MCP.Market

Agentcite MCP server

by Kevinx702·io.github.Kevinx702/agentcite·v0.1.1

Fabrication-free, DOI-backed citations for AI agents — real openAlex sources, never hallucinated.

B82/100grade B
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
New

0 stars34 downloads/wk

Reviews

Write one

Nobody has reviewed Agentcite yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agentcite tools (1)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • get_citations

    Return real, DOI-backed peer-reviewed citations for a topic (never fabricated).

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan2 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 94 days ago8/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agentcite compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 63% of 48,255 servers
Tools
1
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
34
more than 23% of 12,191 servers with a package

What its tools let an agent do: 1 read

Install Agentcite in Claude Code, Cursor or VS Code

Runs npx -y agentcite-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agentcite -- npx -y agentcite-mcp
Add to Cursor

What the publisher says

From the Agentcite repository's README, as published. We do not edit it. Read it on GitHub

AgentCite

Fabrication-free, DOI-backed citations for AI content & agents. Every result is a real openAlex record (CC0 public-domain data) with a resolvable DOI — the API never fabricates a source. Built to stop the hallucinated-citation problem that gets content E-E-A-T-demoted.

Separate deployable from giftedpicks.com (own Vercel project). Productizes the

logic of GiftedPicks/scripts/citation_magnet.py.

API (MVP)

  • GET /api/cite?topic=&n=5&since=YYYY → { topic, count, works[], markdown, source }
  • each work: { title, authors[], firstauthor, year, doi, doiurl, citedbycount, venue, openalex_id }
  • GET /api/health → { status, openalex, ts }

Data: openAlex REST (relevance-ranked, peer-reviewed type:article). Set OPENALEX_MAILTO env to join openAlex's polite pool. Edge-cached 1h per topic.

Roadmap (build order)

GATED: needs .claude/secrets/stripe-test-{publishable,secret}-key saved by Kevin. LIVE go-live = Kevin places the live secret key in the deploy env; agents never hold it.

  1. ✅ Core /cite + /health (openAlex REST, no key, no binary — serverless-portable)
  2. ⏳ API-key + quota gate (Supabase: anon free tier rate-limited vs keyed Pro)
  3. ⏳ MCP server: get_citations(topic, n, since) (stdio + http) — the agent-native surface
  4. ⏳ Stripe billing (TEST mode first; hosted Checkout/Payment Link → webhook provisions quota).
  1. Landing page + MCP-registry listings — owned by Cowork.

Guardrails

Public-domain data only (zero scraping / no unofficial-site APIs). Honesty is the product: output always says "verify each DOI resolves." Test-mode payments only until Kevin flips live; agents never move money or hold the live key.

Billing (Stripe)

Pro tier via hosted Stripe Checkout (subscription). On checkout.session.completed, the signature-verified webhook (/api/stripe-webhook) provisions a Pro API key in Redis (free→Pro quota elevation). Configure via env:

  • STRIPESECRETKEY, STRIPEPRICEID, STRIPEWEBHOOKSECRET, REDIS_URL
  • Create the Pro product/price once: STRIPESECRETKEY=sktest… node scripts/setup-stripe-product.js
  • Without Stripe env set, /api/checkout returns 503 and the citation API still runs free-tier.

Nothing above is checked by us. What we check is on the safety report.

Agentcite: common questions

Is Agentcite MCP server safe?
Mostly: it is graded B (82/100). Read the Agentcite safety report
How do I install Agentcite?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agentcite need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agentcite maintained?
The last commit was 133 days ago (2026-06-24). The latest release is v0.1.1.
How does Agentcite compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,255 servers); tools 1 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.