FabTally Decode MCP server
io.github.zvmzaretsky/onchain-decodezvmzaretskystreamable-httpv1.0.0Scanned
Decode EVM bytes to JSON: event-log decoder, calldata explainer, selector lookup, ABI fetch.
4 tools: 1 do something that can't be undone and 3 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- 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 FabTally Decode MCP server can do
The FabTally Decode MCP server is published by the GitHub account zvmzaretsky. It has 4 tools. It can do things that cannot be undone, such as sending, paying or publishing (decode_calldata), but cannot delete data. 3 tools only read.
1 tool can send data out of your system (decode_calldata).
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 21, 2026, version 1.0.0.
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.
4 tools
Can't be undone 1Claude Code: ask
decode_calldataPAID $0.002 (x402, USDC on Base).Can send data outNo findings
Why it is in this group
- The input addresses people (input.to): what it sends cannot be taken back.
What it can reach
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Description, as the server wrote it PAID $0.002 (x402, USDC on Base). Decode a contract function call. Give {chain, to?, data, abi?}; get the 4-byte selector resolved to a function signature (via provided ABI, the verified contract source, or 4byte.directory) plus fully decoded, typed arguments (tuples/arrays/nested included). Without payment returns the x402 challenge.
Only reads 3Show 3 read-only tools
abi_fetchPAID $0.002 (x402, USDC on Base).No findings
Why it is in this group
- The name "abi_fetch" says "fetch": a word for reading.
Description, as the server wrote it PAID $0.002 (x402, USDC on Base). Fetch the verified ABI + metadata for a contract. Give {address, chain}; get the ABI JSON, verification status/source (Sourcify or Blockscout), the callable function/event signatures, and full proxy-implementation resolution (EIP-1967/1822/OZ-legacy/beacon) — returning the implementation's ABI when it's a proxy. Without payment returns the x402 challenge; pass x_payment to settle.
decode_logPAID $0.003 (x402, USDC on Base).No findings
Why it is in this group
- The name "decode_log" says "log": a word for reading.
Description, as the server wrote it PAID $0.003 (x402, USDC on Base). FLAGSHIP: decode EVM event LOGS to human-readable JSON. Give {chain, tx_hash} to decode every log in a transaction, OR {chain, address, topics[], data} for a single log; optional {abi}. Returns each event's name, canonical signature and named/typed args — correctly handling tuple/array/nested params, anonymous events, and indexed vs non-indexed. Resolves the ABI via Sourcify/Blockscout + 4byte event signatures when none is supplied. Without payment returns the x402 challenge; pass x_payment to settle.
selector_lookupPAID $0.001 (x402, USDC on Base).No findings
Why it is in this group
- The name "selector_lookup" says "lookup": a word for reading.
Description, as the server wrote it PAID $0.001 (x402, USDC on Base). Resolve a 4-byte function selector (0x + 8 hex) OR a 32-byte event topic hash (0x + 64 hex) to its human-readable signature(s) via 4byte.directory + openchain.xyz. Returns all matches (selectors can collide) with a verified flag. Without payment returns the x402 challenge; pass x_payment to settle.
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.
- 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 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 20, 2026, 19:24 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
- 1
- 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 irreversible). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://decode.fabtally.com/mcp: tools/list returned 4 tools to an anonymous client, including decode_calldata (irreversible)
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 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http onchain-decode https://decode.fabtally.com/mcpclaude mcp add --transport http onchain-decode https://decode.fabtally.com/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-decode__decode_log",
"mcp__onchain-decode__selector_lookup",
"mcp__onchain-decode__abi_fetch"
],
"ask": [
"mcp__onchain-decode__decode_calldata"
],
"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-decode. Review it before you use it.
Capability tags behind 1 rule
- mcp__onchain-decode__decode_calldata 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.zvmzaretsky/onchain-decode/verify?hash=d5da5c93f463a04e158656e0b1d190a6d73cfa5fc4a399a30ab97dea7f7d6dc4" | jq -e '.changed == false'Pinned hash d5da5c93f463, from Nov 21, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.zvmzaretsky/onchain-decode/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.zvmzaretsky/onchain-decode)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:52 UTC.
FabTally Decode MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the FabTally Decode MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 1 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 FabTally Decode MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the FabTally Decode MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: decode_calldata.
What tools does the FabTally Decode MCP server have?
- 4 tools: 1 irreversible, 3 read. decode_calldata, decode_log, selector_lookup and abi_fetch.
Does the FabTally Decode MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the FabTally Decode 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): decode_calldata.
Has the FabTally Decode MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.