pdf-reader-mcp
PDF intelligence layer for AI agents providing features such as evidence-first extraction and OCR
GraphCanon updated 2w · GitHub synced 3w
Decision brief
pdf-reader-mcp acts as an intelligence layer for PDFs to support AI agents in document handling, offering features like evidence-first extraction and OCR with a focus on accuracy and provenance via the MCP server.
Good fit when
- When working within environments that integrate Claude, Cursor, VS Code, or any other MCP client where precision in extracting visual crops and ensuring provenance through OCR is required.
- If your AI workflow necessitates trust reports and benchmark-gated releases to maintain high standards of data integrity and reliability.
Avoid when
- For situations where you do not require the specific capabilities like evidence-first extraction or trust reporting that distinguish pdf-reader-mcp from other general OCR tools.
- In scenarios where only plain text extraction is needed without advanced features such as document intelligence, visual crops, or PDF to Markdown conversion.
Observed Jul 15, 2026 · Source: enrich:decision_facts
Verify the decision
Adoption
Package downloads where a registry match exists. GitHub stars (839) are secondary evidence.
- npm downloads (30d)
- 31,968·npm downloads API·3w
Maintenance and security
Full trust report- Maintenance
- Very active (0d since push)
- As of 3w
- Provenance
- Not a fork · Organization account
- As of 3w
- Security (OSV)
- No lockfile
- As of 2w
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
npm install pdf-reader-mcpSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
SylphxAI/pdf-reader-mcp is an Agent Document Twin designed for AI Agents to handle document intelligence tasks with accuracy and provenance, featuring OCR, evidence-first extraction, and more. It supports Claude, Cursor, VS Code, and any MCP client via the MCP server.
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Jul 27, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Jul 27, 2026
- CLI
- CLI entrypoint
Source: package.json:bin|scripts · Jul 27, 2026
- MCP server
- Ships MCP server
Source: package.json:@modelcontextprotocol/* · Jul 27, 2026
- Languages
- typescript, javascript
Source: github.language+package.json · Jul 27, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Jul 27, 2026)
npm install -g @sylphx/pdf-reader-mcpSource link
Source: README excerpt (regex_v1, Jul 27, 2026)
**Claude Desktop / Cursor / VS Code / any MCP client**Source link
Source: README excerpt (regex_v1, Jul 27, 2026)
**Claude Desktop / Cursor / VS Code / any MCP client**Source link
Source: README excerpt (regex_v1, Jul 27, 2026)
**Claude Desktop / Cursor / VS Code / any MCP client**Source link
Tags
README
Install (30 seconds)
npm install -g @sylphx/pdf-reader-mcp
Or pin the current release:
npm install -g @sylphx/pdf-reader-mcp@4.1.1
One native binary is installed for your platform only (not all five).
| Platform | Native package (auto optionalDependency) |
|---|---|
| macOS arm64 | @sylphx/pdf-reader-mcp-darwin-arm64 |
| macOS x64 | @sylphx/pdf-reader-mcp-darwin-x64 |
| Linux x64 | @sylphx/pdf-reader-mcp-linux-x64-gnu |
| Linux arm64 | @sylphx/pdf-reader-mcp-linux-arm64-gnu |
| Windows x64 | @sylphx/pdf-reader-mcp-win32-x64-msvc |
Missing native package → fail closed (no silent engine switch).
Quick start
Claude Code
claude mcp add pdf-reader -- npx @sylphx/pdf-reader-mcp
Claude Desktop / Cursor / VS Code / any MCP client
{
"mcpServers": {
"pdf-reader": {
"command": "npx",
"args": ["@sylphx/pdf-reader-mcp"]
}
}
}
Stdio / HTTP
pdf-reader-mcp
MCP_TRANSPORT=http pdf-reader-mcp
Install footprint (honest product comparison)
Compare full clean installs, not “JS wrapper tarball vs native executable”:
| Metric (measured clean install, linux-x64) | Historical TS 3.0.14 | Sole-Rust 4.1.0 |
|---|---|---|
| Main package on disk | ~403 KB | ~77 KB |
Full node_modules | ~82.3 MiB | ~24.4 MiB (~3.4× smaller) |
| Installed files | 4,101 | 20 (~205× fewer) |
| Production npm dependency graph | PDF.js + MCP TS SDK + more | {} + one platform native |
The native binary is multi-megabyte because it is the PDF intelligence engine (parser, server, rendering/table/OCR routing). That is expected and still yields a cleaner, smaller install than shipping PDF.js + a JS dependency tree.
Details: installed footprint comparison
License
MIT
If this saves your agents from PDF hallucinations, star the repo and share a demo with your team.
For agents
This page has a .md twin and JSON over the API.