Thoth MCP server
Commit Nov 1, 2026Performs agentic systematic literature reviews with automated citation verification and per-claim audit reports.
Also known as ahmedEid1/thoth
- Stars
- 2
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.1
- Last commit
- Nov 1, 2026
- License
- MIT
What is Thoth MCP?
Thoth performs agentic systematic literature reviews with automated citation verification and per-claim audit reports.
Summary generated from the project's README
About Thoth MCP server
Researchers and developers can conduct systematic literature reviews with high precision by using Thoth to automate paper discovery and citation verification. The system functions as an authenticated MCP server that connects to AI clients like Claude.ai, Claude Desktop, or Cursor. It uses a human-in-the-loop process where users must approve the research plan, the discovered papers, and the final included papers before the agent proceeds.
Unlike standard LLM outputs that may hallucinate facts, Thoth includes a cite_check tool that compares every claim in a draft against the actual source paper. This process generates a per-claim audit report and a faithfulness score to ensure accuracy. The server supports various LLM providers and can be self-hosted on your own machine or a cloud instance using Docker. It provides specific tools such as list_reviews, get_review_draft, and get_citation_audit to manage and inspect the research process.
What you can do with it
- 1Verify research claim accuracyAn AI client can use the citation audit tool to identify unsupported claims and invented statistics in a draft review.
- 2Monitor review quality metricsUsers can retrieve a list of completed reviews along with their critic scores and citation faithfulness percentages.
Written from the project's README. Every use case is checked against a quote from it.
How to install Thoth MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Thoth MCP in Claude Code
$ claude mcp add --transport http thoth https://thoth-slr.vercel.app/api/mcp/mcpInstall Thoth MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"thoth": {
"url": "https://thoth-slr.vercel.app/api/mcp/mcp"
}
}
}Install Thoth MCP in VS Code
.vscode/mcp.json
{
"servers": {
"thoth": {
"type": "http",
"url": "https://thoth-slr.vercel.app/api/mcp/mcp"
}
}
}Install Thoth MCP in VS Code CLI
$ code --add-mcp '{"name":"thoth","type":"http","url":"https://thoth-slr.vercel.app/api/mcp/mcp"}'Install Thoth MCP in Codex
$ codex mcp add thoth --url https://thoth-slr.vercel.app/api/mcp/mcpInstall Thoth MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.thoth] url = "https://thoth-slr.vercel.app/api/mcp/mcp"
Install Thoth MCP in Gemini CLI
$ gemini mcp add -s user --transport http thoth https://thoth-slr.vercel.app/api/mcp/mcpInstall Thoth MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"thoth": {
"url": "https://thoth-slr.vercel.app/api/mcp/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableahmedeid1/thoth is public and reachablegithub.com/ahmedeid1/thoth ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-01github.com/ahmedeid1/thoth ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeEndpoint did not answer initialize: HTTP 404Finding
README
View on GitHubThoth
Agentic systematic literature reviews — with every citation checked against the source.
Named for Thoth, ancient Egypt's ibis-headed god of writing and scribes.
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.
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):
https://<your-host>/api/mcp/mcp
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
Run it locally:
git clone https://github.com/ahmedEid1/thoth.git && cd thoth
cp .env.example .env # Clerk + Trigger.dev keys + MISTRAL_API_KEY
docker compose up -d # postgres, minio, langfuse
pnpm install && pnpm prisma migrate dev
pnpm dev # Next.js on :3000
pnpm dev:trigger # Trigger.dev worker (separate terminal)
Full setup, the agent pipeline, and the v2 flow: docs/architecture.md.
Proof
| Hosted app | Ran live in 2026 (Clerk sign-in, sample review at /showcase); retired on 1 Nov 2026 |
| Public evals | /evals (last run 6 July 2026) — inclusion precision 97%, recall 74% (papers included vs. each question's expected list, averaged over the 9 golden questions with an inclusion score) on a versioned 18-question golden set (7 of 18 have data at the latest sweep's commit; faithfulness 38% / coverage 32% tracked in the open as the set fills out; discovery/screening v2 under calibration). Regenerated in CI, published with the last-run date — a regression is a public signal. |
| MCP Registry | io.github.ahmedEid1/thoth — listed; its remote endpoint was retired with the hosted app |
| Tests | 676 unit/integration + 22 live e2e against the deployed instance (MCP transport, real-browser, authenticated walkthroughs, full agent runs) — all green; tsc + lint clean |
| Audit log | Every MCP call recorded with a SHA-256 input hash; no raw input stored |
| Deploy cost | $0/mo — Vercel + Neon + Cloudflare R2 + Langfuse + Trigger.dev, all free tiers (self-host option) |
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
Thoth MCP questions
How do I add Thoth MCP to Claude Code?
Run claude mcp add --transport http thoth https://thoth-slr.vercel.app/api/mcp/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Thoth MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How does Thoth handle citation accuracy?
It uses a cite_check process that compares every cited claim against the source paper and labels it as supported, unsupported, or unclear.
Does Thoth run autonomously?
No, it includes three human-in-the-loop gates for the review plan, discovered papers, and included papers to ensure nothing runs unattended.
How is the server authenticated?
The server uses OAuth 2.1 with PKCE and Dynamic Client Registration via Clerk.