Mmcp.market

Citra MCP server

by SylphxAI·io.github.SylphxAI/citra·v5.0.2

Local-first PDF evidence for agents: structure, tables, OCR, and citations. SDK · CLI · MCP.

A94/100grade A
What users say
No reviews yet
Be the first
Safety scan
A94/100

full report

Adoption
Established

935 stars333 downloads/wk

Reviews

Write one

Nobody has reviewed Citra yet.

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

Citra tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it

no findings
  • Code scan4 source files scanned25/25
  • Live reliabilityno gateway calls yet and no remote to proben/a
  • Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Overall 94/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

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

<!-- Marketing surface: scannable pitch first; engineering docs below the fold. -->

Citra

Give your AI agent eyes for PDFs — with proof.

Local-first PDF evidence for agents. Structured text, tables, OCR, visual crops, and page-level citations your agent can defend — not invent.

Canonical package @sylphx/citra · bin citra · MCP io.github.SylphxAI/citra · live 5.0.0

Zero-config in one line

npx -y @sylphx/citra

No Docker. No API key. No global install. Spawns a stdio MCP server agents can use immediately.

Why Citra feels unfairly good

Plain-text PDF tools make agents guess. Citra returns an Agent Document Twin they can cite.

Five reasons teams pick Citra

  1. Zero-config — real npx MCP, not a 20-step bootstrap.
  2. Evidence, not vibes — citations agents can show a human.
  3. Local-first — PDFs stay on the machine; no required cloud vision API.
  4. Brand-sole — one package, one bin, one story (@sylphx/citra / citra).
  5. Instrument family — compose with Iris (image), Cue (video), Spine, Lookout, Locus.

See the difference

What you get

Three tools. One product surface.

Minimal call:

{
  "sources": [{ "path": "/absolute/path/to/report.pdf" }]
}

Flagship use cases

  1. Financial reports — extract table cells agents can cite by page and geometry
  2. Research papers — headings, reading order, page-level quotes
  3. Scanned documents — OCR path with evidence, not a text soup

Platforms

One optional native package is selected for your host only:

Missing native → fail closed (no silent TypeScript PDF engine).

Product docs

Shortened. The full README is on GitHub.

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

Install directly

Runs npx -y @sylphx/citra on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add citra -- npx -y @sylphx/citra
Add to Cursor

Citra: common questions

Is Citra MCP server safe?
Yes, by our scan: it is graded A (94/100). Read the Citra safety report
How do I install Citra?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Citra need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Citra maintained?
The last commit was in the last day (2026-09-20). The latest release is v5.0.2.

More from SylphxAI