A
licenseA
qualityD
maintenanceEnables AI agents to securely read and extract information from PDF files including text content, metadata, and page counts from both local files and URLs within the project context.
1
1,638 npm
MIT
smart-read-mcp
Officialby SylphxAI
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@smart-read-mcpRead the file ~/documents/project-plan.md and extract its metadata."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Smart Read MCP
Universal read path for agents — local files and guarded remote URLs resolved into the Smart Reader stack.
Status: planned — repository scaffold; MCP tools not shipped yet.
Part of the Sylphx Reader portfolio.
SOTA family roadmap: docs/roadmap/sota-family-roadmap.md.
Sibling | Role |
PDF Agent Document Twin (production) | |
Image Agent Media Twin | |
Video Agent Media Twin | |
Format sniff + delegate | |
Universal path (local + guarded URL) | |
Shared evidence schema |
Read vs interpret
Read (this repo): extract facts, metadata, transcripts, regions, and timelines with provenance — no generative LLM required.
Interpret (out of scope): summarize, classify, or answer open questions — belongs in the agent or an optional remote provider adapter.
Related MCP server: ParseJet - Universal File & URL Parser
Planned MCP surface
Primary tool: read_path
Quick start (after v0.1.0)
npx @sylphx/smart-read-mcpLicense
MIT © SylphxAI
This server cannot be deployed
Maintenance
ActivityStale
ResponsivenessNo issues
Related MCP Connectors
Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.
Deterministic web intake and data utilities for autonomous agents.
Artifact store for AI agents — read, write, and search files by path; share by rendered URL.
Document conversion and OCR for AI agents: PDF, Office docs, images to text.
Related MCP Servers
- AlicenseBqualityCmaintenanceParse any file or URL into structured text. Extract text from PDF, DOCX, YouTube, web pages, images, and 25+ formats via one API. Tools: parse_url, parse_file, get_youtube_transcript.32 npmMIT
- AlicenseNot gradedqualityFmaintenanceReads PDF, image, or video files by sniffing format and delegating to specialized sibling MCP servers, extracting facts and metadata without LLMs.41 npmMIT
- FlicenseNot gradedqualityCmaintenanceEnables LLM agents to securely explore, read, search, and analyze text-based files within a sandboxed environment.-