Cybercentry Verification MCP server
uk.co.cybercentry/verificationcybercentry.co.ukstreamable-httpv1.0.4Scanned
Twelve tools: token, wallet, contract and site security. Two free, the rest $1 in USDC over x402.
14 tools: 13 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 2
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
13 tools here change things. 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 Cybercentry Verification MCP server can do
The Cybercentry Verification MCP server is published by cybercentry.co.uk, a domain the MCP Registry verified. It has 14 tools. It can create or change data (13 tools: recent_exploits, base_token_verification, cyber_security_consultant, ethereum_token_verification and 9 more), but cannot delete data. 1 tool only reads.
2 tools can send data out of your system (post_launch_screening and web_application_verification).
The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 18, 2026, version 1.0.4.
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.
14 tools
Changes things 13Claude Code: ask
base_token_verificationCheck a Base token contract before buying: detects honeypots, armed freeze-and-seize, a live pause, fake B20s and ticker-impersonation copycats, and separately discloses issuer con…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Check a Base token contract before buying: detects honeypots, armed freeze-and-seize, a live pause, fake B20s and ticker-impersonation copycats, and separately discloses issuer controls (admin centralisation, supply cap, transfer policy, rebase) so a legitimate token is not mistaken for a scam. Costs $1.00 per call, paid in USDC over x402.
cyber_security_consultantAsk a cyber security question and get an expert answer backed by real-time threat intelligence, covering current threats, best practice and compliance.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Ask a cyber security question and get an expert answer backed by real-time threat intelligence, covering current threats, best practice and compliance. Costs $1.00 per call, paid in USDC over x402.
ethereum_token_verificationCheck an Ethereum or EVM token contract before buying: rug pull, hidden tax, liquidity legitimacy and holder concentration risk.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Check an Ethereum or EVM token contract before buying: rug pull, hidden tax, liquidity legitimacy and holder concentration risk. Token due diligence returned as a scan report. Costs $1.00 per call, paid in USDC over x402.
media_content_verificationCheck whether an image or video is authentic and where it came from: C2PA content credentials, provenance and metadata extraction, with an avatar and logo impersonation check.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...ic and where it came from: C2PA content credentials, provenance and metadata extraction, wi..."
Description, as the server wrote it Check whether an image or video is authentic and where it came from: C2PA content credentials, provenance and metadata extraction, with an avatar and logo impersonation check. Detect AI-generated or tampered media before trusting it. Costs $1.00 per call, paid in USDC over x402.
openclaw_ai_agent_verificationAudit an AI agent configuration for security holes: prompt injection exposure, missing authentication, over-broad tool permissions and unsafe gateway settings.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Audit an AI agent configuration for security holes: prompt injection exposure, missing authentication, over-broad tool permissions and unsafe gateway settings. Check an agent before you trust it or connect to it. Costs $1.00 per call, paid in USDC over x402.
post_launch_screeningScore a live token launch under ERC-8376, the token launch abuse standard we co-authored.Can send data outNo findings
Why it is in this group
- The name "post_launch_screening" says "post": a word for a change.
What it can reach
- outboundThe name "post_launch_screening" says "post": it sends or publishes something to other people.
Description, as the server wrote it Score a live token launch under ERC-8376, the token launch abuse standard we co-authored. The twelve-signal vector is assembled from chain state and scored against the eleven deployer abuse patterns into an abuse score of 0 to 100, with confidence reported separately so a high score on thin evidence cannot read as a certainty. Signals that could not be computed are named rather than scored clean. Price decline is excluded by rule, so a launch that locked liquidity, sold nothing and fell 95 per cent still scores clean: falling is not fraud. Name the creator, because at most venues the token was deployed by the venue's own factory and the creating address is the launchpad rather than the applicant. A screening, not a bonded on-chain report. Costs $1.00 per call, paid in USDC over x402.
pre_launch_screeningScreen who is asking to launch, before you deploy anything for them.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Screen who is asking to launch, before you deploy anything for them. At most venues the launchpad creates the token, so the only thing in front of you beforehand is a connected wallet: this screens that wallet, and it includes the full wallet verification rather than a summary of one. OFAC SDN sanctions screening, the funding chain walked to depth across 33 chains, mixer contact including the Tornado Cash pools, dusting, control clusters and exchange reuse, with a risk score. Then the launch-specific half: allocations this wallet has taken from contracts before and whether it still holds them or sold them, and whether the ticker it wants collides with a token it already touched. Says what it could not establish rather than reporting it clean. Eight of the twelve ERC-8376 signals describe conduct during or after a sale and cannot exist yet, so this reports on the party and not on the launch. Costs $1.00 per call, paid in USDC over x402.
