Paper Distill MCP

io.github.Eclipse-Cj由 GitHub 账号 Eclipse-Cj 发布v0.2.4更新于 Oct 24, 2026

Academic paper search across 11 sources with AI curation, ranked push, Zotero and Obsidian support.

已验证STDIO仅桌面网页搜索与抓取知识与记忆沟通与协作

概览

AI 生成的概览

一个本地 MCP 服务器，让助手检索 11 个学术论文来源、排序筛选结果，并把摘要推送到聊天平台、Zotero 和 Obsidian。

可以做什么
并行检索 11 个学术来源，并与已推送论文去重，通过 CORE 和 Unpaywall 查找开放获取全文。按相关性、时效性、影响力和新颖度加权排序，支持单 AI 或双 AI 盲审的每日论文池审阅流程。通过对话配置研究主题、推送篇数、排序权重和审阅模式。生成 JSONL、个人论文库网站和 Obsidian 笔记卡片等输出。把选中的论文保存到 Zotero 库，并向 Telegram、Discord、飞书或企业微信推送格式化摘要。管理会话并在会话之间延续研究上下文。
适用场景
适合希望由助手跟踪研究主题、定期检索文献并生成精选论文摘要的研究者和学生，免去手动浏览各来源。若你已使用支持 MCP 的客户端，并希望结果进入 Zotero、Obsidian 或聊天频道，值得添加。
运行要求
以 Python 包形式本地运行（uvx、pip、Homebrew 或 Docker），需要 Python 3.10 及以上。基础检索无需密钥。可选环境变量：OPENALEX_EMAIL、CORE_API_KEY、ZOTERO_LIBRARY_ID 与 ZOTERO_API_KEY、TELEGRAM_BOT_TOKEN 与 TELEGRAM_CHAT_ID、DISCORD_WEBHOOK_URL，以及飞书和企业微信的 webhook 地址。需要访问论文 API 和推送平台的网络。
安装前请注意
会要求若干可选密钥：CORE_API_KEY、ZOTERO_API_KEY、TELEGRAM_BOT_TOKEN 和 DISCORD_WEBHOOK_URL，以及飞书和企业微信的 webhook 地址；README 建议在客户端配置的 env 字段中设置。服务器会写入你的 Zotero 库，并可通过部署钩子触发网站重建。它会把检索词和论文数据发送给第三方学术 API，并向聊天平台推送内容。项目自称处于早期开发阶段，可能不稳定。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Paper Distill MCP，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

📚 Paper Distill MCP Server

[License: AGPL-3.0] [Python 3.10+] [PyPI version] [CI]

Academic paper search, intelligent curation, and multi-platform delivery — built on the Model Context Protocol.

Compatible with all MCP clients: Claude Desktop, Claude Code, Cursor, Trae, Codex CLI, Gemini CLI, OpenClaw, VS Code, Zed, and more.

⚠️ Early development stage. Many features are still being validated and may contain bugs or instabilities. Feedback and bug reports are warmly welcome!

✨ Features

  • 🔍 11-source parallel search — OpenAlex, Semantic Scholar, PubMed, arXiv, Papers with Code, CrossRef, Europe PMC, bioRxiv, DBLP, CORE, Unpaywall
  • 🤖 Adaptive AI delivery — the agent tracks your evolving research interests and automatically refines search keywords and recommendations over time
  • 📊 4-dimensional weighted ranking — relevance × recency × impact × novelty, fully customizable weights
  • 👥 Dual-AI blind review — two AI reviewers independently shortlist papers; a chief reviewer synthesizes a final push/overflow/discard decision (optional)
  • 🧹 Scraper delegation — offload abstract extraction to a low-cost agent or API to cut token spend significantly
  • 🌐 Personal paper library site — Astro + Vercel auto-deploy; site updates within 30 seconds of each push
  • 📬 Multi-platform delivery — Telegram / Discord / Feishu / WeCom
  • 📦 Zotero integration — save papers to Zotero with one command
  • 📝 Obsidian integration — auto-generate paper note cards with Zotero backlinks; supports summary and template modes

🚀 Quick Install

bash
uvx paper-distill-mcp

That's it. Your AI client will discover all tools automatically. No API keys required for basic paper search.

