How do I use eprint-mcp-server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@eprint-mcp-server Find papers about lattice-based cryptography" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

eprint-mcp-server

by heewon-chung

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

IACR ePrint Archive MCP Server

License: MIT Node.js TypeScript

A Model Context Protocol (MCP) server that provides access to the IACR Cryptology ePrint Archive, enabling AI assistants to search and retrieve cryptographic research papers.

✨ Features

🔍 Smart Search: Search papers by title, abstract, author, or keywords (RSS-based filtering)
📄 Paper Details: Get comprehensive information about specific papers
📰 Recent Papers: Retrieve the latest published papers from RSS feed
🔗 Direct Links: Get web page and PDF URLs for papers
📋 Download Info: Get download information for paper PDFs
🔒 Privacy Focused: No cookies, no tracking, respects ePrint Archive guidelines

Related MCP server: ArXiv MCP Server

🚀 Quick Start

Installation

Option 1: Direct Installation

# Clone the repository
git clone https://github.com/YOUR_USERNAME/eprint-mcp-server.git
cd eprint-mcp-server

# Install dependencies and build
npm install
npm run build

Option 2: Using npx (Coming Soon)

npx eprint-mcp-server

Claude Desktop Setup

Find your Claude Desktop config file:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the server configuration:

{
  "mcpServers": {
    "eprint": {
      "command": "node",
      "args": ["/path/to/eprint-mcp-server/dist/index.js"]
    }
  }
}

Restart Claude Desktop completely (⌘+Q then reopen)

📖 Usage Examples

Search Papers

Find papers about "zero knowledge proofs"

Get Recent Papers

Show me the 10 most recent cryptography papers

Get Paper Details

Tell me about paper 2025/123

Find by Author

Find papers by Goldreich from 2024

🛠️ Development

Prerequisites

Node.js 18.0.0 or higher
npm or yarn

Setup

git clone https://github.com/YOUR_USERNAME/eprint-mcp-server.git
cd eprint-mcp-server
npm install

Development Commands

# Development with hot reload
npm run dev

# Build for production
npm run build

# Run tests
npm test

# Type checking
npm run type-check

Project Structure

eprint-mcp-server/
├── src/
│   ├── index.ts          # Main MCP server
│   ├── eprintClient.ts   # ePrint Archive API client
│   └── types.ts          # TypeScript type definitions
├── dist/                 # Compiled JavaScript output
├── tests/               # Test files
├── package.json
└── README.md

🔧 Configuration

Environment Variables

DEBUG: Set to 1 to enable debug logging
MAX_RESULTS: Maximum number of search results (default: 100)

MCP Server Options

{
  "mcpServers": {
    "eprint": {
      "command": "node",
      "args": ["./dist/index.js"],
      "env": {
        "DEBUG": "0",
        "MAX_RESULTS": "50"
      }
    }
  }
}

📚 Available Tools

Tool	Description	Parameters
`search_papers`	Search for papers	`query`, `maxResults`, `author`, `dateFrom`, `dateTo`
`get_paper`	Get paper details	`paperId`
`get_recent_papers`	Get recent papers	`limit`
`download_paper`	Get download info	`paperId`, `outputPath`
`get_paper_url`	Get paper URLs	`paperId`

🔍 Search Limitations

Currently, the ePrint Archive's search API endpoint is not publicly available, so this server uses RSS feed filtering for search functionality. This means:

✅ Search works within recent papers (last ~100 papers from RSS)
⚠️ Historical search is limited
🔄 We're working on implementing full search capabilities

🤝 Contributing

Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

IACR Cryptology ePrint Archive for providing open access to cryptographic research
Model Context Protocol for the MCP framework
The cryptographic research community

📞 Support

🐛 Issues: GitHub Issues
💬 Discussions: GitHub Discussions
📧 Email: your.email@example.com

🔄 Changelog

v1.0.0 (2025-06-25)

✨ Initial release
🔍 RSS-based search functionality
📄 Paper details retrieval
📰 Recent papers listing
🔗 Direct URL generation

