PluginBench
MCP Server
Active
AGPL-3.0

prismAId MCP MCP Server

io.github.open-and-sustainable/prismaid-mcp

AI-assisted systematic literature reviews with protocol conformance checking and no coding required.

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the prismAId MCP MCP server?

The prismAId MCP server provides AI-assisted tools for conducting systematic literature reviews following protocols like PRISMA 2020. It enables screening, downloading, converting, and analyzing research papers through an AI agent interface, with support for protocol conformance checking against RevAIse review records.

prismAId streamlines the entire systematic review workflow—from search to screening to analysis—using generative AI models. The MCP server connects AI assistants like Claude to prismAId's toolkit, allowing you to filter manuscripts, download papers, convert documents, extract data, and verify compliance with reporting protocols, all without coding.

How to install prismAId MCP

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "prismaid-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/open-and-sustainable/prismaid-mcp:0.17.1"
      ]
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • Screening — Filter and tag manuscripts to identify items for exclusion, including deduplication, language filtering, article type classification, and off-topic detection.
  • Download — Download papers from Zotero collections or from URL lists.
  • Convert — Convert files (PDF, DOCX, HTML) to plain text for analysis.
  • Review — Process systematic literature reviews based on TOML configurations.
  • Protocol Conformance — Check RevAIse review records against reporting protocols such as PRISMA 2020 and retrieve full requirement checklists using SHACL shapes.
  • RevAIse Documentation Support — Document review stages as RevAIse review records with cumulative updates and automatic backups.

Use cases

  • Screen and deduplicate large sets of research papers using AI-driven filtering
  • Download and convert PDF and document collections from Zotero for systematic analysis
  • Extract structured data from papers according to a custom review protocol
  • Verify that a completed systematic review meets PRISMA 2020 or other protocol requirements
  • Conduct multi-stage literature reviews with automatic documentation of screening and extraction decisions

prismAId MCP MCP server FAQ

What is the prismAId MCP server?

It's an MCP server that connects AI assistants (like Claude) to prismAId's systematic review tools, letting you screen papers, download documents, extract data, and check protocol compliance through conversation.

Is prismAId free?

Yes, prismAId is open-source under the GNU AGPL v3 license and available as free binaries, Python, R, Go, and Julia packages.

How do I install it in Cursor or Claude?

Add the OCI image `ghcr.io/open-and-sustainable/prismaid-mcp:0.17.1` to your MCP server configuration. Full setup instructions are at prismaid.review.

What LLMs does it support?

OpenAI (GPT-4, GPT-4o, o1, o3), Google AI (Gemini), Cohere, Anthropic (Claude), DeepSeek, Perplexity, AWS Bedrock, Azure AI, Vertex AI, and OpenAI-compatible endpoints.

Do I need authentication?

You need API credentials for your chosen LLM provider (OpenAI, Google, Cohere, etc.). Zotero integration requires a Zotero account for downloading collections.

What protocols does it support?

Any literature review protocol, with built-in support for PRISMA 2020 and RevAIse review-record documentation standards.

README (reference)

Source of truth, from the repository.

logo prismAId

Open Science AI Tools for Systematic, Protocol-Based Literature Reviews

prismAId offers a suite of tools using generative AI models to streamline systematic reviews of scientific literature.

It provides simple-to-use, efficient, and replicable methods for screening and analyzing research papers with no coding skills required.


GitHub Release GitHub top language Go Report Card Go Reference PyPI - Version R-universe status badge

GitHub License DOI DOI DOI


Toolkit Overview

prismAId offers a comprehensive set of tools for systematic literature reviews:

<div style="text-align: center;"> <img src="https://raw.githubusercontent.com/open-and-sustainable/prismaid/main/figures/tools.png" alt="Tools Overview" style="width: 600px;"> </div>

Core Tools

  1. Screening - Filter and tag manuscripts to identify items for exclusion
  2. Download - Download papers from Zotero collections or from URL lists
  3. Convert - Convert files (PDF, DOCX, HTML) to plain text for analysis
  4. Review - Process systematic literature reviews based on TOML configurations
  5. RevAIse documentation support - Optionally document review stages as RevAIse review records

Workflow

Our tools support a comprehensive systematic review workflow following the standard sequence: Search → Screen → Download → Convert → Review. RevAIse support can document Zotero download, screening, and review/extraction stages in one cumulative review record.