No uv? → curl -LsSf https://astral.sh/uv/install.sh | sh or brew install uv

Other installation methods (pip / Homebrew / Docker / source)

pip:

bash
pip install paper-distill-mcp

Homebrew:

bash
brew tap Eclipse-Cj/tapbrew install paper-distill-mcp

Docker:

bash
docker run -i --rm ghcr.io/eclipse-cj/paper-distill-mcp

From source (developers):

bash
git clone https://github.com/Eclipse-Cj/paper-distill-mcp.gitcd paper-distill-mcppython3 -m venv .venv && .venv/bin/pip install --upgrade pip && .venv/bin/pip install -e .

🔗 Connecting to AI Clients

Claude Desktop

Add to claude_desktop_config.json (Settings → Developer → Edit Config):

json
{  "mcpServers": {    "paper-distill": {      "command": "uvx",      "args": ["paper-distill-mcp"]    }  }}

Claude Code

bash
claude mcp add paper-distill -- uvx paper-distill-mcp

Or add to .mcp.json:

json
{  "mcpServers": {    "paper-distill": {      "command": "uvx",      "args": ["paper-distill-mcp"]    }  }}

Codex CLI (OpenAI)

Add to ~/.codex/config.toml:

toml
[mcp_servers.paper-distill]command = "uvx"args = ["paper-distill-mcp"]

Gemini CLI (Google)

Add to ~/.gemini/settings.json:

json
{  "mcpServers": {    "paper-distill": {      "command": "uvx",      "args": ["paper-distill-mcp"]    }  }}

OpenClaw

bash
mcporter config add paper-distill --command uvx --scope home -- paper-distill-mcpmcporter list  # verify

To remove: mcporter config remove paper-distill

OpenClaw — install from source
bash
git clone https://github.com/Eclipse-Cj/paper-distill-mcp.git ~/.openclaw/tools/paper-distill-mcpcd ~/.openclaw/tools/paper-distill-mcpuv venv .venv && uv pip install .mcporter config add paper-distill \  --command ~/.openclaw/tools/paper-distill-mcp/.venv/bin/python3 \  --scope home \  -- -m mcp_server.servermcporter list

To remove: rm -rf ~/.openclaw/tools/paper-distill-mcp && mcporter config remove paper-distill

Other clients (Cursor, VS Code, Windsurf, Zed, Trae)

Same JSON config, different config file paths:

ClientConfig path
Claude Desktopclaude_desktop_config.json
TraeSettings → MCP → Add
Cursor~/.cursor/mcp.json
VS Code.vscode/mcp.json
Windsurf~/.codeium/windsurf/mcp_config.json
Zedsettings.json

HTTP transport (remote / hosted)

bash
paper-distill-mcp --transport http --port 8765

🎯 Getting Started

After connecting your client, tell the agent "initialize paper-distill". It will call setup() and walk you through:

  1. Research topics — describe your interests in plain language; the AI extracts keywords
  2. Delivery platform — set up Telegram / Discord / Feishu / WeCom (optional)
  3. Paper library site — build a personal paper library that updates automatically (optional)
  4. Scraper delegate — point to a low-cost agent or API for abstract extraction (recommended)
  5. Preferences — paper count, ranking weights, review mode, etc.
  6. First search — pool_refresh() populates the paper pool

All settings can be updated at any time through conversation:

  • "Push 8 papers next time"
  • "Add a new topic: RAG retrieval"
  • "Enable dual-AI blind review"
  • "Increase recency weight"

⚙️ Configuration Reference

All parameters are set via configure() or add_topic() — no manual file editing needed.

Research Topics (add_topic / manage_topics)

ParameterDescriptionDefault
keyTopic identifier (e.g. "llm-reasoning")—
labelDisplay name (e.g. "LLM Reasoning")—
keywordsSearch keywords, 3–5 recommended—
weightTopic priority 0.0–1.0 (higher = more papers)1.0
blockedTemporarily disable without deletingfalse

Paper Count & Review (configure)

ParameterOptionsDefaultDescription
paper_count_valueany integer6Papers per push
paper_count_mode"at_most" / "at_least" / "exactly""at_most"Count mode
picks_per_reviewerany integer5Shortlist size per reviewer
review_mode"single" / "dual""single"Single AI or dual blind review
custom_focusfree text""Custom selection criteria

💡 Dual blind review: two independent AI reviewers each shortlist papers; a chief reviewer makes the final push/overflow/discard call. Papers that don't make the cut are held for the next cycle rather than discarded. Enable with configure(review_mode="dual").

Ranking Weights (configure)

Controls paper scoring. The four weights should sum to approximately 1.0.

