MCPFax On-Chain Toolkit MCP server
com.mcpscores/onchain-toolkitmcpscores.comstreamable-httpv1.0.2Scanned
The on-chain facts you need in the seconds before you transact.
6 tools: 4 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
4 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 MCPFax On-Chain Toolkit MCP server can do
The MCPFax On-Chain Toolkit MCP server is published by mcpscores.com, a domain the MCP Registry verified. It has 6 tools. It can create or change data (4 tools: request_data, demand_report, gas_now and address_info), but cannot delete data. 2 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 3 findings (base64-blob). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 17, 2026, version 1.0.2.
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.
6 tools
Changes things 4Claude Code: ask
address_infoNative balance, the next nonce to use, and whether the address holds contract code — the three things needed before sending from or to an address.2 findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- Warn
The input schema at properties.address.examples[0] contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.address.examples[0]: "0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045"
- Warn
The input schema at properties.token.examples[0] contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.token.examples[0]: "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913"
Description, as the server wrote it Native balance, the next nonce to use, and whether the address holds contract code — the three things needed before sending from or to an address. Pass 'token' as well to read an ERC-20 balance for the same address in the same call. Values are read at the latest block, so a reorg can change them. Costs $0.008 USDC per call via x402 on Base.
demand_reportFREE, no payment.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it FREE, no payment. The aggregate of what agents have told us they are looking for, most-requested first, with the categories nothing available yet serves.
gas_nowLive gas price on Ethereum, Base, Arbitrum, Optimism or Polygon — in wei and gwei, plus what a plain 21,000-gas transfer would cost in the native token, which is the number you act…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Live gas price on Ethereum, Base, Arbitrum, Optimism or Polygon — in wei and gwei, plus what a plain 21,000-gas transfer would cost in the native token, which is the number you actually budget with. Pass several chains comma-separated to compare where to execute. Call this immediately before sending a transaction: gas moves every block, so the answer is good for seconds, not minutes. Costs $0.005 USDC per call via x402 on Base.
request_dataFREE, no payment.No findings
Why it is in this group
- The name "request_data" says "request": a word for a change.
Description, as the server wrote it FREE, no payment. Describe in your own words the data you are trying to buy — anything, not just on-chain data — and get back whether we operate a service that supplies it, with the MCP endpoint if so. Every request is catalogued so repeatedly-requested data gets built. Nothing identifying is stored, only the words of the request.
Only reads 2Show 2 read-only tools
token_infoRead an ERC-20's name, symbol, decimals and total supply straight from the contract on the chain you name, and confirm the address actually has code there.1 finding
Why it is in this group
- The description's first verb is "read": a word for reading.
Findings
- Warn
The input schema at properties.address.examples[0] contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.address.examples[0]: "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913"
Description, as the server wrote it Read an ERC-20's name, symbol, decimals and total supply straight from the contract on the chain you name, and confirm the address actually has code there. Use before quoting an amount or building a transfer: getting decimals wrong is the classic way to send 1,000,000x the intended value. An address with no code, or a contract that is not an ERC-20, is reported as such and is NOT charged. Costs $0.005 USDC per call via x402 on Base.
tx_statusStatus of a transaction by hash: success, failed or still pending, with the block it landed in, sender and recipient, value moved, gas used, the fee actually paid, and how many log…No findings
Why it is in this group
- The name "tx_status" says "status": a word for reading.
Description, as the server wrote it Status of a transaction by hash: success, failed or still pending, with the block it landed in, sender and recipient, value moved, gas used, the fee actually paid, and how many logs it emitted. Use to confirm an action you took really settled rather than assuming it did. An unknown hash is reported as not_found and is NOT charged. Costs $0.005 USDC per call via x402 on Base.
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 untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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, 19:27 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
- 4
- 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 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://onchain-toolkit.bowling-anthony.workers.dev/mcp: tools/list returned 6 tools to an anonymous client, including request_data (write), demand_report (write), gas_now (write), address_info (write)
Findings
Matches of fixed checks, with the text they matched.
- Warntoken_info
The input schema at properties.address.examples[0] contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.address.examples[0]: "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913"
- Warnaddress_info
The input schema at properties.address.examples[0] contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.address.examples[0]: "0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045"
- Warnaddress_info
The input schema at properties.token.examples[0] contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.token.examples[0]: "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913"
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 1.0.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http onchain-toolkit https://onchain-toolkit.bowling-anthony.workers.dev/mcpclaude mcp add --transport http onchain-toolkit https://onchain-toolkit.bowling-anthony.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__onchain-toolkit__token_info",
"mcp__onchain-toolkit__tx_status"
],
"ask": [
"mcp__onchain-toolkit__request_data",
"mcp__onchain-toolkit__demand_report",
"mcp__onchain-toolkit__gas_now",
"mcp__onchain-toolkit__address_info"
],
"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 onchain-toolkit. Review it before you use it.
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/com.mcpscores/onchain-toolkit/verify?hash=b382d3081de47830b223f5c1e4e33505aec763db6abac0f69ba6f6b21591b9a8" | jq -e '.changed == false'Pinned hash b382d3081de4, from Nov 17, 2026, 18:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.mcpscores/onchain-toolkit/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.mcpscores/onchain-toolkit)Source: MCP Registry. Synced Oct 21, 2026, 17:59 UTC.
MCPFax On-Chain Toolkit MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the MCPFax On-Chain Toolkit MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 4 of which can change, send or delete something, and 3 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 MCPFax On-Chain Toolkit MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the MCPFax On-Chain Toolkit 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 MCPFax On-Chain Toolkit MCP server have?
- 6 tools: 4 write, 2 read. request_data, demand_report, gas_now, address_info, token_info and tx_status.
Does the MCPFax On-Chain Toolkit MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the MCPFax On-Chain Toolkit MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the MCPFax On-Chain Toolkit MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.