# Cybercentry Verification

> Twelve tools: token, wallet, contract and site security. Two free, the rest $1 in USDC over x402.

- name: uk.co.cybercentry/verification
- version: 1.0.4
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/uk.co.cybercentry%2Fverification
- tools: https://api.protogrid.dev/v1/servers/uk.co.cybercentry%2Fverification/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "verification": {
      "type": "http",
      "url": "https://centry.cybercentry.co.uk/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 85
- provenance: 100
- drivers: +repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-100% ~updated-59d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: base_token_verification (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); post_launch_screening (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); pre_launch_screening (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,485 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 2 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 14, about 2,485 tokens to load them all
- tool set hash: 757343f729dc0e58d5dbf6ee0a084ce5
- tools last changed: 2026-09-28T00:20:48.948Z
- badge: [![protogrid quality](https://protogrid.dev/badge/uk.co.cybercentry/verification.svg)](https://protogrid.dev/servers/uk.co.cybercentry/verification)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-09-28 `pre_launch_screening` added
  - 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.
- 2026-09-28 `post_launch_screening` added
  - 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.

Full history: https://api.protogrid.dev/v1/servers/uk.co.cybercentry%2Fverification/changes

## Remotes

- https://centry.cybercentry.co.uk/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (14)

- `base_token_verification`: 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_consultant`: 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_verification`: 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.
- `list_services`: List every Cybercentry verification service with its price, inputs and SLA. Free.
- `media_content_verification`: 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_verification`: 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_screening`: 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_screening`: 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_verification`: 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_verification`: 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_exploits`: Recent real-world web3 exploits from the live feed, with loss amounts, attack vectors and the Cybercentry service that addresses each. Free.
- `solidity_code_verification`: 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_verification`: 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_verification`: 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.