MCP servers › io.github.ak10082247-max › canaryguard-402

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

io.github.ak10082247-max/canaryguard-402

Deterministic prompt-injection detection & sanitization for AI agents via x402 on Base. — the publisher's description

4 of 5 record checks metRead-only · tools listed 2026-10-23Topic: security · AI-classifiedversion 1.0.2TypeScriptstreamable HTTP28 tools

Summary

io.github.ak10082247-max/canaryguard-402 is a remote MCP server listed in the official MCP registry at version 1.0.2. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 28 tools, 0 resources and 0 prompts.

Record checks

4 of 5 record checks met · 4 do not apply

met: Registry entry is active and says how to run it
met: Source repository link opens
met: Repository is not archived
met: Code pushed to the repository in the 90 days before our check
not met: Repository publishes a security policy (SECURITY.md)
not applicable: Package names its licence with a standard (SPDX) identifier
not applicable: The version the registry lists can be installed and is not withdrawn
not applicable: npm package carries build provenance (attestation)
not applicable: No known critical or high advisory in the package or its dependencies

Not ranked by downloads: a remote server publishes no download figure
Not ranked by stars: 0 stars (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs: remote (hosted by the publisher)
Transport: streamable HTTP
Sign-in: none needed to open a session
Repository: public
Tools: 28
Described as changing data: 0 of 28 toolsAI-classified
Mainly works on: nothing outside itself: it only answers questionsAI-classified
Topic: securityAI-classified
Last tested: 2026-10-23

Add to your client

How fresh this is

Live-tested

yes, a real session (not a text-only review)

Last tested

2026-10-23

Mode

read-only (no tool calls)

Latest version

1.0.2, published 2026-10-15 (registry, as of the 2026-10-23 snapshot)

First listed version

2026-10-13 (earliest version still in the registry; older removed versions would be earlier)

Version history

3 versions listed, 2026-10-13 to 2026-10-17; 3 in the 90 days before the 2026-10-23 snapshot.

Most recent 3 versions

1.0.0 · 2026-10-17
1.0.2 · 2026-10-15
1.0.1 · 2026-10-13

(versions still listed in the registry only)

Registry data

snapshot 2026-10-23

Package and repository

checked 2026-10-23

Engine

mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.0.2 (published 2026-10-15).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

28tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: nothing outside itself: it only answers questions.

None of its 28 tools are described as changing anything.

canary_sanitizecalculates or converts
“Deterministic prompt-injection firewall and honeypot scrubber for AI agents.”
Publisher declares: read-only yes · destructive no · open-world yes
2 inputs, 1 required
- contentstringrequired“Untrusted text or web content to sanitize”
- strict_modeboolean
inspectBaseTokenreads or searches
“Audits Base ERC-20 token contracts for honeypot risks, buy/sell transfer taxes, liquidity depth, and prompt injection traps in token metadata.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input, 1 required
- token_addressstringrequired“Base ERC-20 contract address”
checkWalletDrainerreads or searches
“Audits EVM wallet and counterparty addresses on Base for Permit2 drainer exposure, approval phishing history, and OFAC sanctions flags.”
Publisher declares: read-only yes · destructive no · open-world yes
2 inputs, 1 required
- wallet_addressstringrequired“EVM wallet address to screen (0x...)”
- chain_idinteger
auditMcpToolPoisoningreads or searches
“Inspects Model Context Protocol (MCP) tool definitions, descriptions, and JSON schemas for hidden prompt overrides, shadowing attacks, and exfiltration sinks.”
Publisher declares: read-only yes · destructive no · open-world yes
3 inputs, 1 required
- tool_namestringrequired
- tool_descriptionstring
- input_schemaobject
guardAgentMemoryreads or searches
“Scans RAG context chunks, vector DB retrievals, and persistent agent memory payloads for delayed sleeper-agent instructions and cross-session poisoning.”
Publisher declares: read-only yes · destructive no · open-world yes
2 inputs, 1 required
- memory_chunkstringrequired“Memory or RAG chunk to verify before persistence”
- session_idstring
inspectPhishingUrlreads or searches
“Audits target URLs, API endpoints, and Web3 dApp domains for IDN homograph spoofing, Angel/Pink/Inferno drainer scripts, and hidden DOM prompt injections.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input, 1 required
- urlstringrequired“URL or domain to inspect”
checkSmartContractHoneypotreads or searches
“Audits Base smart contracts for hidden transfer locks, owner blacklist modifiers, unverified proxy upgrades, and malicious fee-on-transfer hooks.”
Publisher declares: read-only yes · destructive no · open-world yes
2 inputs, 1 required
- contract_addressstringrequired“Base contract address (0x...)”
- chain_idinteger
auditEip712SignaturePayloadreads or searches
“Audits EIP-712 and EIP-3009 typed-data signature payloads (Permit, Permit2, transferWithAuthorization) to prevent unauthorized token approvals and replay attacks.”
Publisher declares: read-only yes · destructive no · open-world yes
3 inputs, 1 required
- verifying_contractstringrequired
- primary_typestring
- spender_or_tostring
getSafeBaseTrendingreads or searches
“Returns top Base Mainnet tokens by 24h DEX volume and liquidity velocity that pass CanaryGuard zero-honeypot and prompt-injection safety gates.”
Publisher declares: read-only yes · destructive no · open-world yes
2 inputs
- min_liquidity_usdnumber
- limitinteger
getPolymarketVerifiedOddsreads or searches
“Delivers CanaryGuard-sanitized Polymarket CLOB implied probabilities, bid-ask spread depth, and smart-money orderbook skew across high-volume markets.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input
- categorystring
runFullEnterpriseRiskAuditreads or searches
“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…”
Publisher declares: read-only yes · destructive no · open-world yes
3 inputs, 1 required
- target_addressstringrequired“Token, pool, or contract address on Base (0x...)”
- counterparty_walletstring“Optional wallet address to include in AML/drainer audit”
- chain_idinteger
verifyAgentAttestationreads or searches
“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.”
Publisher declares: read-only yes · destructive no · open-world yes
2 inputs, 1 required
- agent_walletstringrequired“Agent or merchant EVM wallet address (0x...)”
- service_domainstring“Optional x402 service domain to verify”