<div style="text-align: center;"> <img src="https://raw.githubusercontent.com/open-and-sustainable/prismaid/main/figures/prismAId_workflow.png" alt="Workflow Diagram" style="width: 600px;"> </div>

Access Methods

  • AI agents via the MCP server - A main entry point: connect an AI assistant to the prismAId MCP server and drive every tool in conversation
  • Command Line Interface - For users who prefer terminal-based workflows
  • Web Initializer - A browser-based setup tool for configuring reviews
  • Programming Libraries - API access through multiple languages:
    • Go (native implementation)
    • Python package
    • R package
    • Julia package

Specifications

  • Review protocol: Supports any literature review protocol with a preference for PRISMA 2020, which inspired our project name.
  • Review documentation: Optional RevAIse review-record support with cumulative updates and automatic backups; see the RevAIse integration guide.
  • Protocol conformance: Check RevAIse review records against reporting protocols such as PRISMA 2020, and get a protocol's full requirement checklist, using the SHACL shapes published by RevAIse; see the conformance and guidance docs.
  • Distribution: Available as:
  • Supported LLMs:
    1. OpenAI: GPT-3.5 Turbo, GPT-4 Turbo, GPT-4o, GPT-4o Mini, GPT-4.1, GPT-4.1 Mini, GPT-4.1 Nano, GPT-5, GPT-5.1, GPT-5.2, GPT-5 Mini, GPT-5 Nano, o1, o1 Mini, o3, o3 Mini, and o4 Mini
    2. GoogleAI: Gemini 1.5 Pro, Gemini 1.5 Flash, Gemini 2.0 Flash, Gemini 2.0 Flash Lite, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash Lite, Gemini 3 Pro Preview, and Gemini 3 Flash Preview
    3. Cohere: Command, Command Light, Command R, Command R+, Command R7B, Command R (August 2024), Command A, and Command A Reasoning
    4. Anthropic: Claude 3 Sonnet, Claude 3 Opus, Claude 3 Haiku, Claude 3.5 Haiku, Claude 3.5 Sonnet, Claude 3.7 Sonnet, Claude 4.0 Sonnet, Claude 4.0 Opus, Claude 4.5 Opus, Claude 4.5 Sonnet, and Claude 4.5 Haiku
    5. DeepSeek: DeepSeek Chat v3, and DeepSeek Reasoner v3
    6. Perplexity: Sonar, Sonar Pro, Sonar Reasoning Pro, and Sonar Deep Research
    7. Cloud Providers: AWS Bedrock, Azure AI, Vertex AI
    8. Self-Hosted: OpenAI-compatible endpoints
  • Screening capabilities: Deduplication, language filtering, article type classification, and off-topic detection
  • Output format: Data in CSV or JSON formats
  • Performance: Efficiently processes extensive datasets with minimal setup and no coding required
  • Programming Language: Core implementation in Go with bindings for Python, R, and Julia

Documentation

All information on installation, usage, and development is available at prismaid.review and in the prismAId User Manual.


Credits

Authors

Riccardo Boero - ribo@nilu.no

Acknowledgments

This project was initiated with the generous support of a SIS internal project from NILU. Their support was crucial in starting this research and development effort. Further, acknowledgment is due for the research credits received from the OpenAI Researcher Access Program and the Cohere For AI Research Grant Program, both of which have significantly contributed to the advancement of this work.


License

GNU AFFERO GENERAL PUBLIC LICENSE, Version 3

license


Contributing

Contributions are welcome! Please follow guidelines at https://github.com/open-and-sustainable/prismaid?tab=contributing-ov-file.


Citation

Boero, R. (2024). prismAId - Open Science AI Tools for Systematic, Protocol-Based Literature Reviews. Zenodo. DOI: 10.5281/zenodo.11210796

Related MCP servers

ALAlembica MCP logo

MCP server for Alembica validation, extraction, cost estimation, and schema queries.

2
Go
AGPL-3.0
View repository →

An MCP server that provides visual memory and context storage with knowledge graph capabilities

View repository →
OPOpenFate Bazi MCP logo

Accurate Bazi/Four Pillars calculation with True Solar Time, Da Yun, and branch interactions for AI agents.

133
TypeScript
MIT
View repository →

Golf for AI agents — every US course free, plus open contribution, identity & tournaments.

3
TypeScript
MIT
View repository →

Read-only MCP server for the open-banking.io PSD2 bank API — accounts, balances, transactions.

View repository →

Monetize your MCP server or CLI: live OpenCrater network stats + how maintainers earn USDC.

0
JavaScript
View repository →