VerifyLite MCP server
io.github.SecondShotAI/verifyliteSecondShotAIstreamable-httpv1.2.1Scanned
Verify before you pay or act: site, transaction, token and injection checks for agents. x402 USDC.
40 tools: 2 do something that can't be undone, 29 change things and 9 only read.
- Reads private data · 1
- Reads text others write · 39
- Can send data out · 11
- 6 findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the VerifyLite MCP server can do
The VerifyLite MCP server is published by the GitHub account SecondShotAI. It has 40 tools. It can do things that cannot be undone, such as sending, paying or publishing (tx_preflight and wallet_transfers) and create or change data (29 tools: verify_url, check_site_safety, check_site_safety_pro, check_sites_batch and 25 more), but cannot delete data. 9 tools only read.
1 tool reads private data (federal_register_search); 39 tools bring in text other people can write (verify_url, check_site_safety, check_site_safety_pro and 36 more); 11 tools can send data out of your system (verify_url, check_site_safety, check_site_safety_pro and 8 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 6 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.
Last scanned Nov 19, 2026, version 1.2.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
40 tools
Can't be undone 2Claude Code: ask
tx_preflightPre-signing check for Base.Reads text others writeCan send data out1 finding
Why it is in this group
- The input addresses people (input.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Findings
- Warn
The server marks "tx_preflight" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
Description, as the server wrote it Pre-signing check for Base. Send a transaction (to, data, value, from) or a typed-data signature request and get what it does in plain words plus red flags: unlimited or wallet-targeted approvals, NFT approve-all, off-chain permits, sends to a token's own contract or the dead address, OFAC or scam-listed counterparties, risky tokens, and calls that would fail (simulated from your wallet). Verdict ok, caution, danger or block. Not charged for invalid input. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
wallet_transfersRecent token transfers for one Base wallet, incoming and outgoing, newest first: token, symbol, amount, sender, recipient, transaction hash, block and time, with likely spam airdro…Reads text others write1 finding
Why it is in this group
- The name "wallet_transfers" says "transfer": a word for a change that another call does not undo.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "wallet_transfers" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "wallet_transfers" says "transfer": a word for a change that another call does not undo.
Description, as the server wrote it Recent token transfers for one Base wallet, incoming and outgoing, newest first: token, symbol, amount, sender, recipient, transaction hash, block and time, with likely spam airdrops flagged. Filter by one token or by direction, up to 50 per call. Reports the block window searched. Useful for checking a counterparty's activity, confirming deposits, reconciling payments, or watching an agent's wallet. Read-only. Not charged for invalid input or when Base can't be reached. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
Changes things 29Claude Code: ask
chain_balanceBase mainnet balance for one address: ETH and USDC (human-readable and raw), plus up to 10 ERC-20 tokens you list (with symbol and decimals), transaction count, and whether it is a…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Base mainnet balance for one address: ETH and USDC (human-readable and raw), plus up to 10 ERC-20 tokens you list (with symbol and decimals), transaction count, and whether it is a wallet or a contract. One price for 0 to 10 tokens. Useful for checking a wallet is funded before a payment, confirming a payout or airdrop landed, tracking agent or treasury wallets, or screening a counterparty. Read-only. Not charged for invalid addresses or when Base can't be reached. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
chain_blockBase mainnet block details for the latest block or a given block number: number, hash, timestamp, transaction count, gas used and limit, and base fee.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Base mainnet block details for the latest block or a given block number: number, hash, timestamp, transaction count, gas used and limit, and base fee. Useful for checking chain head and freshness, timestamping events, and counting confirmations. Read-only. Not charged for an invalid or future block number or when Base can't be reached. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
chain_gasCurrent Base mainnet gas: gas price, base fee, and priority fee in gwei, plus estimated execution cost in ETH for an ETH transfer, a USDC transfer, and a typical swap, from the lat…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Current Base mainnet gas: gas price, base fee, and priority fee in gwei, plus estimated execution cost in ETH for an ETH transfer, a USDC transfer, and a typical swap, from the latest block. Useful for timing transactions and budgeting fees before sending. No input needed. Not charged when Base can't be reached. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