ParameterMeasuresDefault
w_relevanceKeyword and topic match0.55
w_recencyHow recently the paper was published0.20
w_impactCitation count (log-normalized)0.15
w_noveltyWhether this is the first appearance0.10

Example: "Prioritize recent papers" → configure(w_recency=0.35, w_relevance=0.40)

Scraper / Abstract Extraction Delegate (configure)

Abstract extraction is the most token-intensive step. It runs on the main agent by default, but can be delegated to a cheaper model to cut costs significantly.

ParameterValueDescription
summarizer"self"Main agent handles extraction (most expensive)
agent name (e.g. "scraper")Delegate to a low-cost sub-agent
API URLCall an external LLM API (DeepSeek, Ollama, etc.)

🔧 Strongly recommended: for 30+ papers, frontier model costs add up fast. A $0.14/M-token model handles extraction just as well. Set this with configure(summarizer="scraper").

Paper Pool & Scan Batches (configure)

ParameterDescriptionDefault
scan_batchesSplit the paper pool into N batches, reviewed over N+1 days2 (3 days)

pool_refresh() searches all 11 APIs and fills the pool. The pool is then split into batches for daily AI review — avoiding a single 60+ paper dump.

  • scan_batches=2 (default): review first half on day 1, second half on day 2, finalize on day 3
  • scan_batches=3: review one-third per day, finalize on day 4

When all batches are reviewed, the pool is exhausted and the next run triggers a fresh API search automatically.

Delivery Platforms (Environment Variables)

PlatformEnvironment variablesplatform value
TelegramTELEGRAM_BOT_TOKEN + TELEGRAM_CHAT_ID"telegram"
DiscordDISCORD_WEBHOOK_URL"discord"
FeishuFEISHU_WEBHOOK_URL"feishu"
WeComWECOM_WEBHOOK_URL"wecom"

⚠️ Important: set environment variables in the MCP client config env field, not as system environment variables. Otherwise send_push() cannot access the webhook URL and the AI may generate scripts that call webhooks directly, causing encoding issues.

Config example (WeCom + Claude Desktop):

json
{  "mcpServers": {    "paper-distill": {      "command": "uvx",      "args": ["paper-distill-mcp"],      "env": {        "WECOM_WEBHOOK_URL": "https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=YOUR_KEY"      }    }  }}

Restart the MCP client after editing the config.

Push message format (fixed):

1. Paper Title (Year)   Journal Name   - One-sentence summary   - Why it was selected   https://doi.org/...

Paper Library Site (configure)

Personal paper library website, auto-updated on every push. Built on Astro + Vercel (free tier).

ParameterDescription
site_deploy_hookVercel deploy hook URL (triggers site rebuild)
site_repo_pathLocal path to the paper-library repository

Setup steps (the AI agent will guide you):

  1. Create a repo from the paper-library-template
  2. Connect to Vercel and deploy
  3. Create a deploy hook in Vercel (Settings > Git > Deploy Hooks)
  4. Tell the agent the hook URL → saved via configure(site_deploy_hook=...)

After setup, every finalize_review() call pushes the digest JSON to the site repo and triggers a Vercel rebuild. The site updates in ~30 seconds.

Zotero Integration

Save papers to Zotero with one command. Requires a Zotero account and API key.

Getting credentials:

  1. API Key: go to zotero.org/settings/keys/new → check "Allow library access" + "Allow write access" → Save Key
  2. Library ID: go to zotero.org/settings/keys → your userID is shown at the top

Add to MCP client config:

json
{  "mcpServers": {    "paper-distill": {      "command": "uvx",      "args": ["paper-distill-mcp"],      "env": {        "ZOTERO_LIBRARY_ID": "your userID",        "ZOTERO_API_KEY": "your API key"      }    }  }}

After setup, reply collect 1 3 after a push to save papers 1 and 3 to Zotero, automatically sorted into per-topic folders.

All Environment Variables

VariableDescriptionRequired
OPENALEX_EMAILIncreases OpenAlex API rate limit; also used for Unpaywalloptional
CORE_API_KEYCORE API key (free registration)optional
DEEPSEEK_API_KEYEnhanced search via DeepSeekoptional
ZOTERO_LIBRARY_ID + ZOTERO_API_KEYSave papers to Zoterooptional
SITE_URLPaper library website URLoptional
PAPER_DISTILL_DATA_DIRData directorydefault: ~/.paper-distill/

🛠️ Tools (19 total)

Setup & Configuration

ToolDescription
setup()First call — detects fresh install and returns guided initialization instructions
add_topic(key, label, keywords)Add a research topic with search keywords
configure(...)Update any setting: paper count, ranking weights, review mode, etc.

