_BRIDGE_PORTSSame built-in pool
configPLUMB_CACHE_DIR~/.cache/plumb/
configPLUMB_CACHE_TTL_MS300000 (5 minutes)
configPLUMB_CHROMEAuto-detected from the standard install paths
configPLUMB_FIT_MODELThe built-in default
configPLUMB_LOG_FORMATHuman-readable lines
configPLUMB_LOG_LEVELinfo
configPLUMB_SESSION_NAMEThe current directory name
configPLUMB_TEST_AFTER_COMMENT
configPLUMB_TEST_AFTER_JUNK
configPLUMB_TEST_BLANK
configPLUMB_TEST_DQ
configPLUMB_TEST_EQUALS
configPLUMB_TEST_SIMPLE
configPLUMB_TEST_SPACES
configPLUMB_TEST_SQ
configPLUMB_TEST_WINS
// quality suggestions

All four hints declared on every tool

28/28 tools missing one or more hints — plumb_assets (missing: destructiveHint); plumb_audit (missing: destructiveHint); plumb_brand (missing: destructiveHint), +25 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool annotations match behaviour

1 read-only tool performs write/delete/exec — plumb_query (line 220: /\s(\d+(?:\.\d+)?)px/.exec(tok))

Either remove the readOnlyHint:true annotation, or remove the write/delete call from the tool handler.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — plumb_screenshot deletes at line 176 (unlinkSync(tempPath))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Shell command execution

1 call in production code run through a shell (src/cli/chrome.ts:59)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/tathagat22/plumb-mcp?variant=verified)](https://m8ven.ai/mcp/tathagat22/plumb-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 4f7568ff6f6bdc832aa777c3f420cdb021ba8b81
code hash: a183f918ddc0d8aadeccf57dbb4c597320e8130975ea0e38af7e150bcb3c77c9
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client