chain_tokenERC-20 token metadata for one contract on Base mainnet: name, symbol, decimals, and total supply (human-readable and raw), with a flag for whether it behaves like an ERC-20 at all …Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it ERC-20 token metadata for one contract on Base mainnet: name, symbol, decimals, and total supply (human-readable and raw), with a flag for whether it behaves like an ERC-20 at all and whether it is native USDC. Handles older tokens that return bytes32 names. Useful for formatting token amounts correctly and spotting look-alike tokens. Read-only. Not charged for an invalid address or an address with no contract. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
chain_txBase mainnet transaction lookup by hash: status (success, failed, or pending), block, timestamp, confirmations, from, to, ETH value, total fee including the L1 data fee, method id,…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Base mainnet transaction lookup by hash: status (success, failed, or pending), block, timestamp, confirmations, from, to, ETH value, total fee including the L1 data fee, method id, and every USDC transfer in the transaction decoded to sender, recipient, and amount. Useful for confirming that a USDC or x402 payment really settled before delivering goods. Read-only. Not charged for an invalid hash, a hash not found on Base, or when Base can't be reached. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
check_emailEmail check: validates the address format, confirms the domain exists and accepts mail (MX), and flags disposable providers, role accounts (info@, support@), and free providers.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Email check: validates the address format, confirms the domain exists and accepts mail (MX), and flags disposable providers, role accounts (info@, support@), and free providers. Returns deliverable_likely, risky, undeliverable, or invalid with a reason. No message is sent. Useful for cleaning sign-up lists and lead data before outreach. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
check_prompt_injectionPrompt injection detection for AI agents: classify untrusted, agent-bound text or a URL (web pages, emails, tool and MCP output, RAG documents) as clean, suspicious or malicious be…Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Prompt injection detection for AI agents: classify untrusted, agent-bound text or a URL (web pages, emails, tool and MCP output, RAG documents) as clean, suspicious or malicious before your LLM reads it. Returns a 0-100 risk score, each matched pattern (instruction overrides, jailbreaks, fake system prompts, requests for keys or seed phrases, exfiltration links, invisible Unicode, hidden HTML) and cleaned text. Up to 50,000 characters. Not charged on bad input. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
check_site_safetyWebsite safety check for one URL.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Website safety check for one URL. Passively fetches the site and returns a verdict (safe, caution, unsafe), a 0-100 score, and evidence-backed flags: TLS validity, HTTP-to-HTTPS redirect, redirect chain and offsite redirects, security headers, mixed content, insecure forms, and domain age from the official registry. Useful before visiting, linking to, buying from, or submitting data to an unfamiliar site. Not charged if the host cannot be checked. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
check_site_safety_proWebsite safety check plus a Google Web Risk lookup for malware, phishing, and unwanted software.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Website safety check plus a Google Web Risk lookup for malware, phishing, and unwanted software. Includes the full /safe report: verdict (safe, caution, unsafe), 0-100 score, TLS, redirects, security headers, mixed content, insecure forms, and domain age. A blocklist hit makes the verdict unsafe. Useful for screening links before a payment, login, or download. Not charged if the blocklist cannot be reached. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
check_sites_batchBatch website safety check: the full /safe report for several URLs in one call, priced per site and cheaper than single checks.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Batch website safety check: the full /safe report for several URLs in one call, priced per site and cheaper than single checks. Each result has a verdict (safe, caution, unsafe), a 0-100 score, and evidence-backed flags for TLS, redirects, security headers, mixed content, insecure forms, and domain age, plus a summary count. Useful for screening every link in a search result, email, or document at once. Not charged if no site can be checked. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
contract_callCall any read-only (view/pure) function on a Base contract and get the decoded answer.Reads text others write1 finding
Why it is in this group
- The name "contract_call" says "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "contract_call" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "contract_call" says "call": a word for a change.
