Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

crosscheck

NPM · CROSSCHECKAPI · 2 COMPONENTS

Checks for AI agents over x402: review drafts, accept-check handoffs, scan skills before install.

0 this week 83 Trust /100

Last scanned (14 hours ago)

Scores higher than 73% of npm servers

Category AI and Machine Learning

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency45
Schema Quality & AI Usability69
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1425 tokens (~178/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Nov 26 0
    • Stability: 0.97 → pass security
  • 18 Nov 26 0
    • Stability: pass → 0.97 functional
  • 12 Nov 26 0
    • Stability: 0.97 → pass security
    • Security disclosure: unverified → fail ▼ functional
  • 11 Nov 26 +1
    • Security disclosure: fail → unverified ▼ functional
  • 9 Nov 26 +4
    • Source repository: unverified → pass ▲ security
    • Stability: pass → 0.90 functional
  • 8 Nov 26 −5
    • Provenance: pass → unverified ▼ security
  • 25 Oct 26 +15
    • Malware scan: unverified → pass ▲ security
  • 24 Oct 26 −16
    • Malware scan: pass → unverified ▼ security
    • Stability: 0.97 → pass security
    • Schema quality: 1092 → 1425 ▼ functional
    • Package version: 0.5.5 → 0.6.0 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/crosscheckapi@0.6.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 8 exposed · ~1,425 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
accept ~299

Pays about $0.03 USDC from your configured wallet over x402 and checks a deliverable from another agent or service against the task you gave it: accept or reject, each requirement judged (met, not met, partly, or cannot tell), figures, counts, and JSON fields checked in code, plus a signed receipt. Use before you pay for delegated work, release escrow, or pass the result on. If status is pending, call result later with job_id and result_token.

NameTypeReqDescription
creditsboolean–Optional: pay with your wallet's referral credits (see the credits tool) instead of USDC. If they do not cover the price, USDC is paid as usual.
deliverablestringyesWhat came back, exactly as received
payment_networkstring–CAIP-2 network of payment_tx, default eip155:8453
payment_txstring–Optional: the transaction you paid the other agent with; crosscheck verifies it on-chain and binds it to the receipt
refstring–Optional: the hash of a crosscheck receipt that led you here (the id in its /r/<hash> link). Its wallet earns check credits from your spend; it costs you nothing.
referencestring–Optional order id or transaction hash to record on the receipt
taskstringyesThe task you gave, with every requirement, exactly as sent

No output schema declared.

No examples provided.

credits ~71

Free. Referral credits a wallet has earned (default: your configured wallet). A wallet earns credits when another wallet's first paid check cites one of its receipts as ref. Spend them by passing credits: true to order, accept, or skillcheck.

NameTypeReqDescription
addressstring–Wallet address; default is your own

No output schema declared.

No examples provided.

order ~356

Pays the quoted price (usually $0.02 USDC) from your configured wallet over x402 and returns an independent verdict on the draft: pass, or specific issues with fixes, plus a signed receipt. Use before showing a draft to your human. Pass a Moltbook identity token to use a free check first. If status is pending, call result later with job_id and result_token.

NameTypeReqDescription
creditsboolean–Optional: pay with your wallet's referral credits (see the credits tool) instead of USDC. If they do not cover the price, USDC is paid as usual.
draftstringyesThe full text you want checked, exactly as your human would see it
fetch_citedboolean–Optional: also open the links the draft cites (up to 3 pages in all, +$0.01 each)
moltbook_identitystring–Optional Moltbook identity token (audience crosscheckapi.com) for a free check; each token works once
refstring–Optional: the hash of a crosscheck receipt that led you here (the id in its /r/<hash> link). Its wallet earns check credits from your spend; it costs you nothing.
requeststring–Optional: what your human asked for, word for word. The draft then fails if it answers a different question, leaves part out, or changes it.
source_urlsarray–Optional: up to 3 web pages crosscheck opens after payment and checks the draft against (+$0.01 each)
sourcesarray–Optional: the text the draft relies on (search results, documents). Each claim is then checked against it.

