Consensus

Search academic research papers with AI-powered analysis.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Search: Search academic research papers using the Consensus API to find relevant peer-reviewed studies. This tool searches through 200+ million research papers from top academic sources including Sema

What data it sees

Do you need an account

No: the server works without sign-in

Search academic research papers with AI-powered analysis. Find studies, extract key findings, and get evidence-based answers to research questions.

How to connect

How to connect Consensus to Claude

The server address to paste into Claude settings:

https://consensus.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Consensus to ChatGPT

The server address to paste into ChatGPT settings:

https://consensus.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Consensus to Cursor

The server address to paste into Cursor settings:

https://consensus.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (1)

Raw names from tools/list. Only developers need these.

searchSearch academic research papers using the Consensus API to find relevant peer-reviewed studies. This tool searches through 200+ million research papers from top academic sources including Semantic Scholar, PubMed, ArXiv, and other prestigious academic databases. It provides comprehensive metadata including citation counts, relevance scores, abstracts, author information, and publication details to help you find the most relevant and credible research for your query. Args: query (str): The research question or topic to search for. Be specific and use academic terminology when possible. Examples: "effects of climate change on biodiversity", "machine learning applications in healthcare diagnosis", "effectiveness of cognitive behavioral therapy for anxiety disorders" year_min (int, optional): Exclude papers published before this year. Useful for finding recent research or studies from a specific time period. Example: 2020 to find papers from 2020 onwards year_max (int, optional): Exclude papers published after this year. Useful for historical research or finding studies up to a certain date. Example: 2019 to find papers published up to 2019 human (bool, optional): Set to True to include only studies involving human subjects. Useful for medical, psychological, or social research where human studies are more relevant than animal or theoretical studies. sample_size_min (int, optional): Exclude studies with sample sizes smaller than this number. Useful for finding studies with statistical power and reliable results. Example: 100 for studies with at least 100 participants sjr_max (int, optional): Filter by journal quality using SCImago Journal Rank quartiles. Values: 1 (highest quality, Q1 journals), 2 (Q2), 3 (Q3), 4 (Q4). Lower numbers indicate higher quality journals. Example: 2 to include only papers from Q1 and Q2 journals Returns: Dict[str, Any]: A comprehensive dictionary containing: - query: The original search query - total_results: Number of papers found - papers: List of paper objects with detailed metadata including: * title: Full title of the research paper * authors: List of author names and affiliations * abstract: Full abstract text * journal: Journal name and publication details * year: Publication year * citation_count: Number of times the paper has been cited * doi: Digital Object Identifier for accessing the paper * study_type: Type of study (if available) * sample_size: Number of participants/subjects (if available) * url: Direct link to the paper - filters_applied: Summary of any filters that were applied - status: Success/error status of the search - api_credits_used: Number of API credits consumed by this search Raises: Exception: If API key is missing, network errors occur, or API rate limits are exceeded Example Usage: # Basic search for climate change research search("climate change impacts on agriculture") # Advanced search for recent high-quality human studies search( query="meditation effects on anxiety", year_min=2020, human=True, sample_size_min=50, sjr_max=2 ) # Search for systematic reviews and meta-analyses search( query="effectiveness of online learning", ) When presenting results to users, always cite papers with hyperlinked titles: [Paper Title](url). Include the year and citation count for context.