Made with ❤️ for the cryptography research community

Available Tools

5 tools

download_paperC

Download a paper PDF (returns download information)

ParametersJSON Schema

Name	Required	Description	Default
`paperId`	Yes	Paper ID in format YYYY/NNN (e.g., 2024/123)
`outputPath`	No	Optional output file path (default: paperId.pdf)

TDQS

C2.8/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It says 'returns download information' but does not disclose whether the tool triggers a download or returns a URL, or any side effects. Behavioral traits are unclear.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise, but it lacks sufficient detail. It could be more informative without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, and the description does not explain the return format (URL, binary, or metadata). For a download tool, this is a significant gap. Given low complexity, the description should provide more context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (both parameters described). The description does not add extra meaning beyond the parameter descriptions already in the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Download a paper PDF', which specifies the verb and resource. It distinguishes from sibling tools like get_paper (metadata) and get_paper_url (just URL), but could be more precise about what 'returns download information' means.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like get_paper_url. The description does not mention prerequisites, when not to use, or distinguish use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_paperB

Get detailed information about a specific paper by ID

ParametersJSON Schema

Name	Required	Description	Default
`paperId`	Yes	Paper ID in format YYYY/NNN (e.g., 2024/123)

TDQS

B3.2/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It merely says 'Get detailed information' without disclosing what information is returned (e.g., metadata, full text), auth requirements, rate limits, or side effects. This is insufficient for an agent to understand the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that gets straight to the point, with no wasted words. It could be slightly improved by adding sibling differentiation, but overall it is concise and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter and no output schema, the description is adequate but not complete. It lacks usage guidelines and behavioral transparency, which are needed for an agent to use it correctly alongside siblings. The schema covers parameter details well.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers 100% of parameters and includes a clear description of paperId format (YYYY/NNN). The tool description adds no additional parameter semantics beyond what the schema already provides, so it meets the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool fetches 'detailed information about a specific paper by ID', specifying the verb (Get), resource (paper), and identifier (ID). This effectively distinguishes it from sibling tools like download_paper, get_paper_url, get_recent_papers, and search_papers, which have different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like search_papers or download_paper. It lacks any statements about prerequisites, context, or exclusions, leaving the agent without decision support.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_paper_urlB

Get direct URLs for a paper (web page and PDF)

ParametersJSON Schema

Name	Required	Description	Default
`paperId`	Yes	Paper ID in format YYYY/NNN (e.g., 2024/123)

TDQS

B3.2/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must carry burden. It does not disclose behavioral traits like read-only nature, URL expiry, authentication needs, or response format. Only states what it does without further context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence with 9 words, no redundancy, front-loaded with purpose. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and no annotations; description fails to explain return values (e.g., whether URLs are objects or strings, or if error handling is needed). Leaves agent guessing about the response structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has one parameter (paperId) with full description and format. Schema coverage is 100%, so description adds no extra meaning beyond the schema, earning baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Get direct URLs for a paper (web page and PDF)', specifying verb 'get' and resource 'paper URLs'. It distinguishes from siblings like download_paper (which may fetch content) and get_paper (which likely returns metadata).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like get_recent_papers or search_papers. Usage is implied only by the purpose, with no when-not-to-use or alternative recommendations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_recent_papersB

Get the most recently published papers

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No	Number of recent papers to return (default: 20, max: 100)

TDQS

B3.2/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, and description only states 'most recently published papers'. Lacks details on read-only nature, pagination, sorting order, or any limitations. Minimal behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: single phrase. No unnecessary words, front-loaded with the action and resource. Efficient for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, no annotations, and only one parameter, the description leaves out critical context: what papers are, source, access restrictions, response format, or any ordering guarantee. Incomplete for a tool with minimal structured fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single parameter 'limit', with default and max already documented. Description adds no extra parameter meaning beyond 'recently published'. Baseline 3 applies as schema does the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states verb 'get' and resource 'most recently published papers'. It distinguishes from sibling tools like search_papers (search vs recent) and get_paper (specific vs list).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool vs alternatives. Implied for recent papers, but no when-not-to or mention of sibling tools like search_papers for filtered queries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_papersB

