{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_yjbuhhvctst3","handle":"zra-mcp","url":"https://wellknown.network/agents/zra-mcp","links":{"self":"https://wellknown.network/agents/zra-mcp/record.json","html":"https://wellknown.network/agents/zra-mcp","markdown":"https://wellknown.network/agents/zra-mcp/record.md","api":"https://wellknown.network/api/v1/agents/zra-mcp","status":"https://wellknown.network/api/v1/agents/zra-mcp/status","claim":"https://wellknown.network/agents/zra-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/zra-mcp/claim.json","badge":"https://wellknown.network/agents/zra-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:zra-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"zra-mcp","summary":"AI-powered Zotero research assistant — a standalone MCP server with 36 tools for literature search, bilingual retrieval, reading analysis, citation management, and review writing.","description":"# Zotero Research Assistant\n\n[![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue.svg)](https://www.python.org/)\n[![License: MIT](https://img.shields.io/badge/license-MIT-green.svg)](./LICENSE)\n[![MCP](https://img.shields.io/badge/protocol-MCP-purple.svg)](https://modelcontextprotocol.io/)\n\n**[English](./README.md)** | **[中文](./README_zh.md)**\n\n---\n\n> **Turn your Zotero library into an AI-searchable knowledge base.**\n>\n> A production-grade RAG pipeline — from PDF chunking to bilingual semantic retrieval — that runs entirely on your machine. Find papers by meaning, not just keywords. Works with any MCP-compatible AI client.\n\n---\n\n## Table of Contents\n\n- [RAG Pipeline](#rag-pipeline) — the core\n- [Quick Start](#quick-start)\n- [Client Setup](#client-setup)\n- [MCP Tools (36)](#mcp-tools-36)\n- [Configuration](#configuration)\n- [Tables & Figures](#tables--figures)\n- [Other Features](#other-features)\n- [Updating](#updating)\n- [Troubleshooting](#troubleshooting)\n- [Architecture](#architecture)\n- [Acknowledgments](#acknowledgments)\n- [License](#license)\n\n---\n\n## RAG Pipeline\n\nThe RAG pipeline is the heart of this project. Every design decision — from chunking strategy to embedding backend to diversity reranking — is optimized for one goal: **maximize retrieval precision for academic papers on consumer hardware.**\n\n### Pipeline Overview\n\n```\nYour Zotero Library\n      │\n      ▼\n┌──────────────────────────────────────────────────────┐\n│ 1. PDF EXTRACTION (PyMuPDF)                          │\n│    Page-by-page text extraction, parallel processing │\n├──────────────────────────────────────────────────────┤\n│ 2. TEXT CLEANING (52 regex rules)                    │\n│    Strips journal boilerplate: article-info blocks,  │\n│    CLC numbers, funding footers, page numbers, DOIs  │\n│    EN journals (9 rules) · CN journals (24) · Univ. (19) │\n│    Avg 10.6% line removal (CN 19.3%, EN 7.2%)       │\n├──────────────────────────────────────────────────────┤\n│ 3. SEMANTIC CHUNKING …","publisher":{"name":"qiobn","url":null},"homepage":"https://github.com/qiobn/zotero-research-assistant","repository":"https://github.com/qiobn/zotero-research-assistant","version":"0.4.9","license":"MIT","protocols":["mcp"],"tags":["ai","citation","literature-review","mcp","model-context-protocol","research","semantic-search","zotero"],"pricing":null,"endpoints":[{"url":"pypi:zra-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"code.review","name":"Code Review","confidence":1,"provenance":"derived"},{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"derived"},{"slug":"research.academic","name":"Academic Research","confidence":0.802,"provenance":"derived"}],"categories":["code","data","research"],"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":"zra-mcp","registry":"pypi","observedAt":"2026-09-10T16:24:38.408Z","publishedAt":"2026-08-10T16:21:38.424562Z","latestVersion":"0.4.9"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"zra-mcp","url":"https://pypi.org/project/zra-mcp/","firstSeenAt":"2026-09-10T16:24:06.034Z","fetchedAt":"2026-09-10T16:24:06.034Z","normalizedAt":"2026-09-10T16:24:06.034Z"}]},"firstSeenAt":"2026-09-10T16:24:06.034Z","updatedAt":"2026-09-10T16:24:38.408Z"}