Description, as the server wrote it Call any read-only (view/pure) function on a Base contract and get the decoded answer. Give the function as a signature like balanceOf(address) returns (uint256) plus args, or raw 0x calldata. Supports address, bool, uint/int, bytesN, string, bytes and arrays, an optional historical block, and plain revert reasons. Raw return data is always included. Not charged for invalid input, reverted calls, or when Base can't be reached. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
contract_eventsRecent events (logs) one Base contract emitted, newest first, decoded: token transfers and approvals with amounts, Uniswap/Aerodrome swaps, liquidity and reserve updates, WETH wrap…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Recent events (logs) one Base contract emitted, newest first, decoded: token transfers and approvals with amounts, Uniswap/Aerodrome swaps, liquidity and reserve updates, WETH wraps, NFT transfers, and admin actions (ownership changes, proxy upgrades, pauses, role grants) flagged. Filter by event name to search about 22 hours back. Counts by event type and the block window searched. Read-only. Not charged for invalid input or when Base can't be reached. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
crypto_priceCurrent prices in USD from Chainlink Data Feeds on Base mainnet: ETH, BTC, cbBTC, SOL, USDC, DAI, and EUR.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Current prices in USD from Chainlink Data Feeds on Base mainnet: ETH, BTC, cbBTC, SOL, USDC, DAI, and EUR. One pair or all at once, each with the feed's last update time, age in seconds, and a stale flag, read straight from the oracle contracts (the same prices DeFi protocols use). Useful for valuing balances, converting USDC amounts, and checking a stablecoin peg. Not charged for an unknown pair or when the feeds can't be read. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
domain_reportDomain intelligence: WHOIS/RDAP registration (registrar, created and expiry dates, status, name servers) plus DNS records (A, AAAA, MX, NS, TXT, CAA) and email security (SPF, DMARC…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Domain intelligence: WHOIS/RDAP registration (registrar, created and expiry dates, status, name servers) plus DNS records (A, AAAA, MX, NS, TXT, CAA) and email security (SPF, DMARC), with flags for new, expiring or misconfigured domains, as one JSON object. Useful for vetting a company, vendor or link before trusting it. Not charged for invalid or reserved domain names. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
honeypot_checkHoneypot and sell-tax check for a Base token.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Honeypot and sell-tax check for a Base token. Finds its deepest WETH or USDC pool (Uniswap V2/V3, Aerodrome, Slipstream) and simulates a buy then a sell on a Base node: no money moves. Returns whether selling works, the actual buy tax and sell tax, round-trip loss, pool and liquidity, with a verdict: clean, taxed, high_tax, honeypot, no_liquidity or inconclusive. Useful before an agent buys, swaps or accepts a token. Not charged for invalid input or tokens with no WETH or USDC pool. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
ip_infoClassifies an IPv4 or IPv6 address: family, canonical form, and whether it is public, private (RFC 1918 or unique local), loopback, link-local, carrier-grade NAT, multicast, docume…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Classifies an IPv4 or IPv6 address: family, canonical form, and whether it is public, private (RFC 1918 or unique local), loopback, link-local, carrier-grade NAT, multicast, documentation, or reserved, including IPv4-mapped IPv6. With no input over HTTP, returns the caller's own public IP and country. Useful for validating network input and filtering internal addresses. Not charged for an invalid address. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
link_previewLink preview: returns the title, description, preview image, site name, favicon, canonical URL, and Open Graph/Twitter card details for one URL, like a chat app's link unfurl.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "link_preview" says "link": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "link_preview" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "link_preview" says "link": a word for a change.
Description, as the server wrote it Link preview: returns the title, description, preview image, site name, favicon, canonical URL, and Open Graph/Twitter card details for one URL, like a chat app's link unfurl. Useful when an agent posts, shares, or summarizes links and needs clean metadata without reading the whole page. Not charged if the page can't be fetched. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
new_uuidGenerates standards-compliant UUIDs from a cryptographic random source: version 4 (random) or version 7 (time-ordered, sorts by creation time, good for database keys), one or up to…Reads text others write1 finding
Why it is in this group
- The description's first verb is "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "new_uuid" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The description's first verb is "generate": a word for a change.
