{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_q42cmuzfzk2z","handle":"docsray-mcp","url":"https://wellknown.network/agents/docsray-mcp","links":{"self":"https://wellknown.network/agents/docsray-mcp/record.json","html":"https://wellknown.network/agents/docsray-mcp","markdown":"https://wellknown.network/agents/docsray-mcp/record.md","api":"https://wellknown.network/api/v1/agents/docsray-mcp","status":"https://wellknown.network/api/v1/agents/docsray-mcp/status","claim":"https://wellknown.network/agents/docsray-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/docsray-mcp/claim.json","badge":"https://wellknown.network/agents/docsray-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/docsray-mcp/history","tools":"https://wellknown.network/api/v1/agents/docsray-mcp/tools"},"ard":{"identifier":"urn:air::server:docsray-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"docsray-mcp","summary":"AI-powered document perception and analysis MCP server with intelligent provider selection","description":"# 🔍 Docsray MCP Server\n\n[![PyPI](https://img.shields.io/pypi/v/docsray-mcp)](https://pypi.org/project/docsray-mcp/)\n[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)\n[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)\n[![MCP](https://img.shields.io/badge/MCP-Compatible-green.svg)](https://github.com/anthropics/mcp)\n[![Status](https://img.shields.io/badge/Status-Working-brightgreen.svg)](https://github.com/docsray/docsray-mcp)\n[![Netlify Status](https://api.netlify.com/api/v1/badges/6065d1ba-7e6c-49fa-a97e-9cada2cbc00a/deploy-status)](https://app.netlify.com/projects/docsray/deploys)\n\n**Docsray** is a powerful Model Context Protocol (MCP) server that gives AI assistants like Claude advanced document perception capabilities. Extract text, navigate pages, analyze structure, and understand any document with ease.\n\n**✅ Status: Published to PyPI and TestPyPI - Working in Cursor, Claude Desktop, and other MCP clients**\n\n## ✨ Features\n\n### 🎯 Five Powerful Tools\n\n1. **`docsray_peek`** - Quick document overview with format detection and provider capabilities\n2. **`docsray_map`** - Generate comprehensive document structure maps with caching\n3. **`docsray_xray`** - AI-powered deep analysis extracting entities, relationships, and insights\n4. **`docsray_extract`** - Extract content in multiple formats (markdown, text, JSON, tables)\n5. **`docsray_seek`** - Navigate to specific pages, sections, or search for content\n\n### 🔌 Multi-Provider Architecture\n\n- **PyMuPDF4LLM** - Lightning-fast PDF processing (✅ Implemented)\n  - Fast markdown extraction\n  - Basic table detection\n  - Multi-page support\n  - Always enabled as fallback\n\n- **LlamaParse** - Deep document understanding with LLMs (✅ Implemented)\n  - AI-powered entity extraction\n  - Custom analysis instructions\n  - Comprehensive caching in .docsray directories\n  - Rich format preservation (markdown, i…","publisher":null,"homepage":"https://docsray.dev","repository":"https://github.com/xingh/docsray-mcp/issues","version":"0.3.3","license":null,"protocols":["mcp"],"tags":["mcp","document","pdf","ai","llm","analysis","extraction","llamaparse","mistral-ocr","ocrmypdf","tesseract"],"pricing":null,"endpoints":[{"url":"pypi:docsray-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"documents.ocr","name":"OCR","confidence":1,"provenance":"derived"},{"slug":"documents.extraction","name":"Data Extraction","confidence":1,"provenance":"declared"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":0.791,"provenance":"derived"}],"categories":["dev","documents"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"docsray-mcp","registry":"pypi","observedAt":"2026-09-15T13:22:01.597Z","publishedAt":"2025-08-06T23:41:05.392323Z","latestVersion":"0.3.3"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"docsray-mcp","url":"https://pypi.org/project/docsray-mcp/","firstSeenAt":"2026-09-09T14:32:03.336Z","fetchedAt":"2026-09-15T13:20:39.646Z","normalizedAt":"2026-09-15T13:20:39.646Z"}]},"firstSeenAt":"2026-09-09T14:32:03.336Z","updatedAt":"2026-09-15T13:22:01.597Z"}