# CanaryGuard 402 (remote · canaryguard-402.onrender.com)

Deterministic prompt-injection detection & sanitization for AI agents via x402 on Base.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `canaryguard-402.onrender.com`: 69/100 (this document), [markdown](https://verifymcp.io/servers/ak10082247-max-canaryguard-402/canaryguard-402.md), [page](https://verifymcp.io/servers/ak10082247-max-canaryguard-402/canaryguard-402)

## Channel facts

- Endpoint: `https://canaryguard-402.onrender.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2499 tokens (~73/item across 34 items; 34 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 75/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 26% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 34 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 34 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the CanaryGuard 402 MCP server?

CanaryGuard 402 is a hosted endpoint at https://canaryguard-402.onrender.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ak10082247-max-canaryguard-402 'https://canaryguard-402.onrender.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ak10082247-max-canaryguard-402": {
      "url": "https://canaryguard-402.onrender.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ak10082247-max-canaryguard-402": {
      "type": "http",
      "url": "https://canaryguard-402.onrender.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ak10082247-max-canaryguard-402]
url = "https://canaryguard-402.onrender.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ak10082247-max-canaryguard-402": {
      "type": "remote",
      "url": "https://canaryguard-402.onrender.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ak10082247-max-canaryguard-402 --url 'https://canaryguard-402.onrender.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ak10082247-max-canaryguard-402:
    url: "https://canaryguard-402.onrender.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ak10082247-max-canaryguard-402": {
      "Transport": "http",
      "Url": "https://canaryguard-402.onrender.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ak10082247-max-canaryguard-402 -t streamable-http -u 'https://canaryguard-402.onrender.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ak10082247-max-canaryguard-402": {
      "type": "http",
      "url": "https://canaryguard-402.onrender.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 69, +1)

- [functional regression] Schema quality: 2106 → 2499
- [functional regression] Tool coverage: 31% → 26%
- [functional] New tool “nansenProfilerAddressBalance”
- [functional] New tool “nansenSmartMoneyDexTrades”
- [functional] New tool “nansenSmartMoneyNetflow”
- [functional] New tool “nansenTgmHolders”
- [functional] New tool “nansenTgmWhoBoughtSold”
- [functional] New tool “nansenTokenScreener”

### 2026-10-17 (score 68, −2)

- [security] Tool “canary_sanitize” rewrote its description, which is the text the model reads
- [functional regression] MCP protocol: pass → fail
- [functional improvement] Tool coverage: 0% → 31%
- [functional improvement] Schema quality: 85 → 75
- [functional] MCP protocol version: 2025-11-25 → 2024-11-05
- [functional] Server version: 1.2.0 → 1.3.0
- [functional] New tool “analyzeEvmWallet”
- [functional] New tool “auditEip712Signature”
- [functional] New tool “auditEip712SignaturePayload”
- [functional] New tool “auditMcpToolPoisoning”
- [functional] New tool “auditMcpToolSchema”
- [functional] New tool “auditUrlAgentReadiness”
- [functional] New tool “calculateLlmTokenPricing”
- [functional] New tool “checkSmartContractHoneypot”
- [functional] New tool “checkWalletDrainer”
- [functional] New tool “checkWalletSanctions”
- [functional] New tool “decodeBaseTxStatus”
- [functional] New tool “getCryptoPriceOnchain”
- [functional] New tool “getOndemandMarketSnapshot”
- [functional] New tool “getPolymarketOddsPulse”
- [functional] New tool “getPolymarketVerifiedOdds”
- [functional] New tool “getSafeBaseTrending”
- [functional] New tool “getSafeDefiYields”
- [functional] New tool “getSafeYieldAllocation”
- [functional] New tool “getTokenHistoryAndSpread”
- [functional] New tool “guardAgentMemory”
- [functional] New tool “inspectBaseToken”
- [functional] New tool “inspectContractInfo”
- [functional] New tool “inspectPhishingUrl”
- [functional] New tool “inspectUniswapPoolState”
- [functional] New tool “repairAndSanitizeJson”
- [functional] New tool “runFullEnterpriseRiskAudit”
- [functional] New tool “verifyAgentAttestation”
- [cosmetic] “canary_sanitize” reworded the description of “content”

### 2026-10-16 (score 70, 0)

- [security] Tool “canary_sanitize” rewrote its description, which is the text the model reads
- [functional] Server version: 1.0.1 → 1.2.0

### 2026-10-15 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 69, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-13 (score 69)

First indexed and scored.

## MCP tools (34)

### `canary_sanitize` (~77 tokens)

Deterministic prompt-injection firewall and honeypot scrubber for AI agents. Sanitizes untrusted text and blocks detected wallet-draining commands before context ingestion. Price: 0.010 USDC on Base.

Input parameters:

- `content` (string, required): Untrusted text or web content to sanitize
- `strict_mode` (boolean)

### `inspectBaseToken` (~65 tokens)

Audits Base ERC-20 token contracts for honeypot risks, buy/sell transfer taxes, liquidity depth, and prompt injection traps in token metadata. Price: 0.010 USDC on Base.

Input parameters:

- `token_address` (string, required): Base ERC-20 contract address

### `checkWalletDrainer` (~74 tokens)

Audits EVM wallet and counterparty addresses on Base for Permit2 drainer exposure, approval phishing history, and OFAC sanctions flags. Price: 0.02 USDC on Base.

Input parameters:

- `chain_id` (integer)
- `wallet_address` (string, required): EVM wallet address to screen (0x...)

### `auditMcpToolPoisoning` (~80 tokens)

Inspects Model Context Protocol (MCP) tool definitions, descriptions, and JSON schemas for hidden prompt overrides, shadowing attacks, and exfiltration sinks. Price: 0.02 USDC on Base.

Input parameters:

- `input_schema` (object)
- `tool_description` (string)
- `tool_name` (string, required)

### `guardAgentMemory` (~73 tokens)

Scans RAG context chunks, vector DB retrievals, and persistent agent memory payloads for delayed sleeper-agent instructions and cross-session poisoning. Price: 0.02 USDC on Base.

Input parameters:

- `memory_chunk` (string, required): Memory or RAG chunk to verify before persistence
- `session_id` (string)

### `inspectPhishingUrl` (~71 tokens)

Audits target URLs, API endpoints, and Web3 dApp domains for IDN homograph spoofing, Angel/Pink/Inferno drainer scripts, and hidden DOM prompt injections. Price: 0.02 USDC on Base.

Input parameters:

- `url` (string, required): URL or domain to inspect

### `checkSmartContractHoneypot` (~72 tokens)

Audits Base smart contracts for hidden transfer locks, owner blacklist modifiers, unverified proxy upgrades, and malicious fee-on-transfer hooks. Price: 0.02 USDC on Base.

Input parameters:

- `chain_id` (integer)
- `contract_address` (string, required): Base contract address (0x...)

### `auditEip712SignaturePayload` (~84 tokens)

Audits EIP-712 and EIP-3009 typed-data signature payloads (Permit, Permit2, transferWithAuthorization) to prevent unauthorized token approvals and replay attacks. Price: 0.02 USDC on Base.

Input parameters:

- `primary_type` (string)
- `spender_or_to` (string)
- `verifying_contract` (string, required)

### `getSafeBaseTrending` (~72 tokens)

Returns top Base Mainnet tokens by 24h DEX volume and liquidity velocity that pass CanaryGuard zero-honeypot and prompt-injection safety gates. Price: 0.02 USDC on Base.

Input parameters:

- `limit` (integer)
- `min_liquidity_usd` (number)

### `getPolymarketVerifiedOdds` (~62 tokens)

Delivers CanaryGuard-sanitized Polymarket CLOB implied probabilities, bid-ask spread depth, and smart-money orderbook skew across high-volume markets. Price: 0.02 USDC on Base.

Input parameters:

- `category` (string)

### `runFullEnterpriseRiskAudit` (~114 tokens)

Enterprise 360-degree security audit bundle combining Base bytecode/proxy inspection, DEX liquidity rug-risk analysis, OFAC/Lazarus sanctions screening, EIP-712 permit verification, and deterministic prompt-injection firewalling. Price: 0.020 USDC on Base.

Input parameters:

- `chain_id` (integer)
- `counterparty_wallet` (string): Optional wallet address to include in AML/drainer audit
- `target_address` (string, required): Token, pool, or contract address on Base (0x...)

### `verifyAgentAttestation` (~91 tokens)

Generates a cryptographic attestation report verifying an autonomous AI agent wallet, x402 EIP-3009 payment capability, counterparty reputation score, and zero-drainer history on Base. Price: 0.020 USDC on Base.

