What can you do with this server?

This MCP server provides AI-powered academic paper search and Litra.ai account management. * search_papers: Search academic papers by natural language query, with AI relevance scoring (1-10), AI-generated summaries, optional year range filtering, and configurable result count (10-30). * search_author: Find papers by author name, returning author profile (affiliation, h-index) and publications, with optional result limit (1-50). * check_credits: Check your Litra.ai credit balance and subscription plan, with no parameters required.

How do I use litra-paper-search-mcp?

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., "@litra-paper-search-mcp search for recent papers on quantum entanglement" 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.

litra-paper-search-mcp

by akkylab

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

litra-paper-search-mcp

⚠️ This project is no longer maintained.
Litra AI discontinued its public API and MCP server on 2026-09-04. The API endpoints this server calls no longer exist, so it cannot work even with a valid API key.
Why: what makes Litra AI useful is the way it shows papers — citation trees, lineage of references, year distributions, research maps. MCP can only carry text, so none of that reaches you. A plain list of papers is something other services already provide. We chose to focus on the web app, where the value actually lands.
Please use the web app at https://litra-ai.com instead.
This repository stays online, read-only, for reference.

MCP server for Litra.ai – AI-powered academic paper search with relevance scoring and summarization.

Features

search_papers – Search academic papers with AI-powered relevance scoring (1-10) and summarization. Year filtering is available but currently experimental (see Known limitations).
search_author – Search papers by author name. Returns author profile (affiliation, h-index) and publications.
check_credits – Check your Litra.ai credit balance and subscription plan.

Related MCP server: semantic-scholar-mcp

Prerequisites

Node.js 18 or higher
A Litra.ai account with a paid plan (Mini or above)

Get Your API Key

Sign in at litra-ai.com/account
Navigate to the API Keys section
Click Create API Key and copy the key (it is shown only once)

Setup

Claude Code

claude mcp add litra-paper-search -- npx -y litra-paper-search-mcp

Then set the environment variable LITRA_API_KEY in your shell or Claude Code config.

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "litra-paper-search": {
      "command": "npx",
      "args": ["-y", "litra-paper-search-mcp"],
      "env": {
        "LITRA_API_KEY": "litra_xxxxxxxxxxxx"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "litra-paper-search": {
      "command": "npx",
      "args": ["-y", "litra-paper-search-mcp"],
      "env": {
        "LITRA_API_KEY": "litra_xxxxxxxxxxxx"
      }
    }
  }
}

Windsurf

Add to .windsurf/mcp.json:

{
  "mcpServers": {
    "litra-paper-search": {
      "command": "npx",
      "args": ["-y", "litra-paper-search-mcp"],
      "env": {
        "LITRA_API_KEY": "litra_xxxxxxxxxxxx"
      }
    }
  }
}

Cline

Add to .cline/mcp_settings.json:

{
  "mcpServers": {
    "litra-paper-search": {
      "command": "npx",
      "args": ["-y", "litra-paper-search-mcp"],
      "env": {
        "LITRA_API_KEY": "litra_xxxxxxxxxxxx"
      }
    }
  }
}

GitHub Copilot (VS Code)

Add to .vscode/mcp.json:

{
  "servers": {
    "litra-paper-search": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "litra-paper-search-mcp"],
      "env": {
        "LITRA_API_KEY": "litra_xxxxxxxxxxxx"
      }
    }
  }
}

Tools

search_papers

Search academic papers with AI-powered relevance scoring and summarization.

Parameter	Type	Required	Description
`query`	string	Yes	Natural language search query (1-500 chars)
`max_results`	number	No	Maximum number of papers (10-30, default: 30)
`year_from`	number	No	Minimum publication year (inclusive). Experimental – see Known limitations.
`year_to`	number	No	Maximum publication year (inclusive). Experimental – see Known limitations.

Example usage:

Search for recent papers on transformer architectures in NLP from 2023 onwards

Known limitations (year filtering): The year_from / year_to filters are still experimental. The pilot search stage currently does not apply the year filter, so some papers outside the specified range may still appear in results. Full support is tracked in Litra.ai issue #1068. As a workaround, you may need to post-filter the returned papers by their year field.

search_author

Search academic papers by author name.

Parameter	Type	Required	Description
`name`	string	Yes	Author name
`limit`	number	No	Maximum number of papers (1-50, default: 20)

Example usage:

Find papers by Yoshua Bengio

check_credits

Check your Litra.ai credit balance and subscription plan. No parameters required.