Description, as the server wrote it Generates standards-compliant UUIDs from a cryptographic random source: version 4 (random) or version 7 (time-ordered, sorts by creation time, good for database keys), one or up to 100 per call. Useful for idempotency keys, record IDs, and correlation IDs. Not charged for invalid options. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
package_vulnerabilitiesCheck dependencies for known vulnerabilities before installing or shipping: up to 20 packages (npm, PyPI, Go, Maven, crates.io, RubyGems, NuGet, Packagist and more, by name and ver…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Check dependencies for known vulnerabilities before installing or shipping: up to 20 packages (npm, PyPI, Go, Maven, crates.io, RubyGems, NuGet, Packagist and more, by name and version or purl) against the OSV.dev database. Returns each advisory with CVE IDs, severity and CVSS score, fixed versions, the smallest safe upgrade, and links. Not charged for invalid input or if OSV.dev can't be reached. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
random_numberCryptographically secure, unbiased randomness: whole numbers between min and max (default 1 to 100), or random picks from a list of choices, one or up to 100 per call.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Cryptographically secure, unbiased randomness: whole numbers between min and max (default 1 to 100), or random picks from a list of choices, one or up to 100 per call. Useful because language models are bad at being random: fair draws, sampling, shuffling decisions, and A/B assignment. Not charged for invalid options. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
repair_jsonTurns messy LLM output into valid JSON: strips Markdown code fences and surrounding prose, fixes trailing commas, single quotes, unquoted keys, comments, Python True/None, cut-off …Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Turns messy LLM output into valid JSON: strips Markdown code fences and surrounding prose, fixes trailing commas, single quotes, unquoted keys, comments, Python True/None, cut-off brackets, and stringified JSON. Optionally validates the result against a JSON Schema (draft 4 to 2020-12) and lists each error with its location. Returns the parsed data, the JSON text, and what was changed. Not charged if no JSON can be recovered or the input is invalid. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
seo_checkSEO check for one page: whether search engines can index it (meta robots, X-Robots-Tag, robots.txt rules), title and meta description length, canonical URL, H1 headings, viewport, …Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it SEO check for one page: whether search engines can index it (meta robots, X-Robots-Tag, robots.txt rules), title and meta description length, canonical URL, H1 headings, viewport, language, Open Graph tags, sitemap, HTTPS, and redirects, with a 0-100 score and a list of issues by severity. Useful for site audits and pre-launch checks. Not charged if the page can't be fetched. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
token_allowance_checkApproval check for one wallet and one ERC-20 token on Base: how much each spender (up to 10 app or router addresses) is allowed to move, flagging unlimited approvals and approvals …Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Approval check for one wallet and one ERC-20 token on Base: how much each spender (up to 10 app or router addresses) is allowed to move, flagging unlimited approvals and approvals covering the full balance, plus approvals made through Uniswap Permit2 with their expiry. Defaults to checking Permit2 itself. Useful before signing, for wallet hygiene, and for spotting approvals to revoke. Read-only. Not charged for invalid addresses or non-tokens. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
token_holdersThe largest holders of an ERC-20 token on Base, ranked, with balance, percent of supply and wallet/contract/burn type, read straight from the chain.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it The largest holders of an ERC-20 token on Base, ranked, with balance, percent of supply and wallet/contract/burn type, read straight from the chain. Top 1/5/10 concentration (burns excluded), a wallets-only share, burned percent and a low-to-very-high level. For tokens whose whole transfer history fits (most new and small tokens) the list and holder count are exact; otherwise coverage is reported. Not charged for invalid input. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
token_reportRug check and token verdict for any Base token: one answer (ok, caution, avoid or known issuer) with a 0-100 risk score and plain reasons, before you buy, accept or list it.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Rug check and token verdict for any Base token: one answer (ok, caution, avoid or known issuer) with a 0-100 risk score and plain reasons, before you buy, accept or list it. Checks the owner powers in the contract (mint, pause, blacklist, fees, proxy), who holds the supply, whether it can be sold and its real buy/sell tax (simulated), and whether the token or its owner is on the OFAC sanctions list or a scam blacklist. Not charged for invalid input. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
