Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add alvinindra/figma-mcp-rust --skill bridge-troubleshootinggit clone --depth 1 https://github.com/alvinindra/figma-mcp-rustWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alvinindra/figma-mcp-rust/bridge-troubleshooting)<a href="https://agentmods.dev/skills/alvinindra/figma-mcp-rust/bridge-troubleshooting"><img src="https://agentmods.dev/badge/skills/alvinindra/figma-mcp-rust/bridge-troubleshooting/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alvinindra/figma-mcp-rust/bridge-troubleshooting"><img src="https://agentmods.dev/badge/skills/alvinindra/figma-mcp-rust/bridge-troubleshooting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.00633 |
| Opus 5 | $0.00034 | $0.00316 |
| Sonnet 5 | $0.00013 | $0.00127 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
bridge-troubleshooting scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bridge Troubleshooting
figma-mcp-rust talks to Figma through a companion Figma plugin over a local websocket (default ws://127.0.0.1:1994). Every tool call needs that plugin running in Figma Desktop. Use this checklist when calls fail.
Error: "plugin not connected"
The MCP server is running but no Figma plugin is attached.
- Open Figma Desktop (not the browser) and open the file to work on.
- If the plugin is not installed yet:
- Download plugin.zip from https://github.com/alvinindra/figma-mcp-rust/releases
- In Figma Desktop: Plugins, then Development, then "Import plugin from manifest"
- Select manifest.json from the extracted plugin.zip
- Run the plugin (Plugins, Development, figma-mcp-rust) and keep its window open.
- Confirm the plugin UI shows a connected state, then retry the tool call.
The plugin window must stay open; closing it disconnects the bridge.
Error: timeout
The plugin is connected but the operation took too long (30s default, 60s for get_document).
- Very large pages: prefer get_design_context with detail="minimal" or "compact" and a small depth instead of get_document.
- Scan tools (scan_text_nodes, scan_nodes_by_types) on huge trees: target a smaller subtree nodeId.
- If Figma itself is frozen or showing a dialog, dismiss it and retry.
Error: "port 1994 already in use"
Another process holds the port and is not a healthy figma-mcp-rust leader.
- If it is another figma-mcp-rust instance, that is normal: instances elect a leader on the port and the rest follow it automatically. No action needed.
- If an unrelated app owns the port, start the server with --port and update the host/port in the Figma plugin UI to match.
Multiple MCP clients (Claude Code + Cursor, etc.)
Running several clients at once is supported. The first server process binds port 1994 and becomes the leader that owns the Figma websocket; later processes detect the healthy leader and forward their requests to it. If the leader exits, a follower takes over the port on its next attempt.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 59 lines · 67 tokens per session scan A a9f1befdfa4a
bridge-troubleshooting is a skill published in the GitHub repository alvinindra/figma-mcp-rust (38 stars, last pushed 6d ago), licensed MIT. It adds 67 tokens to every session and 633 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
landing-page-conversion
Build or improve landing pages and marketing sites that convert, not just look good. Use when writing a hero, structuring a page, choosing a CTA, adding social proof, or diagnosing why a page isn't converting. Covers positioning, copy-first workflow, the above-the-fold contract, page narrative, CTAs, trust, and…
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
report-issue-framework
File a bug or feature request against @cyanheads/mcp-ts-core when you hit a framework issue. Use when a builder, utility, context method, or config behaves contrary to the documented API — not for server-specific application bugs.
report-issue-local
File a bug or feature request against this MCP server's own repo. Use for server-specific issues — tool logic, service integrations, config problems, or domain bugs that aren't caused by the framework.
render-inspect
Interpret diagnostic hints from kernelcad evaluate during a reference reconstruction. Which hints mean "missing feature", which mean "wrong arg", which mean "illegal geometry". Cross-references kernelcad-features for feature details.
clean-interface-design
Design clean, calm, uncluttered interfaces that don't read as templated AI output. Use when building or restyling any UI (web, iOS, Android, macOS) and it needs visual hierarchy, restraint, spacing discipline, one clear primary action, and a cohesive look. Covers accent color, whitespace, corner radius, type scale…