Pricing & Rate Limits

API access requires a paid Litra.ai subscription (Mini or above). Each search consumes credits from your existing subscription pool.

Plan	Rate Limit
Mini	10 requests/min
Standard	30 requests/min
Pro	60 requests/min
Max	120 requests/min

See litra-ai.com/pricing for plan details and pricing.

Response Language

All API responses — including paper titles, summaries, and research overviews — are returned in English only.

This is an intentional design choice for the MCP server and public API:

LLM accuracy: Large language models perform reasoning, analysis, and tool use more reliably in English. Returning structured data in English ensures the highest quality when AI agents process search results for downstream tasks (e.g., literature reviews, citation analysis, research synthesis).
Token efficiency: English responses consume fewer tokens than translated equivalents, reducing both latency and cost for LLM-based workflows.
No multilingual plans for the API: This MCP server is designed specifically for AI agent consumption. There are no plans to add other response languages. If you need Japanese or other languages, use the Litra.ai web interface directly, which provides full Japanese support including translated titles and summaries.

If your AI workflow requires output in a specific language, the AI client can translate the English response as a post-processing step — this is more reliable than asking the API to translate, since the LLM can adapt the translation to your specific context.

Troubleshooting

"LITRA_API_KEY environment variable is required"

Set the LITRA_API_KEY environment variable in your MCP client configuration. See the Setup section for examples.

"Invalid API key"

Your API key may be incorrect or revoked. Generate a new key at litra-ai.com/account.

"Insufficient credits"

Your credit balance is too low. Top up at litra-ai.com/account.

"Paid subscription required"

API access requires a paid plan (Mini or above). Subscribe at litra-ai.com/pricing.

"Rate limit exceeded"

You've exceeded your plan's rate limit. Wait a moment and try again, or upgrade your plan for a higher limit.

Development

git clone https://github.com/akkylab/litra-paper-search-mcp.git
cd litra-paper-search-mcp
npm install
npm run build

To test locally with Claude Code:

claude mcp add litra-paper-search -- node /path/to/litra-paper-search-mcp/dist/index.js

License

MIT

Available Tools

3 tools

check_creditsA

Check your Litra.ai credit balance and subscription plan.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4/5.0

Behavior3/5

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

No annotations are provided, so the description bears the full burden. It accurately indicates a read-only check but offers no additional behavioral context such as authentication requirements, rate limits, or return format. It does not contradict any annotations.

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?

The description is a single, concise sentence that front-loads the key action 'Check'. Every word is necessary and there is no redundancy or filler.

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

Completeness4/5

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

Given the tool's simplicity (no parameters, read-only, no output schema), the description is nearly complete. It could potentially mention what the output contains (e.g., credit balance amount, plan name) but this is not critical for a basic check tool.

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

Parameters4/5

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

With no parameters and 100% schema coverage (empty schema), the description adds value by stating the tool's purpose beyond the empty schema. It effectively explains what the tool does without needing parameter details.

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 retrieves credit balance and subscription plan, with a specific verb 'Check' and resource 'Litra.ai credit balance and subscription plan'. It distinguishes well from sibling tools that involve searching for authors or 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?

The description implies usage for checking account details but provides no explicit guidance on when to use this tool versus alternatives or any prerequisites. The context of siblings suggests it's a read-only utility, but no exclusions or caveats are stated.

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

search_authorB

Search academic papers by author name. Returns author profile and publications.

ParametersJSON Schema

Name	Required	Description	Default
`name`	Yes	Author name
`limit`	No	Maximum number of papers (1-50, default: 20)

TDQS

B3/5.0

Behavior2/5

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

No annotations provided, so description bears full burden. Only states it searches and returns profile and publications. Does not disclose limit parameter, pagination, rate limits, authentication needs, or what constitutes an 'author profile'.

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?

Two sentences, minimal waste, but lacks mention of the limit parameter and other structural details. Front-loads purpose but is incomplete.

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 2 parameters, no output schema, and no annotations, the description is too brief. It does not explain the output format, pagination, error handling, or prerequisites. Incomplete for an effective search tool.

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 description coverage is 100%, so baseline is 3. Description adds no additional meaning beyond the schema's parameter descriptions (name and limit).

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?

Clearly states verb 'Search' and resource 'academic papers by author name', with explicit output 'Returns author profile and publications'. Differentiates from sibling 'search_papers' which likely searches by keyword/topic.