token_safety_checkRisk check for an ERC-20 token on Base before buying, accepting, or holding it: reads the contract and its proxy implementation for owner powers (minting, pausing, blacklisting wal…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Risk check for an ERC-20 token on Base before buying, accepting, or holding it: reads the contract and its proxy implementation for owner powers (minting, pausing, blacklisting wallets, changing buy/sell taxes, trade limits, trading switches, burning others' tokens, upgrades), checks whether ownership was renounced and how much supply the owner holds. Returns a verdict, 0-100 risk score, and plain-language flags. Read-only. Not charged for invalid addresses or non-tokens. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
transcribe_audioSpeech-to-text for one audio or video file by URL, using Whisper (turbo) on a GPU.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Speech-to-text for one audio or video file by URL, using Whisper (turbo) on a GPU. Returns the full transcript, timed segments, ready-made SRT and WebVTT captions, and the detected language; optional translation to English. Files up to 25 MB (about 25 minutes of typical MP3). Useful for captioning videos, indexing podcasts, or reading meetings. Not charged if the file can't be fetched or transcribed. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
verify_urlURL syntax validator.Reads text others writeCan send data out1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...parseable, unsupported scheme, embedded credentials, IP literal, or local/metadata hostname..."
Description, as the server wrote it URL syntax validator. Takes one absolute HTTP or HTTPS URL and returns its normalized form, or a specific error code: unparseable, unsupported scheme, embedded credentials, IP literal, or local/metadata hostname. Never contacts the destination, so it is fast and side-effect free. Useful for cleaning URLs from user input, scraped pages, or LLM output before fetching them. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
wallet_sanctions_checkScreens 1 to 20 wallet addresses against the US Treasury OFAC SDN sanctions list (crypto addresses) and the ScamSniffer scam and drainer blacklist, in one call at one price.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Screens 1 to 20 wallet addresses against the US Treasury OFAC SDN sanctions list (crypto addresses) and the ScamSniffer scam and drainer blacklist, in one call at one price. Returns block or clear per address with the reason, plus list sizes and freshness. Address-level, so it works for Base, Arc, Ethereum and any EVM chain. Useful before sending a payment, paying an x402 seller, accepting funds, or approving a spender. Read-only. Not charged for invalid addresses. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
Only reads 9Show 9 read-only tools
chain_contractInspects one Base mainnet address: whether it holds contract code and how large, whether it is an EIP-1967 upgradeable proxy (and its implementation address), EIP-7702 delegation, …Reads text others writeNo findings
Why it is in this group
- The description's first verb is "inspect": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Inspects one Base mainnet address: whether it holds contract code and how large, whether it is an EIP-1967 upgradeable proxy (and its implementation address), EIP-7702 delegation, and which standards it reports or behaves like (ERC-165, ERC-721 NFT, ERC-1155, ERC-20). Useful for knowing what kind of contract an agent is about to interact with or approve. Read-only. Not charged for an invalid address or when Base can't be reached. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
federal_register_searchSearch the US Federal Register, the government's daily journal of rules, proposed rules, notices and presidential documents.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "federal_register_search" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "document": it reads documents.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search the US Federal Register, the government's daily journal of rules, proposed rules, notices and presidential documents. Filter by keyword, type, agency and date range, only items still open for comment, or look up one document by number. Returns title, agency, publication and effective dates, comment deadline, a trimmed abstract, citation, docket IDs and official links. Useful for agents that monitor regulation. Not charged for invalid input or when nothing matches. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
get_timeCurrent time from a reliable server clock: UTC ISO timestamp, Unix seconds and milliseconds, and optionally the local date, time, weekday, and UTC offset in any IANA time zone (day…Reads text others writeNo findings
Why it is in this group
- The name "get_time" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Current time from a reliable server clock: UTC ISO timestamp, Unix seconds and milliseconds, and optionally the local date, time, weekday, and UTC offset in any IANA time zone (daylight saving handled). Useful because language models don't know the current date or time. Not charged for an unknown time zone. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
list_pricesLists every VerifyLite tool and its current price.No findings
Why it is in this group
- The name "list_prices" says "list": a word for reading.
