Fresh data · 15-17 September 2026 · instant download

Security datasets for the MCP & agent economy

The MCP ecosystem has 21,643 registered servers — and almost nobody publishes measured, per-server security data. We scan it, verify it twice, and sell the result. Every number on this page comes from our own published scans.

94
live servers scored
335
verified findings
44
open handshakes
25
rules in flaw DB

The datasets

One-time purchase, instant download. Single-user license: use the data internally, build products and reports on it — just don't resell the raw dataset.

Best value

MCP Trust Database

Every remote MCP server in the official registry that we could reach, security-scored. The vendor-risk list for the agent economy.
  • 94 servers: id, host, score 0-100, grade A-F
  • 335 verified findings mapped to 7 flaw classes
  • 44 critical findings (44 open handshakes)
  • JSON + CSV, methodology & verification notes included
  • Grade distribution: A 10 · B 13 · C 35 · D 27 · F 9
$29 one-time
Get the Trust DB Free sample — 12 rows

MCP Flaw Database

The complete FlowSentry rulebook: 25 flaw classes for MCP endpoints and agent workflows, with live prevalence measured across 94 servers and copy-ready remediations.
  • 7 endpoint rules with measured prevalence (e.g. 91% missing CSP)
  • 18 workflow-scanner rules (n8n / agent pipelines)
  • OWASP Agentic AI Top 10 mapping per rule
  • Why-it-matters + remediation for each rule
  • The same engine that powers our public reports
$19 one-time
Get the Flaw DB Free sample — descriptions only

Agent Economy Monitor

What agents actually pay for: a snapshot of the x402 commerce rail from Coinbase's Bazaar catalog, plus MCP market sizing from our registry research.
  • 15,858 indexed x402 resources (catalog total)
  • Price distribution: median $0.0045, max $5 in sample
  • Scheme mix: exact vs batch-settlement
  • MCP market size: 21,643 servers, 72,606 versions (arXiv 2609.14119)
  • Monthly refresh cadence — October snapshot included free
$9 one-time
Get the Monitor Free sample — top-line stats

Bundle: all three — $39 (save $18)

One download, everything above: mcp-security-dataset.zip (README, trust DB JSON+CSV, flaw DB, economy monitor, free samples for comparison).

Grade distribution & worst offenders (from the Trust DB)

This is the actual data you're buying — the same table our public MCP Security Report is built from.

A
10
B
13
C
35
D
27
F
9

8 lowest-scoring servers (preview)

Registry IDHostScoreGradeFindings
agency.goji/gojimcp.goji.agency22F6 critical
ai.adoraads/beautymcp.adoraads.ai22F6 critical
ai.afmr/discoveryafmr.ai22F6 critical
ai.agentlookups/counterscriptrx.agentlookups.ai22F6 critical
ai.agentlookups/greenlightsolar.agentlookups.ai22F6 critical
ai.agentlookups/groundtruthenv.agentlookups.ai22F6 critical
ai.agentlookups/overassessedoverassessed.agentlookups.ai22F6 critical
ai.agentlookups/plumblinecontractors.agentlookups.ai22F6 critical

Full 94-row table (JSON + CSV) in the dataset. Free 12-row sample above.

Schema — mcp_trust_db.json

{ "dataset": "...", "version": "2026-09-15", "count": 94, "servers": [ { "id": "agency.goji/goji", "host": "mcp.goji.agency", "score": 22, "grade": "F", "critical_findings": 1, "findings_total": 6, "findings": ["FS-MCP-001", "..."], "scanned": "2026-09-15" } ] }

Checkout — instant download

Two rails: pay-per-request for agents (x402, USDC on Base, no account) and a one-time email delivery for humans. Send payment, email the tx hash, download link lands in your inbox within hours.

Humans — USDC on Base

  1. Send the amount to 0xa1b8be63bde77ddc65d9ffe8a21a2a5f2c9ca6a8
  2. Fill the form below with the tx hash
  3. Download link delivered to your inbox (usually minutes, max 24h)

Agents — x402 pay-per-request

Machine-native checkout over the same rail our paid API uses. Your agent hits the endpoint, receives HTTP 402 with payment terms, pays USDC on Base, retries with the receipt — zero human in the loop.

POST https://flowsentry-agentpay2.vercel.app/v1/scan · $0.50
POST https://flowsentry-agentpay2.vercel.app/v1/scan/deep · $2.00
GET https://flowsentry-agentpay2.vercel.app/v1/trust · $0.05

Buying the datasets themselves by agent? Hit the trust endpoint to verify our data quality live, then email [email protected] with the payment receipt — delivery follows the same inbox.

Why trust this data

Every finding was confirmed by a second independent scan pass. Header findings were cross-validated with a second HTTP client on a sample — zero mismatches. No tool calls beyond initialize, no exploitation, findings reported as problem classes. The methodology, per-server table and rule details are public in the MCP Security Report, and our scoring API is live at /trust so you can verify a sample of the claims before paying.

Security-first, privacy-by-design: we store what you pay for and nothing else. No trackers, no third-party scripts on this site.

FAQ

How fresh is the data?
Trust DB scanned 15 September 2026, single vantage point, one endpoint per server. Economy Monitor snapshot 17 September. Next refresh: monthly (Trust DB re-scan included free for bundle buyers when we publish v2).
Why only 94 servers when the registry has 21,643?
The official registry holds 21,643 entries but only ~55% publish a working remote endpoint; 94 fully-remote servers passed reachability during the scan window. We verify before we count — placeholder entries like literal {api_host} sit in the registry today, and we exclude or flag them.
Can I resell or publish the dataset?
Single-user license: internal use, derived products and reports are yours. Redistributing or reselling the raw dataset itself is not permitted. Custom licensing on request.
Refunds?
If the data doesn't match its description, email us within 14 days with the discrepancy and we refund the full amount to your Base address.
Do you take custom scan commissions?
Yes — fleet scans (up to 100 endpoints) are $20 via the services page, and we deliver the same per-server table you see here for your own endpoints.

Not ready to buy? Verify us first

Read the public MCP Security Report (100 servers, methodology, per-class breakdowns), query our live trust API, or book a fleet scan on our services page. The datasets are the machine-readable layer under all three.