Alertio MCP server
io.alertio/alertioalertio.iostreamable-httpv1.2.0Scanned
Real-time DeFi risk data: health factors, liquidations, stablecoin pegs, utilization. No API key.
7 tools: 5 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 7
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
5 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 Alertio MCP server can do
The Alertio MCP server is published by alertio.io, a domain the MCP Registry verified. It has 7 tools. It can create or change data (5 tools: scan_wallet, scan_solana_wallet, scan_ton_wallet, simulate_liquidation and 1 more), but cannot delete data. 2 tools only read.
7 tools bring in text other people can write (scan_wallet, scan_solana_wallet, scan_ton_wallet and 4 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 11, 2026, version 1.2.0.
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.
7 tools
Changes things 5Claude Code: ask
calculate_health_factorCalculates a lending health factor from position inputs, with no wallet or on-chain lookup required.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 Calculates a lending health factor from position inputs, with no wallet or on-chain lookup required. Give it collateral (one or more assets, each with its own liquidation threshold) and the debt, and it returns the health factor, the blended threshold, the collateral drop that would trigger liquidation, and the collateral value at which liquidation begins. Optionally simulates a collateral price drop and a change in the borrowed asset's price. Formula: HF = (Σ collateral value × liquidation threshold) ÷ debt. Works for Aave, Morpho, Spark, Kamino and any protocol using the standard formula. Use this when asked: "What is my health factor if I supply 5 ETH at 80% and borrow $6,500?", "How far can ETH fall before I get liquidated?", "What happens to my HF if I add collateral or repay?", "Work out the health factor for this position".
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
scan_solana_walletScans a Solana wallet address for Kamino lending positions and returns active borrowing positions with health factors and liquidation risk.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 Scans a Solana wallet address for Kamino lending positions and returns active borrowing positions with health factors and liquidation risk. Health factor < 1.0 means the position is liquidatable. Use this when asked: "Check Kamino health for this Solana wallet", "Is this Solana address at risk of liquidation?", "What is this wallet borrowing on Solana?"
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
scan_ton_walletScans a TON wallet address on the EVAA lending protocol and returns the active borrowing position with health factor and liquidation risk.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 Scans a TON wallet address on the EVAA lending protocol and returns the active borrowing position with health factor and liquidation risk. Health factor < 1.0 means the position is liquidatable. Use this when asked: "What is the EVAA health factor for this TON wallet?", "Is this TON address at risk on EVAA?", "Check lending risk for EQ…"
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
scan_walletScans an EVM wallet address across all supported lending protocols and returns every active borrowing position with health factors and liquidation risk.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 Scans an EVM wallet address across all supported lending protocols and returns every active borrowing position with health factors and liquidation risk. Covers Aave V3 (7 chains: Ethereum, Base, Arbitrum, Polygon, Optimism, Avalanche, Scroll), Aave V4 (Ethereum Core/Prime/Plus), Spark (Ethereum), Morpho (Ethereum, Base, Arbitrum), Euler (Ethereum, Monad), and Moonwell (Base, Optimism). Health factor < 1.0 means the position is liquidatable. Use this when asked: "Is this wallet at risk of liquidation?", "Show all lending positions for 0x…", "Which protocols is this wallet borrowing from?", "Which of these wallets is closest to liquidation?"
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
simulate_liquidationSimulates the impact of a collateral price drop on all active EVM lending positions for a wallet (Aave V3/V4, Spark, Morpho, Euler, Moonwell).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 Simulates the impact of a collateral price drop on all active EVM lending positions for a wallet (Aave V3/V4, Spark, Morpho, Euler, Moonwell). Formula: newHF = currentHF × (1 − drop%). Shows per-position health factor changes and flags which positions would move to AT RISK, DANGER, or LIQUIDATED. Use this when asked: "What happens to this wallet if ETH drops 30%?", "Would this wallet survive a 40% market crash?", "Stress-test this address at -20% collateral", "Which positions are closest to liquidation if the market drops?"
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 2Show 2 read-only tools
get_market_utilizationReturns Aave V3 lending market utilization rates, supply APY, and borrow APY across 7 chains (Ethereum, Base, Arbitrum, Polygon, Optimism, Avalanche, Scroll).Reads text others writeNo findings
Why it is in this group
- The name "get_market_utilization" 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 Returns Aave V3 lending market utilization rates, supply APY, and borrow APY across 7 chains (Ethereum, Base, Arbitrum, Polygon, Optimism, Avalanche, Scroll). High utilization above the optimal rate causes borrow APY to spike sharply. Also shows if a market is frozen or paused. Use this when asked: "What is the USDC utilization on Aave Ethereum?", "Is there room to borrow WETH on Base?", "Which Aave markets are above optimal utilization?", "What is the current borrow rate for USDC on Arbitrum?", "Are any Aave markets frozen?"
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_stablecoin_pegsReturns real-time USD peg data for the top stablecoins (USDT, USDC, DAI, FRAX, crvUSD, USDS, GHO, and more) sourced from DeFiLlama.Reads text others writeNo findings
Why it is in this group
- The name "get_stablecoin_pegs" 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 Returns real-time USD peg data for the top stablecoins (USDT, USDC, DAI, FRAX, crvUSD, USDS, GHO, and more) sourced from DeFiLlama. Shows current price, deviation from $1.00, and market cap. Flags any coin deviating more than 0.5% as a depeg signal. Use this when asked: "Is USDC currently depegged?", "Which stablecoins are showing depeg signals right now?", "What is DAI trading at?", "Are any stablecoins losing their peg?"
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: 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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write7
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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, 18:55 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
- 5
- 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 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.alertio.io/api/mcp: tools/list returned 7 tools to an anonymous client, including scan_wallet (write), scan_solana_wallet (write), scan_ton_wallet (write), simulate_liquidation (write), calculate_health_factor (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
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 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http alertio https://www.alertio.io/api/mcpclaude mcp add --transport http alertio https://www.alertio.io/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__alertio__get_stablecoin_pegs",
"mcp__alertio__get_market_utilization"
],
"ask": [
"mcp__alertio__scan_wallet",
"mcp__alertio__scan_solana_wallet",
"mcp__alertio__scan_ton_wallet",
"mcp__alertio__simulate_liquidation",
"mcp__alertio__calculate_health_factor"
],
"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 alertio. Review it before you use it.
Capability tags behind 7 rules
- mcp__alertio__scan_wallet untrusted-input
- mcp__alertio__scan_solana_wallet untrusted-input
- mcp__alertio__scan_ton_wallet untrusted-input
- mcp__alertio__simulate_liquidation untrusted-input
- mcp__alertio__calculate_health_factor untrusted-input
- mcp__alertio__get_stablecoin_pegs untrusted-input
- mcp__alertio__get_market_utilization 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.alertio/alertio/verify?hash=251e259fdbb5a174678a9d29e110d23671c5935d5956182ebe2cbc468837bc80" | jq -e '.changed == false'Pinned hash 251e259fdbb5, from Nov 11, 2026, 15:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.alertio/alertio/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.alertio/alertio)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:13 UTC.
Alertio MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Alertio MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 5 of which can change, send or delete something, and 0 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 Alertio MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Alertio 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 Alertio MCP server have?
- 7 tools: 5 write, 2 read. scan_wallet, scan_solana_wallet, scan_ton_wallet, simulate_liquidation, calculate_health_factor, get_stablecoin_pegs and get_market_utilization.
Does the Alertio MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Alertio MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Alertio MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.