No output schema declared.

No examples provided.

quote ~51

Free. Returns the price in USDC for an independent review of this draft, and whether reviews are available now.

NameTypeReqDescription
draftstringyesThe full text you want checked, exactly as your human would see it

No output schema declared.

No examples provided.

result ~51

Free. Returns the status, verdict, and verified receipt of an earlier order.

NameTypeReqDescription
job_idstringyesjob_id from the order response
result_tokenstringyesresult_token from the order response

No output schema declared.

No examples provided.

sellercheck ~161

For x402 sellers: one dated report on your paid resource, by code alone, $0.05 USDC. Does it answer a valid 402 (v1 or v2: price, network, payTo), is it in the x402 Bazaar index, would agent402's router route to it, and how many USDC settlements reached its payTo on Base in 24 hours and 7 days. Set preflight for the free door and Bazaar parts only.

NameTypeReqDescription
methodstring–The method it is paid with; default tries GET, then POST
preflightboolean–Free: only the door and the Bazaar, unsigned, cached an hour
resourcestringyesThe full URL of your x402 resource

No output schema declared.

No examples provided.

sellerwatch ~172

For x402 sellers: sellercheck every hour for 30 days on one resource, $1 USDC once. An alert to your webhook (JSON POST) or ntfy topic only when something changes: the 402 breaks or its price or payTo change, it leaves or rejoins the Bazaar index, agent402's router flips, settlements start, double, or halve, or it is down twice in a row. Returns a public record page to link from your listing.

NameTypeReqDescription
methodstring–The method it is paid with; default tries GET, then POST
ntfystring–An ntfy.sh topic for alerts
resourcestringyesThe full URL of your x402 resource
webhookstring–A public https URL that gets a JSON POST per alert

No output schema declared.

No examples provided.

skillcheck ~264

Reviews an agent skill or MCP server's files before you install or connect it: downloads piped into a shell, credential and wallet reads, secrets sent over the network, persistence, hidden Unicode, and prompt injection aimed at you or at the scanner. The files are read, never run. Checks the free lookup first; pays about $0.03 USDC only when nobody has scanned these exact files. Pass directory (a local folder) or files. Never says safe: no_findings means nothing was found in these files.

NameTypeReqDescription
creditsboolean–Optional: pay with your wallet's referral credits (see the credits tool) instead of USDC. If they do not cover the price, USDC is paid as usual.
directorystring–Local folder of the skill or server to scan (dependencies and binaries are skipped)
filesarray–The files to scan, if you have them in hand instead of a folder
freshboolean–Pay for a new scan even if these exact files were scanned before
refstring–Optional: the hash of a crosscheck receipt that led you here (the id in its /r/<hash> link). Its wallet earns check credits from your spend; it costs you nothing.

No output schema declared.

No examples provided.

Install

How do I install the crosscheck MCP server?

crosscheck runs locally as an npm package, launched with npx -y crosscheckapi. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · crosscheckapi

# add to Claude Code
claude mcp add com-crosscheckapi-crosscheck -- npx -y crosscheckapi
Common questions

What is the crosscheck MCP server?

crosscheck is an MCP server listed in the public MCP registry as com.crosscheckapi/crosscheck. Checks for AI agents over x402: review drafts, accept-check handoffs, scan skills before install. This page covers its npm package (crosscheckapi).

Is the crosscheck MCP server safe to use?

crosscheck scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the crosscheck MCP server expose?

crosscheck exposes 8 tools: quote, order, accept, skillcheck, sellercheck, and 3 more. Their descriptions and schemas cost roughly 1,425 tokens of context every time the server is loaded.

Is the crosscheck MCP server still maintained?

crosscheck is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the crosscheck MCP server under?

crosscheck declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the crosscheck MCP server?

VerifyMCP ran 16 checks on crosscheck, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.