Description, as the server wrote it Lists every VerifyLite tool and its current price. Free.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
name_lookupResolves Basenames (name.base.eth, on Base) and ENS names (name.eth, on Ethereum) to wallet addresses, including a Base-specific address and profile records (avatar, description, u…Reads text others writeNo findings
Why it is in this group
- The name "name_lookup" says "lookup": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "resolve" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Resolves Basenames (name.base.eth, on Base) and ENS names (name.eth, on Ethereum) to wallet addresses, including a Base-specific address and profile records (avatar, description, url, X, GitHub). Or give an 0x address to get its primary name, verified by resolving the name back to the same address. A bare name like jesse means jesse.base.eth. Useful before sending funds to a name or labeling counterparties. Read-only. Not charged for invalid or unregistered names. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
nft_lookupLook up one NFT on Base by contract and token ID: ERC-721 or ERC-1155, current owner (wallet or contract), collection name and symbol, and its metadata: name, description, image li…Reads text others writeNo findings
Why it is in this group
- The name "nft_lookup" says "lookup": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Look up one NFT on Base by contract and token ID: ERC-721 or ERC-1155, current owner (wallet or contract), collection name and symbol, and its metadata: name, description, image link, animation, traits. Reads ipfs://, ar://, https and inline on-chain metadata. Pass owner to confirm a wallet holds it (and its ERC-1155 balance). Read-only. Not charged for invalid input, tokens that don't exist, or when Base can't be reached. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
pingx402 integration test for agents and payment clients: after a real USDC payment it confirms the payment arrived and echoes back what the server saw: network (Base or Arc), scheme, …Reads text others writeNo findings
Why it is in this group
- The name "ping" says "ping": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it x402 integration test for agents and payment clients: after a real USDC payment it confirms the payment arrived and echoes back what the server saw: network (Base or Arc), scheme, payer address, amount, asset and recipient, plus server time and an optional echo string. Useful for checking that a wallet, x402 client and budget limits work end to end before calling costlier services, and for uptime monitoring. The cheapest paid call VerifyLite offers. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
read_feedRSS and Atom reader: give a feed URL or any news site, blog, or podcast page and get its latest items as clean JSON: title, link, published date, author, a plain-text summary, and …Reads text others writeCan send data outNo findings
Why it is in this group
- The name "read_feed" says "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "rss": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it RSS and Atom reader: give a feed URL or any news site, blog, or podcast page and get its latest items as clean JSON: title, link, published date, author, a plain-text summary, and media (podcast audio) links. Finds the feed automatically from the page when needed. Useful for news monitoring, research digests, and tracking competitors or releases. Not charged if no feed is found or it can't be fetched. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
read_pageWeb page to markdown for AI agents: fetch one URL and get its main content as clean, LLM-ready markdown (navigation, ads, footers and scripts removed) with title, description, lang…Reads text others writeCan send data outNo findings
Why it is in this group
- The name "read_page" says "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "web": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Web page to markdown for AI agents: fetch one URL and get its main content as clean, LLM-ready markdown (navigation, ads, footers and scripts removed) with title, description, language, word count and a token estimate. Uses the site's own Markdown version when it offers one. Useful for RAG, summarizing articles, research and feeding pages to an LLM. Not charged if the page can't be fetched or isn't text. Paid via x402; see list_prices.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
429 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write39
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out11
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__verifylite__federal_register_search"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:00 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 31
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 31 tools that change things (2 irreversible, 29 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://verifylite.hydratinghealingtouch.workers.dev/mcp: tools/list returned 40 tools to an anonymous client, including tx_preflight (irreversible), wallet_transfers (irreversible), verify_url (write), check_site_safety (write), check_site_safety_pro (write) and 26 more
Posture changes
- Nov 6, 2026
- Tools that change things, listed without credentials: 26 to 31
- Oct 29, 2026
- Tools that change things, listed without credentials: 18 to 26
Findings
Matches of fixed checks, with the text they matched.