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. Does not mention when not to use or compare to siblings like 'check_credits' or 'search_papers'.

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

search_papersB

Search academic papers with AI-powered relevance scoring and summarization. Returns papers ranked by relevance with AI-generated summaries.

ParametersJSON Schema

Name	Required	Description
`query`	Yes	Natural language search query
`year_to`	No	Maximum publication year (inclusive). NOTE: Year filtering is currently experimental. See year_from for details on the known limitation (Litra.ai issue #1068).
`year_from`	No	Minimum publication year (inclusive). NOTE: Year filtering is currently experimental. The pilot search stage does not yet apply the year filter, so some papers outside the specified range may still appear in results. Full support is tracked in Litra.ai issue #1068.
`max_results`	No	Maximum number of papers (10-30, default: 30)

TDQS

B3.3/5.0

Behavior2/5

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

With no annotations, the description carries the full burden of disclosing behavioral traits. It mentions AI-powered scoring and summaries but omits details on authentication, rate limits, or response size. The schema notes experimental year filtering, but that is part of the parameter descriptions, not the main description.

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?

The description is concise, consisting of two sentences that front-load the core purpose. Every sentence adds value with no redundant information.

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?

The description covers the essential purpose but lacks information on return format, expected output details, and behavioral constraints. Given the tool has 4 parameters and no output schema, additional context would improve completeness.

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 with descriptions, so the description adds no extra semantics. Baseline score of 3 is appropriate; the description does not enhance understanding beyond what the schema provides.

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's purpose: searching academic papers with AI-powered relevance scoring and summarization. It specifies the verb 'search' and the resource 'academic papers,' which distinguishes it from siblings like 'check_credits' and 'search_author.'

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 does not provide guidance on when to use this tool versus alternatives or mention conditions for use. No explicit when-to-use or when-not-to-use instructions are given, leaving the AI agent without decision-making support.

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.

3 tool updatesv1.0.1Jul 6, 2026
- First observedcheck_credits
- First observedsearch_author
- First observedsearch_papers

Deploy Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0

Scored 2026-07-06 05:55 across 3 tools

Disambiguation5/5

Each tool targets a clearly distinct function: credits, author search, and paper search. No overlap in purpose.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (e.g., search_author, search_papers) and use snake_case uniformly.

Tool Count4/5

With 3 tools, the server is minimal but focused. The count is slightly low but still reasonable for a narrow-purpose paper search MCP.

Completeness3/5

The tool set covers general search and author search, but lacks tools for retrieving specific paper details or searching by other criteria (e.g., title, year). The presence of check_credits is somewhat tangential.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

PapersFlowOAuth
io.github.papersflow-ai
Academic research MCP server for paper search, citation checks, graphs, and deep research.
Research & Data Search Documentation Access
214
mcp A
ai.llmse
Public MCP server for the LLM Search Engine
Search RAG Systems Developer Tools
102
H-Index A
ai.xr-utilities
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
Search Documentation Access
2
Mirror Memory MCP Server
io.github.Tr1ckyMag1ca1
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
Knowledge & Memory Search Note Taking
2

Related MCP Servers

scholar-search-mcp
Research & Data Search
Silung
A
license
Not graded
quality
C
maintenance
An MCP server for academic paper search that integrates with AI assistants (e.g., Claude Code, Cursor), enabling them to search and retrieve academic paper metadata.
Updated 4 months ago (2026-05-22 08:35 UTC)
250
MIT
semantic-scholar-mcp
Research & Data Search
FujishigeTemma
F
license
A
quality
D
maintenance
An MCP server that provides access to Semantic Scholar's academic paper database, enabling paper search, detailed retrieval, author info, and citation export.
Updated 5 months ago (2026-04-15 05:44 UTC)
4
10
-
aigroup-paper-mcp
Search Research & Data
jackdark425
A
license
A
quality
D
maintenance
Academic paper search and retrieval MCP server integrating multiple scholarly platforms into a unified interface. Supports search, fetch, trend analysis, and literature review workflows.
Updated 6 months ago (2026-03-19 03:55 UTC)
8
42
3
MIT
Deep Research MCP Server
Research & Data Search
wlu03
F
license
Not graded
quality
D
maintenance
An advanced scholarly research MCP server that enables AI assistants to discover, fetch, process, and manage academic papers across multiple sources like arXiv, PubMed, and Semantic Scholar, with capabilities for summarization, citation analysis, and concept relationship extraction.
Updated a year ago (2025-08-07 01:37 UTC)
2
-