Show 16 more tools

getOndemandMarketSnapshotreads or searches
“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.”
Publisher declares: read-only yes · destructive no · open-world yes
2 inputs
- assetsarray
- include_polymarketboolean
getTokenHistoryAndSpreadreads or searches
“Returns multi-timeframe Base token price history (1h, 24h, 7d, 30d OHLCV summary), Chainlink vs.”
Publisher declares: read-only yes · destructive no · open-world yes
3 inputs
- tokenstring“Token symbol or Base contract address”
- quotestring
- windowstring
getSafeYieldAllocation
“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…”
Publisher declares: read-only yes · destructive no · open-world yes
3 inputs
- capital_usdcnumber
- risk_tolerancestring
- chainsarray
analyzeEvmWalletreads or searches
“Comprehensive EVM wallet security profile on Base, analyzing transaction velocity, approval exposure, drainer interaction risk, and smart-account state.”
Publisher declares: read-only yes · destructive no · open-world yes
2 inputs, 1 required
- wallet_addressstringrequired“EVM wallet address (0x...)”
- chain_idinteger
inspectContractInforeads or searches
“Inspects Base EVM smart contract bytecode size, EIP-1967/UUPS proxy implementation slots, EIP-7702 delegation designators, and verified function selectors.”
Publisher declares: read-only yes · destructive no · open-world yes
2 inputs, 1 required
- contract_addressstringrequired“Smart contract address on Base (0x...)”
- chain_idinteger
checkWalletSanctionsreads or searches
“Screens EVM and Solana wallet addresses against OFAC SDN sanctions lists, Lazarus Group attributions, and known DeFi exploit/drainer blacklists.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input, 1 required
- addressstringrequired“EVM or Solana wallet address to screen”
inspectUniswapPoolStatereads or searches
“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.”
Publisher declares: read-only yes · destructive no · open-world yes
2 inputs, 1 required
- pool_or_token_addressstringrequired“Pool or token address on Base”
- quote_tokenstring
getCryptoPriceOnchainreads or searches
“Returns tamper-resistant on-chain USD spot prices, 24h volatility, and Chainlink/TWAP oracle deviation metrics for major Base and EVM assets.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input, 1 required
- symbolstringrequired
repairAndSanitizeJsoncalculates or converts
“Deterministically repairs malformed or truncated LLM JSON payloads (missing quotes, trailing commas, markdown fences) while scrubbing embedded prompt-injection payloads.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input, 1 required
- raw_jsonstringrequired
auditUrlAgentReadinessreads or searches
“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.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input, 1 required
- urlstringrequired
decodeBaseTxStatusreads or searches
“Decodes Base Mainnet transaction receipts, EIP-3009 transferWithAuthorization settlements, ERC-20 transfer logs, gas fees, and finality confirmations.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input, 1 required
- tx_hashstringrequired
getPolymarketOddsPulsereads or searches
“Delivers sanitized Polymarket CLOB implied probabilities, bid-ask spreads, and 24-hour smart-money volume movers across crypto, macro, and geopolitics.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input
- categorystring
getSafeDefiYieldsreads or searches
“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.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input
- assetstring
calculateLlmTokenPricingcalculates or converts
“Calculates exact input, cached-input, and output token costs across frontier LLMs (OpenAI, Anthropic, Gemini, DeepSeek, Meta) and recommends optimal model routing.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input
- modelstring
auditEip712Signaturereads or searches
“Audits EIP-712 and EIP-3009 typed-data signature payloads (Permit, Permit2, transferWithAuthorization) to block malicious spender approvals and phishing domains.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input, 1 required
- verifying_contractstringrequired
auditMcpToolSchemareads or searches
“Inspects Model Context Protocol (MCP) tool definitions, JSON schemas, and server cards for hidden instructions, tool shadowing, and data exfiltration vectors.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input, 1 required
- tool_namestringrequired

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does: 100% of 28 tools
States limits, defaults or errors: 0% of 28 tools

Counted from the listing

Parameters with a description: 31% of 48
Tools with a description: 100% of 28
Typical description length: 189 characters

The tool set

Counted from the listing

Tools: 28
Size of the list: about 5,023 tokens for an agent to load (characters ÷ 4)
Naming: 27 of 28 names use camelCase

AI reading: easy to mix up

No pair found.