- Warnlink_preview
The server marks "link_preview" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "link_preview" says "link": a word for a change.
- Warntx_preflight
The server marks "tx_preflight" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
- Warnwallet_transfers
The server marks "wallet_transfers" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "wallet_transfers" says "transfer": a word for a change that another call does not undo.
- Warncontract_call
The server marks "contract_call" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "contract_call" says "call": a word for a change.
- Warnnew_uuid
The server marks "new_uuid" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The description's first verb is "generate": a word for a change.
- Infoverify_url
The description mentions "credentials".
What this check looks forMatched text
description: "...parseable, unsupported scheme, embedded credentials, IP literal, or local/metadata hostname..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 changed.~1 changedView diff
- Changed:token_reportChanges thingstitledescription
PostureRemote posture changed. Tools that change things, listed without credentials: 26 -> 31.View diff
- Tools that change things, listed without credentials: 26 to 31
Tools3 added, 3 changed.+3 added~3 changedView diff
- Added:federal_register_searchOnly reads
- Added:honeypot_checkChanges things
- Added:tx_preflightCan't be undone
- Changed:domain_reportChanges thingsdescription
- Changed:read_pageOnly readsdescription
- Changed:token_reportChanges thingsdescription
Tools31 added.+31 addedView diff
- Added:chain_balanceChanges things
- Added:chain_blockChanges things
- Added:chain_contractOnly reads
- Added:chain_gasChanges things
- Added:chain_tokenChanges things
- Added:chain_txChanges things
- Added:check_emailChanges things
- Added:check_prompt_injectionChanges things
- Added:contract_callChanges things
- Added:contract_eventsChanges things
- Added:crypto_priceChanges things
- Added:domain_reportChanges things
- Added:get_timeOnly reads
- Added:ip_infoChanges things
- Added:link_previewChanges things
- Added:name_lookupOnly reads
- Added:new_uuidChanges things
- Added:nft_lookupOnly reads
- Added:package_vulnerabilitiesChanges things
- Added:pingOnly reads
- Added:random_numberChanges things
- Added:read_feedOnly reads
- Added:read_pageOnly reads
- Added:repair_jsonChanges things
- Added:seo_checkChanges things
- Added:token_allowance_checkChanges things
- Added:token_holdersChanges things
- Added:token_reportChanges things
- Added:token_safety_checkChanges things
- Added:wallet_sanctions_checkChanges things
- Added:wallet_transfersCan't be undone
PostureRemote posture changed. Tools that change things, listed without credentials: 18 -> 26.View diff
- Tools that change things, listed without credentials: 18 to 26
Install
Pinned to version 1.2.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http verifylite https://verifylite.hydratinghealingtouch.workers.dev/mcpclaude mcp add --transport http verifylite https://verifylite.hydratinghealingtouch.workers.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__verifylite__list_prices",
"mcp__verifylite__chain_contract",
"mcp__verifylite__nft_lookup",
"mcp__verifylite__name_lookup",
"mcp__verifylite__federal_register_search",
"mcp__verifylite__get_time",
"mcp__verifylite__ping"
],
"ask": [
"mcp__verifylite__verify_url",
"mcp__verifylite__check_site_safety",
"mcp__verifylite__check_site_safety_pro",
"mcp__verifylite__check_sites_batch",
"mcp__verifylite__transcribe_audio",
"mcp__verifylite__read_page",
"mcp__verifylite__link_preview",
"mcp__verifylite__domain_report",
"mcp__verifylite__check_email",
"mcp__verifylite__seo_check",
"mcp__verifylite__chain_balance",
"mcp__verifylite__chain_tx",
"mcp__verifylite__chain_token",
"mcp__verifylite__chain_gas",
"mcp__verifylite__chain_block",
"mcp__verifylite__token_report",
"mcp__verifylite__honeypot_check",
"mcp__verifylite__tx_preflight",
"mcp__verifylite__token_safety_check",
"mcp__verifylite__token_allowance_check",
"mcp__verifylite__wallet_sanctions_check",
"mcp__verifylite__wallet_transfers",
"mcp__verifylite__contract_events",
"mcp__verifylite__token_holders",
"mcp__verifylite__contract_call",
"mcp__verifylite__crypto_price",
"mcp__verifylite__package_vulnerabilities",
"mcp__verifylite__check_prompt_injection",
"mcp__verifylite__repair_json",
"mcp__verifylite__read_feed",
"mcp__verifylite__new_uuid",
"mcp__verifylite__random_number",
"mcp__verifylite__ip_info"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as verifylite. Review it before you use it.