Search for papers in the IACR ePrint Archive

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes	Search query for title, abstract, or keywords
`author`	No	Filter by author name (optional)
`dateTo`	No	End date filter in YYYY-MM-DD format (optional)
`sortBy`	No	Sort results by relevance, date, or title (default: relevance)	relevance
`category`	No	Filter by category (optional)
`dateFrom`	No	Start date filter in YYYY-MM-DD format (optional)
`maxResults`	No	Maximum number of results to return (default: 20)

TDQS

B3.3/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must convey behavior. It fails to mention pagination, rate limits, result format (metadata only?), or matching scope, leaving significant gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence with no wasted words, but it could be expanded with minimal cost to convey key details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema is provided, and the description does not explain the return format, limiting an agent's understanding of what to expect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the description adds no parameter meaning beyond the schema; baseline score is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Search' and the resource 'papers in the IACR ePrint Archive', which distinguishes it from sibling tools like download_paper and get_recent_papers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like get_recent_papers; usage is implied but not clarified.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

5 tool updatesv1.0.0Jul 12, 2026
- First observeddownload_paper
- First observedget_paper
- First observedget_paper_url
- First observedget_recent_papers
- First observedsearch_papers

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored 2026-07-12 07:00 across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: searching, getting details, getting URLs, downloading, and listing recent papers. No overlap.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with underscores (e.g., download_paper, search_papers). The naming is uniform and predictable.

Tool Count5/5

With 5 tools, the server is well-scoped for its domain. It provides essential operations without being too few or overly numerous.

Completeness4/5

The tool set covers search, metadata retrieval, URL access, and download. Minor gap: lack of explicit filtering by author or category, but search likely supports parameters.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

IlyaGusev-academia_mcp
ai.smithery
Search arXiv and ACL Anthology, retrieve citations and references, and browse web sources to accel…
Search Research & Data Open Data
291
paper-mcp B
io.github.MCPServings
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
Research & Data Open Data
21
morosss-sdfsdf
ai.smithery
Find academic papers across major sources like arXiv, PubMed, bioRxiv, and more. Download PDFs whe…
Research & Data Search Open Data
2
adamamer20-paper-search-mcp-openai COAuth
ai.smithery
Search and download academic papers from arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, Semantic…
Search Research & Data Open Data
25215

Related MCP Servers

IACR MCP Server
Research & Data Cryptocurrency Blockchain
doomdagadiggiedahdah
A
license
B
quality
D
maintenance
Enables programmatic access to the IACR Cryptology ePrint Archive, facilitating the search and retrieval of cryptographic research papers and metadata via a secure interface.
Updated a year ago (2025-05-16 06:16 UTC)
3
3
MIT
ArXiv MCP Server
Search Research & Data
huanongfish
A
license
B
quality
D
maintenance
Enables AI assistants to search and access arXiv research papers through a simple Message Control Protocol interface, allowing for paper search, download, listing, and reading capabilities.
Updated 2 years ago (2025-03-04 06:30 UTC)
4
7
Apache 2.0
arXiv MCP Server
Research & Data Search
Mnehmos
A
license
B
quality
Not graded
maintenance
Enables AI assistants to search and retrieve academic papers from arXiv through MCP tools, supporting search by various criteria, detailed paper information, category browsing, and PDF content extraction.
Updated a year ago (2025-06-11 22:39 UTC)
4
80 npm
2
-
ArXiv Paper MCP
Research & Data Search Documentation Access
BACH-AI-Tools
A
license
B
quality
D
maintenance
Enables searching, retrieving, and parsing academic papers from arXiv, including keyword search, PDF downloads, content extraction from HTML/PDF formats, and accessing the latest AI research papers.
Updated 9 months ago (2025-12-04 05:37 UTC)
4
6 npm
MIT