The AI items cover 28 of 28 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai

Settings → Connectors → Add custom connector, then paste:
https://canaryguard-402.onrender.com/mcp

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "canaryguard-402": {
      "url": "https://canaryguard-402.onrender.com/mcp"
    }
  }
}

VS Code · .vscode/mcp.json

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

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"canaryguard-402","type":"http","url":"https://canaryguard-402.onrender.com/mcp"}'

Claude Code

claude mcp add --transport http canaryguard-402 https://canaryguard-402.onrender.com/mcp

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 --server-url https://canaryguard-402.onrender.com/mcp --transport http

The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Remote endpoint canaryguard-402.onrender.com/mcp	Session opened	matches	our test · 2026-10-23
No credential declared as required	Opened a session without any credential	matches	our test · 2026-10-23
Repository github.com/ak10082247-max/canaryguard-402	Opens publicly	matches	api.github.com · 2026-10-23

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: io.github.ak10082247-max · 5 servers
GitHub owner: a personal account (ak10082247-max)

Repository: github.com/ak10082247-max/canaryguard-402
Stars: 0
Repository age: 0–30 days
Last push: 0–30 days ago
Archived: no
Security policy: none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

4 of 5 record checks met · 4 do not apply

Not ranked by downloads: a remote server publishes no download figure
Not ranked by stars: 0 stars (ranked from 10)

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
MetSource repository link opensThe linked GitHub repository is public.
MetRepository is not archivedNot archived.
MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about io.github.ak10082247-max/canaryguard-402

Answered from the data above

Is io.github.ak10082247-max/canaryguard-402 safe to install?

We do not rate servers as safe or unsafe. 4 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does io.github.ak10082247-max/canaryguard-402 need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.

Has io.github.ak10082247-max/canaryguard-402 been security tested?

Partly. 2 of the 14 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security verdict is published before verification.

What can io.github.ak10082247-max/canaryguard-402 do?

It lists 28 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search and calculate or convert. We did not call any tool, so this describes the text, not the behaviour.

Can io.github.ak10082247-max/canaryguard-402 change or delete data?

None of its 28 tools is described as changing anything (our AI model's reading of the descriptions; nobody checked it by hand). We did not call any tool.

Does io.github.ak10082247-max/canaryguard-402 publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Where is the source code of io.github.ak10082247-max/canaryguard-402?

In github.com/ak10082247-max/canaryguard-402, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

io.github.hashgraph-online/hol-guardHOL Guardalso has tools that calculates or converts, reads or searchescompare with this one
io.github.dengyier/OpenWorkProofalso has tools that calculates or converts, reads or searchescompare with this one
com.contrastcyber/apiContrastAPIalso has tools that calculates or converts, reads or searchescompare with this one
io.github.ethanolivertroy/fedramp-docs-mcpalso has tools that calculates or converts, reads or searchescompare with this one
io.github.quantakrypto/pqc-toolsquantakrypto pqc-toolsalso has tools that calculates or converts, reads or searchescompare with this one
io.github.crunchtools/trentinaTrentinaalso has tools that calculates or converts, reads or searchescompare with this one

Active servers whose topic is also “security” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (we call no server's tools)

We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: not run · nothing to check it against
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not run · our policy
Consent handling: not testable from outside
Sign-in metadata: not applicable

2 exercised12 not run (reason given)4 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 2

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised

Not run, with the reason · 12

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside

Does not apply to this server · 4

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable

Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

0 msStarted a read-only session with the server's remote endpoint
695 msConnected after 0 redirects. No credential was sent or needed.
Read the inventory: 28 tools, 0 resources, 0 prompts.
3,818 msFinished: 2 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified

security

AI-classified · 2026-10-23

Pricing modelAI-classified

not known (our limit)

We could not fetch the website with a plain request. This is our limit, not the site's.

Programming language

TypeScript

api.github.com · 2026-10-23

Hosting type

remote (hosted by the publisher)

registry · 2026-10-23

MCP capability

tools

our test · 2026-10-23

Transport

streamable HTTP

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

does not apply

remote-only server: no package is shipped, so there is no package registry

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Integrity hash

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Signature / provenance

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Dependency advisories

does not apply

ships no package, so there are no dependencies to audit

Popularity

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Publisher signals

owner: a personal account · repository age: 0–30 days · stars: 0–9

api.github.com · 2026-10-23

Maintenance

active

api.github.com · 2026-10-23

Environment

the publisher's infrastructure

where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “io.github.ak10082247-max/canaryguard-402: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.ak10082247-max/canaryguard-402

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/io.github.ak10082247-max/canaryguard-402)](https://protocolprobe.com/mcp/servers/io.github.ak10082247-max/canaryguard-402)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology