paper-hermes

paper-hermes

MCP server for scientific literature retrieval and summarization. Enables search, fetch, summarize, and translate arXiv papers, with subscription-based daily digests and integration with Obsidian and Telegram.

Category
Visit Server

README

Paper Hermes

MCP Server de veille scientifique. arXiv + ChemRxiv → DeepSeek → Brain Obsidian → Telegram.

Quick start

git clone https://github.com/elomokm/paper-hermes
cd paper-hermes
uv sync
export DEEPSEEK_API_KEY=sk-...

MCP Tools

Tool Args Description
search_papers query, max_results, sort_by Search arXiv
get_paper arxiv_id, include_summary Fetch paper details
summarize arxiv_id Structured summary in French
translate arxiv_id Translate abstract to French
daily_digest topic, since_days Get new papers for a topic
subscribe topic, query Subscribe to daily digests
subscriptions — List active subscriptions
unsubscribe topic Remove a subscription

Architecture

arXiv API ──→ ArxivScraper ──→ PaperSummarizer (DeepSeek) ──→ MCP Tools
ChemRxiv ──→ (Phase 4)                                           │
                                                                  ├── Obsidian Vault
                                                                  ├── Telegram (@Kadjogbe_bot)
                                                                  └── Hermes Agent / tout client MCP

Usage with Hermes Agent

hermes mcp add paper-hermes --command "uv run --directory ~/DEV/paper-hermes python -m paper_hermes.server"

Then in Hermes:

  • "cherche les derniers papiers sur les composites"
  • "resume le papier 2510.26100"
  • "abonne-moi a safran-veille"

Cron

Un cron Hermes tourne chaque matin a 08:00:

  • daily_digest pour tous les topics abonnes
  • ecrit dans ~/Documents/Brain/Projects/Safran/veille/YYYY-MM-DD-digest.md
  • livre un resume sur Telegram

Development

uv sync           # Install
uv run pytest -q  # Tests
uv run ruff check .  # Lint

Subscriptions

Gerer dans subscriptions.json ou via les MCP tools.

Topics actifs par defaut:

  • safran-veille: composites + polymeres + ML
  • ml-materials: cond-mat + ML/equivariant/GNN

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured