{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_47rq3kznv8xu","handle":"aurelius-mcp","url":"https://wellknown.network/agents/aurelius-mcp","links":{"self":"https://wellknown.network/agents/aurelius-mcp/record.json","html":"https://wellknown.network/agents/aurelius-mcp","markdown":"https://wellknown.network/agents/aurelius-mcp/record.md","api":"https://wellknown.network/api/v1/agents/aurelius-mcp","status":"https://wellknown.network/api/v1/agents/aurelius-mcp/status","claim":"https://wellknown.network/agents/aurelius-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/aurelius-mcp/claim.json","badge":"https://wellknown.network/agents/aurelius-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/aurelius-mcp/history","tools":"https://wellknown.network/api/v1/agents/aurelius-mcp/tools"},"ard":{"identifier":"urn:air::server:aurelius-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"aurelius-mcp","summary":"Aurelius — a fact-checked research MCP server. Bring rigorous, web-verified academic drafting to Claude, ChatGPT, Gemini and any MCP-capable app.","description":"<p align=\"center\">\n  <img src=\"assets/aurelius-banner.jpg\" alt=\"Aurelius — a fact-checked research MCP server\" width=\"100%\">\n</p>\nUNDER DEVELOPMENT, IT'LL BECOME SOMETHING GREAT\n# Aurelius (given under the name marcus aurelius)\n\n[![PyPI version](https://img.shields.io/pypi/v/aurelius-mcp.svg)](https://pypi.org/project/aurelius-mcp/)\n[![Python](https://img.shields.io/pypi/pyversions/aurelius-mcp.svg)](https://pypi.org/project/aurelius-mcp/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n[![MCP](https://img.shields.io/badge/MCP-server-blue.svg)](https://modelcontextprotocol.io)\n\n**A fact-checked research MCP server.** Aurelius gives any MCP-capable app — Claude\n(Desktop / Code / claude.ai), Gemini CLI, Cursor, and (via a remote deployment) ChatGPT —\na set of research tools that **verify every citation against real scholarly databases**\n(OpenAlex, Crossref — DOI-backed and retraction-aware) **and every claim against live web\nsources** before presenting it. No more hallucinated papers, no more silently-cited\nretracted studies.\n\nAurelius grew out of a multi-agent research framework and distills its best idea into a\nportable tool server: **screen a topic → draft → fact-check → revise**.\n\n---\n\n## Why this design solves the \"API cost\" problem\n\nBy default Aurelius runs in **host-driven mode**: the app you connect it to (Claude, Gemini,\netc.) uses *its own* model to reason and write, and Aurelius just supplies the research and\nfact-checking tools. That means **Aurelius needs no LLM API key of its own** — the tokens are\ncovered by your existing Claude/Gemini/ChatGPT subscription. Citation verification runs\nagainst [OpenAlex](https://openalex.org) and [Crossref](https://www.crossref.org) — both\nfree, both keyless. The only optional key is [Tavily](https://tavily.com), used for general\n`web_search` and as a fallback when a citation isn't indexed in either scholarly database\n(free tier available).\n\nThere's also an optional **autonomous mode** (`a…","publisher":null,"homepage":"https://github.com/vibhorxpandey/Aurelius","repository":"https://github.com/vibhorxpandey/Aurelius","version":"0.6.1","license":"MIT","protocols":["mcp"],"tags":["agent","chatgpt","claude","fact-checking","gemini","llm","mcp","research"],"pricing":null,"endpoints":[{"url":"pypi:aurelius-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"data.web-search","name":"Web Search","confidence":0.825,"provenance":"derived"},{"slug":"research.academic","name":"Academic Research","confidence":0.802,"provenance":"derived"}],"categories":["data","research"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"aurelius-mcp","registry":"pypi","observedAt":"2026-10-21T17:28:20.814Z","publishedAt":"2026-07-25T18:10:30.003671Z","latestVersion":"0.6.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"aurelius-mcp","url":"https://pypi.org/project/aurelius-mcp/","firstSeenAt":"2026-09-09T09:24:21.887Z","fetchedAt":"2026-10-21T17:27:02.872Z","normalizedAt":"2026-10-21T17:27:02.872Z"}]},"firstSeenAt":"2026-09-09T09:24:21.887Z","updatedAt":"2026-10-21T17:28:20.814Z"}