Sage

Provides access to academic papers and journals, enabling research-focused responses with search, filtering, and full-text retrieval via MCP tools.
  • typescript

0

GitHub Stars

typescript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "xenovative-sagemcp": {
      "command": "node",
      "args": [
        "C:/AIapps/SageMCP/dist/index.js"
      ],
      "env": {
        "SAGE_DB_PATH": "./data/sage.db"
      }
    }
  }
}

You can run Sage MCP as a local server to give large language models access to academic papers. It provides full-text search, topic and publication filtering, and easy paper retrieval so you can build research-grounded responses and analyses with up-to-date academic content.

How to use

You interact with Sage MCP through a client that speaks the Model Context Protocol. Start the local server, then list the available tools to see what you can do. You can search for papers, fetch full papers by ID, browse topics and journals, filter by topic or publication, and add new papers if you need to expand the knowledge base.

How to install

Prerequisites: You must have Node.js 18+ installed (Node.js 20 LTS is recommended) and npm 9+. You will run the server locally, seed the database, then start the server.

# 1) Install dependencies
npm install

# 2) Build the project
npm run build

# 3) Seed the database with sample papers (optional)
npm run seed

# 4) Start the server
npm start
# The server should output: Sage MCP Server running on stdio

Configuration and environment

You can customize where the database is stored by setting an environment variable. The available variable is SAGE_DB_PATH, which lets you point to a custom SQLite database file.

{
  "mcpServers": {
    "sage": {
      "command": "node",
      "args": ["C:/AIapps/SageMCP/dist/index.js"],
      "env": {
        "SAGE_DB_PATH": "D:/Research/my_papers.db"
      }
    }
  }
}

Using tools and workflows

Once the server is running, you can connect with an MCP client and access the available tools. The core tools include searching papers, retrieving full paper content, listing topics, listing publications, and filtering by topic or by publication. You can also add new papers via the provided tool or XML import when you need to expand the dataset.

Adding your own papers

You can grow the knowledge base by adding papers through the built‑in add_paper tool, importing an XML file, or programmatically feeding paper data. This enables you to tailor the dataset to your research needs.

# Example of adding a paper programmatically
{
  "title": "Your Paper Title",
  "authors": "Author One, Author Two",
  "abstract": "Paper abstract...",
  "content": "Full paper content...",
  "publication": "Journal Name",
  "publication_date": "2024-01-15",
  "doi": "10.1234/example",
  "url": "https://example.com/paper",
  "topics": "Topic1, Topic2",
  "keywords": "keyword1, keyword2, keyword3"
}

Notes on deployment and troubleshooting

If you plan to run Sage MCP on a server or in a VPS, follow the standard deployment steps for Node.js applications, ensuring the server starts correctly and the database file is accessible to the process. If you encounter issues, rebuild the TypeScript sources, verify that environment variables are set, and restart the server. For database problems, reseed the dataset or re-import from XML as needed.

Security and maintenance

Keep dependencies up to date with regular npm install and rebuilds. Restrict access to the server to trusted clients and consider rotating any exposed API keys or sensitive configuration values if you introduce remote access.

Appendix: Tools you can use

The available tools include: search_papers for semantic or keyword searches across all papers, get_paper to retrieve the full content by ID, list_topics to browse topics, list_publications to browse journals, get_papers_by_topic to filter by topic, get_papers_by_publication to filter by publication, and add_paper to add new papers to the database.

Troubleshooting quick checks

Cannot find module errors can often be resolved by rebuilding TypeScript sources. If the client interface doesn’t show tools after connecting, verify the client configuration, restart the client completely, and check logs for any errors. For database errors, reset or reseed the database as described earlier.

Available tools

search_papers

Semantic/keyword search across all papers

get_paper

Retrieve full paper content by ID

list_topics

Browse available research topics

list_publications

Browse available journals/sources

get_papers_by_topic

Filter papers by topic

get_papers_by_publication

Filter papers by journal

add_paper

Add new papers to the database

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
Sage MCP Server - xenovative/sagemcp | VeilStrat