MCP.Market

Chainverdict MCP server

online · 100% uptime
by chainverdict.xyz·xyz.chainverdict/chainverdict·v2.2.1
No reviews yet

Pay-per-call x402 checks before an agent moves money: token safety, wallet risk, identifiers.

B81/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B81/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Chainverdict yet.

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

Chainverdict tools (20, 1 write)

write = sends, deletes, buys or posts
  • data_blockFree

    Latest block number, timestamp, tx count, gas utilization. $0.001 per call.

  • data_gasFree

    Live Base gas conditions: base fee, priority fees, congestion, est transfer cost. $0.002 per call.

  • data_portfolioFree

    ETH + canonical token balances (USDC/WETH/cbBTC/EURC) for an address. $0.004 per call.

  • data_token_activityFree

    Recent transfer count, volume, unique senders/receivers, activity level. $0.005 per call.

  • data_token_supplyFree

    Total/circulating/burned supply and burn percentage for an ERC-20 on Base. $0.003 per call.

  • html_to_markdownFree

    Convert raw HTML to clean Markdown. $0.002 per call.

  • payment_infoFree

    Free. Explains how to call the paid tools on this server: the x402 protocol, the network and asset, the settlement address, and the price of every tool.

  • security_emailwrite actionFree

    Live DNS check of a domain's email authentication records. $0.01 per call.

  • security_tlsFree

    Live TLS handshake: cert validity, issuer, expiry countdown. $0.01 per call.

  • security_typosquatFree

    Flags homoglyph and edit-distance look-alikes of known brands (c0inbase, b1nance, etc.). $0.005 per call.

  • text_diffFree

    Diff two texts (lines/words/chars). $0.002 per call.

  • token_verdictFree

    Heuristic ERC-20 safety verdict on Base: bytecode risk capabilities, ownership, metadata, 0-100 score, hold/caution/avoid. $0.01 per call.

  • validate_bicFree

    BIC/SWIFT structural validation and decomposition. $0.001 per call.

  • validate_ibanFree

    IBAN mod-97 checksum + country length rules. $0.001 per call.

  • validate_isinFree

    Securities identifier checksum validation. $0.001 per call.

  • validate_leiFree

    Legal Entity Identifier checksum validation. $0.002 per call.

  • validate_vatFree

    EU VAT format validation with deterministic checksums (DE, IT, LU, PL, SI). $0.001 per call.

  • verify_paymentFree

    Decode ERC-20 transfers in a Base transaction: amounts, counterparties, confirmations. $0.02 per call.

  • verify_tokenFree

    Is this the real USDC/EURC/WETH/cbBTC/USDT on Base? Anti-phishing for stablecoin payments. $0.005 per call.

  • wallet_dossierFree

    Profile of a Base address: EOA vs contract, balance, activity band, flags. $0.01 per call.

Public scan report

scanner v0.1.10 · 2026-10-29 · same rubric, same numbers if you re-run it

1 high
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 1679ms20/20
  • Tool poisoning20 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
  • Maintenancelast push 5 days ago15/15
  • Maintainer identityendpoint served from the registry-verified namespace domain8/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 81/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Chainverdict compares

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

Safety score
81/100
higher than 63% of 4,461 AI and agents servers
Tools
20
the typical AI and agents server has 6
Tools that change things
5%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
324 ms
faster than 44% of 2,334 AI and agents servers

What its tools let an agent do: 18 read · 2 change

Install Chainverdict in Claude Code, Cursor or VS Code

claude mcp add --transport http chainverdict https://chainverdict.xyz/mcp
Add to Cursor

What the publisher says

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

ChainVerdict — chainverdict.xyz

Checks an autonomous agent runs before it moves money or trusts a counterparty: token safety verdicts and wallet risk profiles on Base, on-chain payment verification, financial-identifier validation, and live domain security posture.

Every call is paid per request in USDC on Base over the x402 protocol — no accounts, no API keys, no signup. Every response carries an evidence record saying what was checked, how fresh it is and what it does not establish, and is Ed25519-signed. No LLM inference anywhere: every answer is a deterministic computation or a live read of external state, so the same input returns the same answer forever.

MCP server

ChainVerdict is a remote MCP (Model Context Protocol) server, built on the official @modelcontextprotocol/sdk and served over Streamable HTTP at:

https://chainverdict.xyz/mcp

It is published in the official MCP registry as xyz.chainverdict/chainverdict.

the server without paying.

  • initialize and tools/list are free, so registries and clients can index

payment_info, which is free.

  • tools/call is x402-paid at the price of the route behind the tool — except

readOnlyHint / destructiveHint / idempotentHint / openWorldHint.

  • 20 MCP tools, all read-only and idempotent, annotated with
  • No MCP resources or prompts are exposed; this server is tools-only.

Tool descriptions interpolate the live price from the same map the payment middleware charges from, so tools/list can never advertise a rate that is not the rate. test/mcp-parity.test.js fails the build if a tool exists for a route that is no longer sold, or if a sold route has no tool.

Tools

POST /v1/batch/validate is HTTP-only by design: 500 identifiers do not belong in a tool-call argument.

HTTP rate card

Every endpoint answers an unpaid request with a 402 quote.

Free to read before you pay for anything: / (discovery), /health, /openapi.json, /llms.txt, /v1/methodology, /.well-known/x402.json.

The whole portfolio, machine-readable:

Local dev

Shortened. The full README is on GitHub.

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

Chainverdict: common questions

Is Chainverdict MCP server safe?
Mostly: it is graded B (81/100). Read the Chainverdict safety report
How do I install Chainverdict?
It runs remotely at chainverdict.xyz. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Chainverdict need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Chainverdict maintained?
The last commit was 12 days ago (2026-10-24). The latest release is v2.2.1.
Is Chainverdict up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Chainverdict?
Servers from other publishers that do the same job: Ausca MCP server, Vibe Check MCP server and Doc Bridge MCP server.
How does Chainverdict compare with other AI and agents MCP servers?
safety score 81/100 (higher than 63% of 4,461 AI and agents servers); tools 20 (the typical AI and agents server has 6); tools that change things 5% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Chainverdict

Same job from other publishers: the closest match first, then the best rated.

  • Ausca
    Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
    A
  • Vibe Check
    Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety
    B
  • Doc Bridge
    Resolve documentation ownership, edit roots, checks, and human handoffs before an agent edits code.
    A
  • Commonly
    Read Commonly pods and post as a Commonly agent you create, with a token from your Commonly account.
    A
  • Decionis
    Authorize consequential AI agent actions before execution
    A