sylphxai/citra

---

The problem

Most PDF tools hand an agent a wall of text. The agent then guesses — the page number, the table grid, the region behind the claim. And a confidently wrong answer costs more than “I can’t tell.”

The difference

Locators in, citations out. A human can check the claim.

One call. Locators included.

{
  "status": "ok",
  "route":   { "engine": "rust-core", "path": "rust-read-pdf-v1" },
  "source":  { "hash": "99d313eb…", "path": "…/selectable-table-v1.pdf" },
  "results": [{
    "data": {
      "table_info": [{
        "page": 1,
        "bounding_box": { "left": 72, "top": 151, "right": 454.8, "bottom": 79 },
        "colCount": 3,
        "cellCount": 9,
        "confidence": 0.92,
        "provenance": { "engine": "pdf-reader-core", "source": "selectable_text" },
        "continuation": {
          "role": "starts",
          "groupId": "table-continuation-p1-table-1-p2-table-1",
          "signals": ["same_column_count", "repeated_header_candidate"]
        },
        "quality": {
          "completeness": 0.79,
          "cellBoundingBoxCoverage": 0.89,
          "signals": ["missing_cells", "merged_cell_candidates"]
        }
      }]
    }
  }],
  "gaps": []
}

Excerpt of a real read_pdf response against test/fixtures/differential/v3014-selectable-table-v1.pdf (paths shortened). The table is detected and linked to its continuation on page 2 — and when Citra cannot prove something, it says so in gaps instead of guessing.

Predictable defaults

Citra keeps the default path cheap and explicit. fast reads the embedded text layer and structure. quality explicitly enables OCR, rendering, and richer crops. research is not hidden inside PDF reading. Expensive work is requested, never silently triggered.

Install in 30 seconds

npx -y @sylphx/citra

No Docker. No API key. No global install. That starts a stdio MCP server your agent can use immediately.

Why teams pick Citra

• Zero-config. A real npx MCP server — not a 20-step bootstrap.
• Evidence, not vibes. Page, geometry, table cells, provenance. Citations a human can check.
• Local-first. PDFs stay on the machine. No required cloud vision API, no document upload.
• Fail closed. No matching native binary? The process refuses to start. Never a silent engine fallback.
• Native and small. A Rust PDF engine behind a thin launcher — not PDF.js plus a large JS tree.

What you get

Four tools. One surface. Few, powerful, obvious.

Full option and result reference: docs/api

Proof, method-bounded

Warm-cache figure is method-bounded: long-lived MCP server, repeated identical local read_pdf after warm-up, measured on the sole-Rust lineage (4.1.0) against TS 3.0.14. The first request in a process pays full parse cost. No multi-host extrapolation. See the performance report and claims policy.

Platforms

One optional native package is selected for your host only:

Security & trust

• Local-first — no required cloud provider; the PDF is not uploaded.
• Fail closed — a missing native binary stops the process; there is no silent TypeScript fallback.
• Panic-unwind — a malformed document (e.g. a broken ToUnicode CMap) fails the request, never the process (#608).
• Remote URL policy — a url source is a pinned, redirect-revalidated http(s) fetch, not a browser; private addresses are rejected unless MCP_PDF_ALLOW_PRIVATE_IPS=true is explicitly set (policy).
• HTTP transport is opt-in and hardened — loopback by default, MCP_API_KEY enforced before binding elsewhere, and --allow-dir restricts filesystem reach. Details: security docs · report privately per SECURITY.md.

Companion MCP tools

Each product is independent. Install only the tools your agent needs.

Documentation

---