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

bashCopy code
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:

jsonCopy code
{
  "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

Surfaces (MCP · CLI · SDK)

MCP (default agent path)

bashCopy code
npx -y @sylphx/citra

Claude Desktop / Cursor / VS Code / Codex

jsonCopy code
{
  "mcpServers": {
    "citra": {
      "command": "npx",
      "args": ["-y", "@sylphx/citra"]
    }
  }
}

Dual-era hosts that send server/discover before initialize (e.g. Gemini Antigravity CLI) are supported on stdio.

CLI

bashCopy code
npx -y @sylphx/citra --help

SDK

• @sylphx/citra/sdk → Citra (read / search / evidence)
• @sylphx/citra/pure-rust → low-level client helpers
• Same tools as MCP: read_pdf · search_pdf · pdf_evidence
• Requires the platform optional native package (same as MCP)

Install footprint (honest)

Compare full clean installs, not “JS wrapper tarball vs native executable”:

The native binary is multi-megabyte because it is the PDF engine. That is expected — and still a cleaner install than shipping PDF.js + a large JS tree.

Details: installed footprint comparison

Performance (method-bounded)

Controlled same-host linux-x64 dual-mode A/B vs historical @sylphx/pdf-reader-mcp@3.0.14, using registry-installed sole-Rust natives (measured on the 4.1.x lineage; method applies to current sole-Rust packages):

persistent_warm includes a process-local cache for identical local path+options. First request in a process still pays full parse cost.

Not a multi-host guarantee. Details: 4.1.0 report · claims policy

Engine note

Current production is a native Rust engine on supported platforms via a thin Node launcher.

Local-first. Five platform packages. One clean install. Fail closed without the matching native.

Unusually formed or broken ToUnicode CMaps are handled without crashing; the release binary is panic-unwind so a worker-thread panic fails the request instead of aborting the process (#608).

Engineering history and recovery pins: docs/migration.md — not the product pitch.

Product proof & links

• Website / guide
• Product proof
• Benchmark
• Installation
• npm

Stop PDF hallucinations. Give agents proof.

bashCopy code
npx -y @sylphx/citra