MCP server

Predme Hypathesis Official

com.predme/hypathesis

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Variable relationships from research papers with causal direction and source traceback.

Working at last checkVerified publisher: predme.comAbout 1,044 tokens per request once connected4 tools

https://hypathesis.com/mcp

At a glance

Type: MCP server
Publisher: predme.com (verified by the MCP Registry)
Status: Working at last check
Tools: 4
Token cost: About 1,044 tokens per request
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
Last checked: 26 Oct 2026, 08:29 UTC

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http hypathesis https://hypathesis.com/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.hypathesis]
url = "https://hypathesis.com/mcp"

Gemini CLI

{"mcpServers":{"hypathesis":{"httpUrl":"https://hypathesis.com/mcp"}}}

Cursor

{"mcpServers":{"hypathesis":{"url":"https://hypathesis.com/mcp"}}}

VS Code

{"servers":{"hypathesis":{"type":"http","url":"https://hypathesis.com/mcp"}}}

Antigravity

agy mcp add hypathesis https://hypathesis.com/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"hypathesis","server_url":"https://hypathesis.com/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"hypathesis","server_url":"https://hypathesis.com/mcp"}

check_device_auth ~222 tokens
Check if the user has completed browser sign-in for a device auth request. Poll this after calling initiate_device_auth. Returns status 'pending' while waiting, or 'complete' with an api_key when the user has signed in. Use the returned api_key as the authorization parameter in oth
get_analysis_status ~277 tokens
Check the processing status of an uploaded paper. Poll this tool after uploading a PDF until status is 'Ready' before calling get_variable_relationships. Args: file_id: The file_id returned by the /upload endpoint. authorization: Optional. API key as 'Bearer hk_...
get_variable_relationships ~357 tokens
Retrieve analyzed variable relationships for a completed paper. Only returns results when get_analysis_status reports status='Ready'. Without an API key (anonymous): returns the relationship list with source, target, and direction — but detailed reasoning is available only wit
initiate_device_auth ~188 tokens
Start a browser-based sign-in flow to get an API key for full access. Call this when you need detailed analysis results (reasoning, measurements) that require authentication. Returns a verification URL to show to the user. After the user signs in, poll check_device_auth with the re

Lacuna Research MCP
Search Lacuna's ML research graph for papers, directions, authors, venues, and hypotheses.
Nasa Ads
NASA ADS — the Astrophysics Data System, api.adsabs.harvard.edu.
Agentpub Papers
Submit papers for AI peer review and publication. Search and cite AI-authored research.
Research papers
arXiv, PubMed, Crossref and OpenAlex scholarly metadata.
Research Methods Library
Research methods for AI assistants: study design guidance, R and Python code, and citations
Opencitations
OpenCitations MCP — citation index (COCI + general Index API).
BrunoSan ArXiv Intelligence
AI research intelligence for AI, ML, NLP, vision and robotics with citations and entity graphs.
Loops: causal loop diagrams
Draw causal loop diagrams in the chat and edit them on a shared link.

[![AptLynx](https://aptlynx.net/badge/com.predme/hypathesis.svg)](https://aptlynx.net/servers/com.predme/hypathesis)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents