MCP.Market

SciFig MCP server

online · 100% uptime
by lilingm963·io.github.lilingm963/scifig·v1.0.0

Create scientific illustrations, data charts and flowcharts with your SciFig account.

A97/100grade A
What users say
No reviews yet
Be the first
Safety scan
A97/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed SciFig yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

SciFig tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 351ms (auth required)20/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityOAuth resource metadata advertised on 40115/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 97/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How SciFig compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
97/100
higher than 98% of 48,255 servers
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
228 ms
faster than 59% of 30,031 servers

Install SciFig in Claude Code, Cursor or VS Code

claude mcp add --transport http scifig https://mcp.scifig.ai/mcp
Add to Cursor

What the publisher says

From the SciFig repository's README, as published. We do not edit it. Read it on GitHub

SciFig · AI Scientific Figures, Data Charts and Flowcharts

Bring scientific illustration, data visualization and research workflows into your AI assistant with SciFig.

Three connected workspaces

  • Illustration: turn research ideas and references into scientific illustrations, diagrams and graphical abstracts.
  • DataChart: plot your tables as scientific charts and refine them through conversation.
  • FlowChart: build editable flowcharts for methods, protocols and study workflows.

Start with research assets, figure templates and color palettes, then refine the result with text and label editing, regional edits, background tools, recoloring, upscaling and SVG vectorization. Prepare work for publication with downloadable license certificates and export formats for papers and presentations.

Paid credits from subscriptions and credit packs never expire. Annual plans start at $8.33 per month, billed annually. Your website and AI assistant use the same SciFig account and credit balance.

This plugin brings the hosted SciFig MCP server together with four focused workflow skills.

Claude Code

Add this repository as a marketplace, then install the plugin:

/plugin marketplace add lilingm963/scifig-plugins
/plugin install scifig@scifig-plugins

Open /mcp, select SciFig, and sign in through OAuth. Review the requested permissions before allowing access. You can disconnect the assistant at any time in SciFig Settings → API Keys → Connected apps.

To connect only the remote server, without these skills:

claude mcp add --transport http scifig https://mcp.scifig.ai/mcp

Codex and other clients

codex mcp add scifig --url https://mcp.scifig.ai/mcp
codex mcp login scifig

First inspect existing configuration and keep unrelated servers. Claude, ChatGPT and Cursor can connect a custom remote MCP server at https://mcp.scifig.ai/mcp. Client availability depends on your account and plan. The portable plugin.json and mcp.json are included for hosts supporting Agent Plugins; the Claude manifest remains under .claude-plugin/.

Full instructions: Install guide · API documentation.

Tools and permissions

External uploads additionally require files:write. Permissions are independent; granting generation does not automatically grant uploads, job reads or balance access. offline_access allows an OAuth client to refresh after you sign out of the website and is not a business permission.

Skills

  • scifig-onboarding: connect, check permissions and handle authentication errors.
  • scifig-figures: illustrations, image editing and flowcharts.
  • scifig-charts: plot only the user's supplied data and edit charts.
  • scifig-export: choose formats, DPI and upscaling for the intended output.

Publication and export workflow

Generate a figure, refine the result, and export it for your paper, poster or presentation. Illustrations support editing and image post-processing; DataChart returns publication formats from your supplied data; FlowChart keeps diagrams editable as SVG.

The same credit balance works across the website and MCP. Browse the current plans for included credits and features. Balance checks, OCR and supported PNG/PDF/TIFF/PPTX conversions are free.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

SciFig: common questions

Is SciFig MCP server safe?
Yes, by our scan: it is graded A (97/100). Read the SciFig safety report
How do I install SciFig?
It runs remotely at mcp.scifig.ai. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does SciFig need an API key?
No key to paste: it signs you in with OAuth when your client connects.
Is SciFig maintained?
The last commit was 20 days ago (2026-10-15). The latest release is v1.0.0.
Is SciFig up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does SciFig compare with other MCP servers?
safety score 97/100 (higher than 98% of 48,255 servers); uptime 100% (of our recent checks; the typical remote server answers 100%); response time 228 ms (faster than 59% of 30,031 servers). Full comparison.