Input parameters:

- `agent_wallet` (string, required): Agent or merchant EVM wallet address (0x...)
- `service_domain` (string): Optional x402 service domain to verify

### `getOndemandMarketSnapshot` (~79 tokens)

On-demand institutional market intelligence snapshot combining Base DEX spot & TWAP prices, Aerodrome/Uniswap V3 liquidity depth, perpetual funding rates, and Polymarket whale orderbook divergence. Price: 0.020 USDC on Base.

Input parameters:

- `assets` (array)
- `include_polymarket` (boolean)

### `getTokenHistoryAndSpread` (~102 tokens)

Returns multi-timeframe Base token price history (1h, 24h, 7d, 30d OHLCV summary), Chainlink vs. Uniswap V3/Aerodrome bid-ask spread in bps, and realized volatility skew. Price: 0.020 USDC on Base.

Input parameters:

- `quote` (string)
- `token` (string): Token symbol or Base contract address
- `window` (string)

### `getSafeYieldAllocation` (~99 tokens)

Computes an institutional risk-adjusted DeFi capital allocation matrix across multi-audited Base and Arbitrum liquidity vaults (Morpho Blue, Aave V3, Moonwell, Aerodrome) with smart-contract timelock and depeg stress scores. Price: 0.020 USDC on Base.

Input parameters:

- `capital_usdc` (number)
- `chains` (array)
- `risk_tolerance` (string)

### `analyzeEvmWallet` (~70 tokens)

Comprehensive EVM wallet security profile on Base, analyzing transaction velocity, approval exposure, drainer interaction risk, and smart-account state. Price: 0.010 USDC on Base.

Input parameters:

- `chain_id` (integer)
- `wallet_address` (string, required): EVM wallet address (0x...)

### `inspectContractInfo` (~80 tokens)

Inspects Base EVM smart contract bytecode size, EIP-1967/UUPS proxy implementation slots, EIP-7702 delegation designators, and verified function selectors. Price: 0.010 USDC on Base.

Input parameters:

- `chain_id` (integer)
- `contract_address` (string, required): Smart contract address on Base (0x...)

### `checkWalletSanctions` (~69 tokens)

Screens EVM and Solana wallet addresses against OFAC SDN sanctions lists, Lazarus Group attributions, and known DeFi exploit/drainer blacklists. Price: 0.010 USDC on Base.

Input parameters:

- `address` (string, required): EVM or Solana wallet address to screen

### `inspectUniswapPoolState` (~83 tokens)

Audits Uniswap V3/V4 and Aerodrome liquidity pools on Base, returning tick liquidity depth, fee tier, price impact bps, and LP concentration rug-risk scores. Price: 0.010 USDC on Base.

Input parameters:

- `pool_or_token_address` (string, required): Pool or token address on Base
- `quote_token` (string)

### `getCryptoPriceOnchain` (~61 tokens)

Returns tamper-resistant on-chain USD spot prices, 24h volatility, and Chainlink/TWAP oracle deviation metrics for major Base and EVM assets. Price: 0.010 USDC on Base.

Input parameters:

- `symbol` (string, required)

### `repairAndSanitizeJson` (~62 tokens)

Deterministically repairs malformed or truncated LLM JSON payloads (missing quotes, trailing commas, markdown fences) while scrubbing embedded prompt-injection payloads. Price: 0.010 USDC on Base.

Input parameters:

- `raw_json` (string, required)

### `auditUrlAgentReadiness` (~69 tokens)

Audits any domain or URL for AI agent readiness (llms.txt, .well-known/x402, openapi.json, MCP server card) and detects hidden CSS/DOM prompt-injection traps. Price: 0.010 USDC on Base.

Input parameters:

- `url` (string, required)

### `decodeBaseTxStatus` (~61 tokens)

Decodes Base Mainnet transaction receipts, EIP-3009 transferWithAuthorization settlements, ERC-20 transfer logs, gas fees, and finality confirmations. Price: 0.010 USDC on Base.

Input parameters:

- `tx_hash` (string, required)

### `getPolymarketOddsPulse` (~64 tokens)

Delivers sanitized Polymarket CLOB implied probabilities, bid-ask spreads, and 24-hour smart-money volume movers across crypto, macro, and geopolitics. Price: 0.010 USDC on Base.

Input parameters:

- `category` (string)

### `getSafeDefiYields` (~78 tokens)

Curates top risk-adjusted USDC, EURC, and WETH DeFi yield pools on Base (Morpho, Aave V3, Aerodrome, Moonwell), pre-screened for TVL depth and audit status. Price: 0.010 USDC on Base.