private_data_verificationProve a fact about private data without revealing the data: validates text integrity and returns a zero-knowledge proof (ZKP) with a verification ID and URL.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Prove a fact about private data without revealing the data: validates text integrity and returns a zero-knowledge proof (ZKP) with a verification ID and URL. Costs $1.00 per call, paid in USDC over x402.
quantum_cryptography_verificationEncrypt text with quantum-resistant (post-quantum) cryptography, for secrets that must outlast classical encryption.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Encrypt text with quantum-resistant (post-quantum) cryptography, for secrets that must outlast classical encryption. Returns a record ID and a decrypt URL. Costs $1.00 per call, paid in USDC over x402.
recent_exploitsRecent real-world web3 exploits from the live feed, with loss amounts, attack vectors and the Cybercentry service that addresses each.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Recent real-world web3 exploits from the live feed, with loss amounts, attack vectors and the Cybercentry service that addresses each. Free.
solidity_code_verificationAudit Solidity smart contract source for vulnerabilities before you deploy or call it.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Audit Solidity smart contract source for vulnerabilities before you deploy or call it. Returns findings with a clear risk level. Costs $1.00 per call, paid in USDC over x402.
wallet_verificationScreen a wallet address for sanctions and risk: OFAC SDN sanctions screening, risk scoring and suspicious-activity detection across 33 EVM chains.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Screen a wallet address for sanctions and risk: OFAC SDN sanctions screening, risk scoring and suspicious-activity detection across 33 EVM chains. Check a counterparty before you transact with it. Costs $1.00 per call, paid in USDC over x402.
web_application_verificationScan a website or dApp frontend for vulnerabilities using OWASP checks, before connecting a wallet to it or trusting it with user data.Can 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.
What it can reach
- outboundThe input takes a URL (input.target_url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Scan a website or dApp frontend for vulnerabilities using OWASP checks, before connecting a wallet to it or trusting it with user data. Costs $1.00 per call, paid in USDC over x402.
Only reads 1Show 1 read-only tool
list_servicesList every Cybercentry verification service with its price, inputs and SLA.No findings
Why it is in this group
- The name "list_services" says "list": a word for reading.
Description, as the server wrote it List every Cybercentry verification service with its price, inputs and SLA. Free.
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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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, 19:20 UTC, unchanged since Oct 22, 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
- 13
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 13 tools that change things (13 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://centry.cybercentry.co.uk/api/mcp: tools/list returned 14 tools to an anonymous client, including recent_exploits (write), base_token_verification (write), cyber_security_consultant (write), ethereum_token_verification (write), media_content_verification (write) and 8 more
Findings
Matches of fixed checks, with the text they matched.
The description mentions "credentials".
What this check looks forMatched text
description: "...ic and where it came from: C2PA content credentials, provenance and metadata extraction, wi..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.4. Values in angle brackets are yours to fill in.
claude mcp add --transport http verification https://centry.cybercentry.co.uk/api/mcpclaude mcp add --transport http verification https://centry.cybercentry.co.uk/api/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__verification__list_services"
],
"ask": [
"mcp__verification__recent_exploits",
"mcp__verification__base_token_verification",
"mcp__verification__cyber_security_consultant",
"mcp__verification__ethereum_token_verification",
"mcp__verification__media_content_verification",
"mcp__verification__openclaw_ai_agent_verification",
"mcp__verification__post_launch_screening",
"mcp__verification__pre_launch_screening",
"mcp__verification__private_data_verification",
"mcp__verification__quantum_cryptography_verification",
"mcp__verification__solidity_code_verification",
"mcp__verification__wallet_verification",
"mcp__verification__web_application_verification"
],
"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 verification. Review it before you use it.
Capability tags behind 2 rules
- mcp__verification__post_launch_screening outbound
- mcp__verification__web_application_verification outbound
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/uk.co.cybercentry/verification/verify?hash=bd0d6fa1d1efc8192ef79a29d67ffd0027149226cfd3106deefbd1fd358b9e12" | jq -e '.changed == false'Pinned hash bd0d6fa1d1ef, from Nov 18, 2026, 09:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/uk.co.cybercentry/verification/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/uk.co.cybercentry/verification)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:55 UTC.
Cybercentry Verification MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Cybercentry Verification MCP server safe?
- No scan can promise that. What its definitions show: 14 tools, 13 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Cybercentry Verification MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Cybercentry Verification MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Cybercentry Verification MCP server have?
- 14 tools: 13 write, 1 read. recent_exploits, base_token_verification, cyber_security_consultant, ethereum_token_verification, media_content_verification, openclaw_ai_agent_verification, post_launch_screening, pre_launch_screening and 6 more.
Does the Cybercentry Verification MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Cybercentry Verification MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): post_launch_screening and web_application_verification.
Has the Cybercentry Verification MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.