Agent Risk Desk MCP server
io.github.soldanoandrea/agent-risk-desksoldanoandreastreamable-httpv0.2.0Scanned
EVM address enrichment, counterparty risk and tx screening for agents, paid per call in USDC (x402)
7 tools: 6 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 6
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
6 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 Agent Risk Desk MCP server can do
The Agent Risk Desk MCP server is published by the GitHub account soldanoandrea. It has 7 tools. It can create or change data (6 tools: enrich_evm_address, counterparty_risk_evm, counterparty_risk_near, verify_allowance_receipt and 2 more), but cannot delete data. 1 tool only reads.
6 tools bring in text other people can write (enrich_evm_address, counterparty_risk_evm, counterparty_risk_near and 3 more); 1 tool can send data out of your system (render_page).
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, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 13, 2026, version 0.2.0.
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 6Claude Code: ask
counterparty_risk_evmCounterparty-risk verdict (allow, warn or block, with reasons) for an EVM address on Base, Ethereum, OP Mainnet, Arbitrum or Base Sepolia, for use before paying, approving or trust…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 Counterparty-risk verdict (allow, warn or block, with reasons) for an EVM address on Base, Ethereum, OP Mainnet, Arbitrum or Base Sepolia, for use before paying, approving or trusting it. Checks the OFAC SDN list and the Chainalysis sanctions oracle, account age, EOA or contract, EIP-7702 delegation, upgradeable proxies and code changes in the last 72 h, and token controls (mint, blacklist, pause, fees, owner). Price: $0.02 USDC per call (x402).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
counterparty_risk_nearCounterparty-risk verdict (allow, warn or block, with reasons) for a NEAR account, for use before paying it.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 Counterparty-risk verdict (allow, warn or block, with reasons) for a NEAR account, for use before paying it. Checks the OFAC SDN list and operator deny-lists, whether the account exists, its age, its contract code and code changes in the last 72 h, global contracts whose publisher can change them, and, with an Allowance vault, the vault denylist and payment history. Price: $0.02 USDC per call (x402).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
enrich_evm_addressProfile of an EVM address on Base, Ethereum, OP Mainnet or Arbitrum in one call: EOA, contract or EIP-7702 account, age, transactions sent, native and major token balances (USDC, U…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 Profile of an EVM address on Base, Ethereum, OP Mainnet or Arbitrum in one call: EOA, contract or EIP-7702 account, age, transactions sent, native and major token balances (USDC, USDT, EURC, DAI, WETH, BTC), Sourcify-verified source and name, proxy and implementation, token metadata, labels (OFAC SDN, Chainalysis oracle, known issuers) and a risk verdict with reasons. Useful to know who an address is before paying, listing or trusting it. Price: $0.01 USDC per call (x402).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
render_pageLoads a public web page in a real Chromium browser, with JavaScript run, from a residential IP in the country you choose, and returns the visible text, title, final URL and HTTP st…Reads text others writeCan 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.
- 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.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Loads a public web page in a real Chromium browser, with JavaScript run, from a residential IP in the country you choose, and returns the visible text, title, final URL and HTTP status, optionally the rendered HTML and a screenshot, plus proof of where the request came from (exit IP, country, city, timezone). Useful to see prices, content or availability as a visitor in that country sees them. Respects robots.txt; no clicks, logins or CAPTCHA solving. Price: $0.02 USDC per call (x402).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
screen_transactionPlain-language explanation of an EVM or NEAR transaction: status, method, native and token transfers, approvals (unlimited ones flagged), fee, and a risk verdict for each counterpa…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 Plain-language explanation of an EVM or NEAR transaction: status, method, native and token transfers, approvals (unlimited ones flagged), fee, and a risk verdict for each counterparty, with a one-line summary. Covers Base, Ethereum, OP Mainnet, Arbitrum, Base Sepolia and NEAR. Useful to check what a payment or approval really did. Price: $0.04 USDC per call (x402).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
verify_allowance_receiptSeller-side check that an Allowance vault receipt on NEAR paid a given account at least a given amount, bound to the seller request hash, at final finality.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 Seller-side check that an Allowance vault receipt on NEAR paid a given account at least a given amount, bound to the seller request hash, at final finality. Returns valid or the reason (not paid yet, wrong payee, amount, asset or request, unknown receipt, not a vault) and the vault code hash read at the same block. Price: $0.005 USDC per call (x402).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
Only reads 1Show 1 read-only tool
list_servicesFree.No findings
Why it is in this group
- The name "list_services" says "list": a word for reading.
Description, as the server wrote it Free. Lists the paid tools of this server with their prices, the payment network and asset, and the HTTP endpoints.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
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.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write6
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- 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 15, 2026, 13:21 UTC, unchanged since Nov 8, 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
- 6
- 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 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://x402-services.soldano.workers.dev/mcp: tools/list returned 7 tools to an anonymous client, including enrich_evm_address (write), counterparty_risk_evm (write), counterparty_risk_near (write), verify_allowance_receipt (write), screen_transaction (write) and 1 more
Posture changes
- Nov 8, 2026
- Tools that change things, listed without credentials: 5 to 6
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.
Tools1 added.+1 addedView diff
- Added:render_pageChanges things
PostureRemote posture changed. Tools that change things, listed without credentials: 5 -> 6.View diff
- Tools that change things, listed without credentials: 5 to 6
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-risk-desk https://x402-services.soldano.workers.dev/mcpclaude mcp add --transport http agent-risk-desk https://x402-services.soldano.workers.dev/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__agent-risk-desk__list_services"
],
"ask": [
"mcp__agent-risk-desk__enrich_evm_address",
"mcp__agent-risk-desk__counterparty_risk_evm",
"mcp__agent-risk-desk__counterparty_risk_near",
"mcp__agent-risk-desk__verify_allowance_receipt",
"mcp__agent-risk-desk__screen_transaction",
"mcp__agent-risk-desk__render_page"
],
"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 agent-risk-desk. Review it before you use it.
Capability tags behind 6 rules
- mcp__agent-risk-desk__enrich_evm_address untrusted-input
- mcp__agent-risk-desk__counterparty_risk_evm untrusted-input
- mcp__agent-risk-desk__counterparty_risk_near untrusted-input
- mcp__agent-risk-desk__verify_allowance_receipt untrusted-input
- mcp__agent-risk-desk__screen_transaction untrusted-input
- mcp__agent-risk-desk__render_page untrusted-input, 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/io.github.soldanoandrea/agent-risk-desk/verify?hash=e03e54aea6443906d53602576a9855206b4c34d2ac38d2f1d9898dd419261bd4" | jq -e '.changed == false'Pinned hash e03e54aea644, from Nov 13, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.soldanoandrea/agent-risk-desk/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.soldanoandrea/agent-risk-desk)Source: MCP Registry. Synced Oct 31, 2026, 23:17 UTC.
Agent Risk Desk MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Risk Desk MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 6 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 Agent Risk Desk MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Risk Desk 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 Agent Risk Desk MCP server have?
- 7 tools: 6 write, 1 read. enrich_evm_address, counterparty_risk_evm, counterparty_risk_near, verify_allowance_receipt, screen_transaction, render_page and list_services.
Does the Agent Risk Desk MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Risk Desk MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): render_page.
Has the Agent Risk Desk MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 13, 2026. Every change is on this page and in its Atom feed.