Input parameters:

- `asset` (string)

### `calculateLlmTokenPricing` (~65 tokens)

Calculates exact input, cached-input, and output token costs across frontier LLMs (OpenAI, Anthropic, Gemini, DeepSeek, Meta) and recommends optimal model routing. Price: 0.010 USDC on Base.

Input parameters:

- `model` (string)

### `auditEip712Signature` (~66 tokens)

Audits EIP-712 and EIP-3009 typed-data signature payloads (Permit, Permit2, transferWithAuthorization) to block malicious spender approvals and phishing domains. Price: 0.010 USDC on Base.

Input parameters:

- `verifying_contract` (string, required)

### `auditMcpToolSchema` (~63 tokens)

Inspects Model Context Protocol (MCP) tool definitions, JSON schemas, and server cards for hidden instructions, tool shadowing, and data exfiltration vectors. Price: 0.010 USDC on Base.

Input parameters:

- `tool_name` (string, required)

### `nansenTokenScreener` (~77 tokens)

Screens trending Solana (Pump.fun/Raydium) and Base (Aerodrome/Uniswap V3) tokens with pre-verified honeypot, tax, and liquidity depth metrics. Price: 0.010 USDC on Base.

Input parameters:

- `chain` (string)
- `token_address` (string)

### `nansenSmartMoneyNetflow` (~63 tokens)

Tracks institutional and high-win-rate whale wallet net inflows and outflows across Solana SPL and Base ERC-20 tokens. Price: 0.010 USDC on Base.

Input parameters:

- `chain` (string)
- `token_address` (string)

### `nansenSmartMoneyDexTrades` (~66 tokens)

Returns real-time DEX trades executed by labeled smart-money and whale wallets on Solana and Base with pre-trade honeypot verification. Price: 0.010 USDC on Base.

Input parameters:

- `chain` (string)
- `token_address` (string)

### `nansenTgmWhoBoughtSold` (~70 tokens)

Analyzes who bought and sold a specific Solana or Base token over the last 24h, segmented by Smart Money, Whales, Fresh Wallets, and Dev Clusters. Price: 0.010 USDC on Base.

Input parameters:

- `token_address` (string)

### `nansenTgmHolders` (~59 tokens)

Returns top-10/top-50 holder distribution, LP lock percentage, and coordinated sybil cluster detection for any Solana or Base token. Price: 0.010 USDC on Base.

Input parameters:

- `token_address` (string)

### `nansenProfilerAddressBalance` (~58 tokens)

Profiles any Solana or Base wallet address for current token balances, USD valuation, historical win-rate, and drainer/OFAC taint. Price: 0.010 USDC on Base.

Input parameters:

- `address` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ak10082247-max-canaryguard-402/canaryguard-402#diagnostics

## Score history

- 2026-10-18: 69
- 2026-10-17: 68
- 2026-10-16: 70
- 2026-10-15: 70
- 2026-10-14: 69
- 2026-10-13: 69

## Common questions

### What is the CanaryGuard 402 MCP server?

CanaryGuard 402 is an MCP server listed in the public MCP registry as io.github.ak10082247-max/canaryguard-402. Deterministic prompt-injection detection & sanitization for AI agents via x402 on Base. This page covers its hosted endpoint (https://canaryguard-402.onrender.com/mcp).

### Is the CanaryGuard 402 MCP server safe to use?

CanaryGuard 402 scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the CanaryGuard 402 MCP server expose?

CanaryGuard 402 exposes 34 tools: canary_sanitize, inspectBaseToken, checkWalletDrainer, auditMcpToolPoisoning, guardAgentMemory, and 29 more. Their descriptions and schemas cost roughly 2,499 tokens of context every time the server is loaded.

### Does the CanaryGuard 402 MCP server require authentication?

No. We connected to CanaryGuard 402 without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the CanaryGuard 402 MCP server still maintained?

CanaryGuard 402 is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://canaryguard-402.onrender.com/mcp
- Repository: https://github.com/ak10082247-max/canaryguard-402
- Website: https://canaryguard-402.onrender.com/
- Changelog RSS feed: https://verifymcp.io/servers/ak10082247-max-canaryguard-402/canaryguard-402.xml
- Changelog JSON feed: https://verifymcp.io/servers/ak10082247-max-canaryguard-402/canaryguard-402.json
- HTML version of this page: https://verifymcp.io/servers/ak10082247-max-canaryguard-402/canaryguard-402