Search & Curation

ToolDescription
search_papers(query)Parallel search across 11 sources
rank_papers(papers)4-dimensional weighted scoring
filter_duplicates(papers)Deduplicate against previously pushed papers

Daily Pipeline (paper pool mode)

ToolDescription
pool_refresh(topic?)Search all 11 APIs and build the paper pool
prepare_summarize(custom_focus?)Generate AI abstract extraction prompt
prepare_review(dual?)Generate review prompt — AI makes push/overflow/discard decisions
finalize_review(selections)Process AI decisions, update pool, output push message
pool_status()Pool status: count, scan day, exhausted or not
collect(paper_indices)Save papers to Zotero + generate Obsidian notes

Session & Output

ToolDescription
init_sessionDetect delivery platform and load research context
load_session_contextLoad historical research context
generate_digest(papers, date)Generate output files (JSONL, site, Obsidian)
send_push(date, papers, platform)Deliver to Telegram / Discord / Feishu / WeCom
collect_to_zotero(paper_ids)Save to Zotero via DOI
manage_topics(action, topic)List / disable / enable / reweight topics
ingest_research_context(text)Inherit research context across sessions

🏗️ Architecture

AI client (Claude Code / Codex CLI / Gemini CLI / Cursor / ...)    ↓ MCP (stdio or HTTP)paper-distill-mcp    ├── search/         — 11-source academic search (with OA full-text enrichment)    ├── curate/         — scoring + deduplication    ├── generate/       — output (JSONL, Obsidian, site)    ├── bot/            — push formatting (4 platforms)    └── integrations/   — Zotero API

The server does not call any LLM internally. Search, ranking, and deduplication are pure data operations. Intelligence comes from your AI client.

📖 Paywalled Papers & Open Access

The system searches all papers by default (including subscription journals) and maximizes free full-text access through:

  1. CORE — world's largest OA aggregator (200M+ papers), covering author self-archived versions from institutional repositories
  2. Unpaywall — after merging results, automatically looks up legal free PDFs via DOI (preprints, green OA, author versions)

For papers with no free version, the system returns a DOI link. If you have institutional VPN access, clicking the DOI link while connected is usually enough — publishers identify your institution by IP.

open_access_url priority: arXiv > CORE > Unpaywall > OpenAlex > Semantic Scholar > Papers with Code

❓ FAQ

Review stage hangs / no response for 30+ minutes

Symptom: the review prompt generated by prepare_review() causes the AI client to hang or time out.

Cause: too many candidate papers in the pool (e.g. 80–100), making the prompt exceed the client's context window or output token limit. VS Code Copilot and some IDE plugins have limited context capacity.

Solutions (pick one):

  1. Increase scan_batches (recommended) — split the pool into more batches: 
    configure(scan_batches=5)
  2. Reduce topics or keywords — fewer topics → fewer search results → smaller pool.
  3. Switch to a higher-context client — Claude Code (200k), Claude Desktop (200k), or Cursor handle long prompts better.

Install error: Requires-Python >=3.10

Python 3.10+ is required. macOS ships with Python 3.9 by default — install a newer version with brew install [email protected] or use uv.

Docker image fails to pull (mainland China)

ghcr.io is blocked in mainland China. Use pip with a Chinese mirror:

bash
pip install paper-distill-mcp -i https://pypi.tuna.tsinghua.edu.cn/simple

🧑‍💻 Development

bash
git clone https://github.com/Eclipse-Cj/paper-distill-mcp.gitcd paper-distill-mcppython3 -m venv .venv && .venv/bin/pip install --upgrade pip && .venv/bin/pip install -e .python tests/test_mcp_smoke.py   # 9 tests, no network required

📄 License

This project is licensed under AGPL-3.0. See LICENSE for details.

Unauthorized commercial use is prohibited. For commercial licensing inquiries, contact the author.

📬 Contact

Bug reports and feature requests are welcome. The project is in active early development — thank you for your patience and support 🙏

来源：README.md，提交 90096c6

工具

0
SourceWeft 尚未在沙箱中启动过该软件包，因此其工具未知。

版本历史

1
  1. v0.2.4最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手；SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分