Atlas Research
io.github.ahmedEid1Published by GitHub account ahmedEid1v0.7.0Updated Oct 24, 2026
Read-only MCP over an agentic SLR workspace with per-claim citation verification
The publisher's own server: Red Atlas Api
Overview
Read-only MCP access to a systematic literature review workspace, exposing drafts, per-claim citation audits and discovered papers to an assistant.
- What you can do
- List your reviews with critic and faithfulness scores
- Read the markdown draft of a completed review
- Retrieve the per-claim citation audit that labels each cited claim supported, unsupported or unclear
- Inspect papers surfaced by the discoverer with fetch and screening status, and the generated search queries with per-provider errors
- When to use it
- Useful when you want an assistant to read and discuss an existing systematic literature review and check whether its citations actually hold up against the source papers, rather than drafting new reviews itself.
- Requirements
- A running instance of the project: the hosted app was retired, so you deploy your own and connect to its MCP URL. OAuth 2.1 sign-in through the browser (Clerk with dynamic client registration) scopes tools to your account. Self-hosting needs Docker, Node.js with pnpm, Postgres, and keys for Clerk, Trigger.dev and an LLM provider such as Mistral.
Installation
In SourceWeft
- Open Atlas Research in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.ahmedEid1%2Fatlas-research/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"atlas-research": {
"type": "http",
"url": "https://atlas-sooty-delta.vercel.app/api/mcp/mcp"
}
}
}README
Thoth
Agentic systematic literature reviews — with every citation checked against the source.
Named for Thoth, ancient Egypt's ibis-headed god of writing and scribes.
[Hosted app] [Tests] [App release] [Deploy cost] [License: MIT]
The hosted app ran live in 2026 and is now retired. The screenshots and walkthroughs below are from it; you can still run it yourself.
[Browsing a completed Thoth review — draft, critic score, and per-claim citation audit]What is Thoth?
Systematic literature reviews are slow to write — and when you ask an LLM to write one, it confidently invents citations and statistics that aren't in any paper.
Thoth does both halves and checks its own work. Give it a research question and
it discovers relevant papers, reads them, drafts an evidence-grounded review — then
runs a verification pass (cite_check) that compares every cited claim against the
source paper and flags anything unsupported before you read the draft. The result
is a review with a critic score, a citation-faithfulness percentage, and a per-claim
audit you can trust.
It ran (hosted, in 2026) as a polished web app, a public eval dashboard, and an authenticated MCP server your AI assistant could call directly; it still runs on your own machine or host.
See it work
Claude.ai catches 6 fabricated citations in a real draft — using Thoth's audit:
Connected to Thoth via the official MCP Registry, Claude calls
get_citation_auditon one deliberately-weak review (faithfulness 0.13 for that single review) and identifies all 6 unsupported claims — every one citing the same paper, with invented percentages that aren't in the source. This iscite_checkdoing its job: it's a single-review audit sample, not the golden-set aggregate (the/evalsdashboard had that).
Every claim, scored against its source — the /showcase review (no login needed). The figures on this card (critic 4.2/5, faithfulness 75%, 8/8 citations checked, 2 unsupported) are this one review's scores — a worked example, not the aggregate:
Evaluated in public — the /evals dashboard tracked inclusion recall / precision, claim faithfulness and coverage over an 18-question versioned golden set (7 of 18 have data at the latest sweep's commit), regenerated in CI and published with the last-run date (last run 6 July 2026, before the hosted app was retired), so a regression was a public, falsifiable signal:
You approve every step — three human-in-the-loop gates (review plan → review discovered papers → approve included papers); nothing runs unattended:
Key features
- 🔎
cite_check— verifiable citations. Every[paper_id]in the draft is scored against the cited paper and labelled supported / unsupported / unclear, so the LLM can't quietly hallucinate a citation. The verdict report is published per claim, not summarised away (claim faithfulness on the golden set: 38%). This is the core differentiator: the citations are measured, not asserted. Paper selection is scored separately: the papers Thoth includes are compared with each golden question's expected paper list — inclusion precision 97%, recall 74%, averaged over the 9 golden questions that have an inclusion score. That measures which papers it picks, not whether its citations are correct, and precision is 1.0 by construction on goldens with no distractor papers (see known limitations). - 🌐 Outbound web search (v2 — under active evaluation). An outbound
discoverer → fetcher → screenerpath is wired across OpenAlex, arXiv, and Exa: it fetches open-access PDFs, OCRs them, and screens each against your plan, so you can run uploaded-only, hybrid, or fully autonomous discovery. The discovery and screening axes are v2 and still being calibrated — they're tracked openly on/evals(both at 0% at the last run) rather than shipped as a silent claim. - 🔌 Authenticated, registered MCP server. OAuth 2.1 + PKCE + Dynamic Client Registration via Clerk, SHA-256 audit logging, rate limits — listed in the official MCP Registry. Most public MCP servers ship with no auth; this one doesn't.