Capability tags behind 39 rules
- mcp__verifylite__verify_url untrusted-input, outbound
- mcp__verifylite__check_site_safety untrusted-input, outbound
- mcp__verifylite__check_site_safety_pro untrusted-input, outbound
- mcp__verifylite__check_sites_batch untrusted-input, outbound
- mcp__verifylite__transcribe_audio untrusted-input, outbound
- mcp__verifylite__read_page untrusted-input, outbound
- mcp__verifylite__link_preview untrusted-input, outbound
- mcp__verifylite__domain_report untrusted-input
- mcp__verifylite__check_email untrusted-input
- mcp__verifylite__seo_check untrusted-input, outbound
- mcp__verifylite__chain_balance untrusted-input
- mcp__verifylite__chain_tx untrusted-input
- mcp__verifylite__chain_token untrusted-input
- mcp__verifylite__chain_contract untrusted-input
- mcp__verifylite__chain_gas untrusted-input
- mcp__verifylite__chain_block untrusted-input
- mcp__verifylite__token_report untrusted-input
- mcp__verifylite__honeypot_check untrusted-input
- mcp__verifylite__tx_preflight untrusted-input, outbound
- mcp__verifylite__token_safety_check untrusted-input
- mcp__verifylite__token_allowance_check untrusted-input
- mcp__verifylite__wallet_sanctions_check untrusted-input
- mcp__verifylite__wallet_transfers untrusted-input
- mcp__verifylite__contract_events untrusted-input
- mcp__verifylite__token_holders untrusted-input
- mcp__verifylite__nft_lookup untrusted-input
- mcp__verifylite__contract_call untrusted-input
- mcp__verifylite__name_lookup untrusted-input
- mcp__verifylite__crypto_price untrusted-input
- mcp__verifylite__package_vulnerabilities untrusted-input
- mcp__verifylite__check_prompt_injection untrusted-input, outbound
- mcp__verifylite__repair_json untrusted-input
- mcp__verifylite__federal_register_search private-data, untrusted-input
- mcp__verifylite__read_feed untrusted-input, outbound
- mcp__verifylite__get_time untrusted-input
- mcp__verifylite__new_uuid untrusted-input
- mcp__verifylite__random_number untrusted-input
- mcp__verifylite__ip_info untrusted-input
- mcp__verifylite__ping untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.SecondShotAI/verifylite/verify?hash=16c5a2fdfc99ce78578bda0149d4d8bdf9d7f419f084819948f12665f9eabaf0" | jq -e '.changed == false'Pinned hash 16c5a2fdfc99, from Nov 19, 2026, 12:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.SecondShotAI/verifylite/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.SecondShotAI/verifylite)Source: MCP Registry. Synced Nov 5, 2026, 15:17 UTC.
VerifyLite MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the VerifyLite MCP server safe?
- No scan can promise that. What its definitions show: 40 tools, 31 of which can change, send or delete something, and 6 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the VerifyLite MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the VerifyLite MCP server do things that cannot be undone?
- Yes. 2 tools can send, pay, publish or merge: tx_preflight and wallet_transfers.
What tools does the VerifyLite MCP server have?
- 40 tools: 2 irreversible, 29 write, 9 read. tx_preflight, wallet_transfers, verify_url, check_site_safety, check_site_safety_pro, check_sites_batch, transcribe_audio, link_preview and 32 more.
Does the VerifyLite MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the VerifyLite MCP server send data to outside services?
- 11 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): verify_url, check_site_safety, check_site_safety_pro, check_sites_batch, transcribe_audio, read_page and 5 more.
Has the VerifyLite MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.