- 📊 Public eval dashboard. Inclusion recall / precision, faithfulness and coverage over a
versioned golden set, regenerated in CI and stamped with the last-run date, rendered at
/evals— an eval regression was a public signal, not a hidden one. The weekly eval run is retired; the last run was 6 July 2026. - 💸 6 LLM providers, $0/mo by default. Swap providers with one env var; the hosted app ran on the Mistral free tier, and the entire stack deploys on free tiers for $0/mo.
🚀 Quickstart
The hosted app ran live in 2026 and is retired, so run your own instance (below).
Connect it to your AI assistant — paste your deployment's MCP URL into claude.ai (Pro/Max), Claude Desktop, Cursor, or any MCP client (OAuth runs in your browser; no token to copy):
Read-only MCP tools (scoped to your account)
list_reviews— your reviews with critic + faithfulness scoresget_review_draft— the markdown draft of a completed reviewget_citation_audit— the per-claim cite_check verdict reportlist_discovered_papers(v2) — papers the discoverer surfaced, with fetch + screening statusget_search_queries(v2) — the queries the discoverer generated + per-provider errors
Full reference: docs/mcp/tools.md · auth + audit model: docs/mcp/security.md
Adding Thoth as a custom connector in claude.ai — OAuth runs in your browser (Clerk + DCR), no token to copy.
Run it locally:
Full setup, the agent pipeline, and the v2 flow: docs/architecture.md.
Proof
For engineers
Thoth is a LangGraph StateGraph driven by a Trigger.dev worker, with durable
human-in-the-loop gates, a per-run cost cap, and exactly-once gate delivery. Next.js 16
- TypeScript (strict), Postgres + Prisma, Clerk auth (web + OAuth 2.1 for MCP), S3-compatible storage, Mistral OCR, Langfuse tracing.
- Architecture — the agent pipeline, full stack, v2 flow, tests
- LLM providers — the 6-provider matrix + resilience knobs
- MCP tools · MCP security
- Security & privacy — data inventory, jurisdictions, deletion paths
- Self-host — one VM on Oracle Cloud Always Free
- Changelog · Releasing
Credits
Ibis icon by Delapouite under CC BY 3.0, via game-icons.net.
License
MIT © 2026 Ahmed Hobeishy
Source: README.md at commit d7c5b4b
Tools
0Version history
1- v0.7.0LatestSep 16, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listedRequired15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Atlas integrations
Red Atlas Api
red.atlasOfficial publisher
Remote MCP server giving an assistant access to Puerto Rico and Colombia real estate data: listings, sales, parcels, permits, analytics and AVM reports.
Election Atlas
Published by GitHub account TaltonFiggins
A remote atlas of US and Canadian election geographies that lets an assistant look up places, districts, boundaries and officials.
Boundary Atlas
Published by GitHub account TaltonFiggins
Remote MCP server for US and Canadian boundaries: look up cities, ZIPs, counties, districts and precincts, locate points, and fetch GeoJSON.
Atlas Primer Voice Roleplay
Published by GitHub account AtlasPrimer
Atlas Primer Voice Roleplay's hosted MCP server; no sign-in required; Streamable HTTP; 1 tool.
Smart Rings Atlas
Published by GitHub account thiazzz
Remote MCP server for researching smart rings: search dated records, compare evidence, estimate subscription costs and find regional buying links.