FabTally Safe

by zvmzaretsky · remote · no sign-in to list tools · v1.0.0 · published by GitHub user zvmzaretsky

Read-only crypto safety: token honeypot checks, EIP-712 signature decode, approval scans.

Final · 2Changes · 6

Compare Registry entry

8 tools: 2 do something that can't be undone and 6 change things.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone2Claude Code: ask: see these tools
Changes things6Claude Code: ask: see these tools
Only reads0Claude Code: allow

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http crypto-safety https://safe.fabtally.com/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

8 tools

Can't be undone 2Sends, pays, publishes or merges: once done, it cannot be taken back.Claude Code: ask

simulatePAID $0.02 (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 $0.02 (x402, USDC on Base). Keyless pre-sign analysis of {chain, from?, to, data, value?}: public-RPC eth_call revert check + static calldata decode predicting approval/transfer deltas + risk flags (unlimited approval, approval-for-all, reverts). Honest keyless limitation stated in the response (no full fork trace). Without payment returns the x402 challenge; pass x_payment. Free teaser: simulate_free.
simulate_freeFREE.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
FREE. Method + revert flag + risk level + predicted effect types for a transaction. Real result, no wallet. Upgrade to simulate for the full predicted deltas + all risk flags.

Changes things 6Creates or changes something that can be changed back.Claude Code: ask

approvalsPAID $0.01 (x402, USDC on Base).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
PAID $0.01 (x402, USDC on Base). Scan a wallet's ERC-20/721 approvals ranked by exposure; flags unlimited amounts, unverified/known-malicious spenders, and address-poisoning 'fake-approval revoke bait'; returns the exact revoke calldata you execute YOURSELF (never executed/broadcast by us). Without payment returns the x402 challenge; pass x_payment. Free teaser: approvals_free.
approvals_freeFREE.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. Approval counts + top-3 riskiest spenders for {address, chain}. Real result, no wallet. Upgrade to approvals for EVERY approval ranked + revoke calldata.
decode_signaturePAID $0.01 (x402, USDC on Base).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
PAID $0.01 (x402, USDC on Base). Decode an off-chain EIP-712 typed-data signature (Permit / Permit2 / Seaport / generic) into plain English with risk flags: unlimited approval, unknown/known-malicious spender, never-expiring or already-expired deadlines, zero-consideration NFT-drain orders. Off-chain signatures are the top wallet-drainer vector. Pure offline decode — never signs/broadcasts. Without payment returns the x402 challenge; pass x_payment. Free teaser: decode_signature_free.
decode_signature_freeFREE.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. Type + plain-English summary + risk level for an EIP-712 `typed_data`. Real result, no wallet. Upgrade to decode_signature for the full field-by-field decode + all risk flags + malicious-spender screening.
token_safetyPAID $0.02 (x402, USDC on Base).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
PAID $0.02 (x402, USDC on Base). Multi-chain token honeypot/rug check aggregating GoPlus token-security + honeypot.is buy/sell-tax simulation into a normalized 0-100 risk score with explainable reasons: honeypot/can't-sell, buy/sell tax, mint/blacklist/pausable/ownership privileges, top-holder concentration, LP-lock, contract verified/bytecode. Descriptive facts only — NOT a buy/sell signal. Without payment returns the x402 challenge; pass x_payment to settle. Free teaser: token_safety_free.
token_safety_freeFREE.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. Score band + top-line honeypot/tax/privilege flags for a token {address, chain}. Real result, no wallet. Upgrade to token_safety for the full numeric breakdown.

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 out2: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.; simulate
simulate_free

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 Oct 22, 2026, 15:08 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: 8
Protocol version: 2025-06-18
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: none
RFC 9728 protected resource metadata: none
Authorization servers: none
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 8 tools that change things (2 irreversible, 6 write). Whether a call also works without credentials was not tested: tools are never called.
Matched text
https://safe.fabtally.com/mcp: tools/list returned 8 tools to an anonymous client, including simulate (irreversible), simulate_free (irreversible), token_safety (write), token_safety_free (write), decode_signature (write) and 3 more
What this check looks for

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http crypto-safety https://safe.fabtally.com/mcp

Run 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.

.claude/settings.json

{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__crypto-safety__token_safety",
      "mcp__crypto-safety__token_safety_free",
      "mcp__crypto-safety__decode_signature",
      "mcp__crypto-safety__decode_signature_free",
      "mcp__crypto-safety__approvals",
      "mcp__crypto-safety__approvals_free",
      "mcp__crypto-safety__simulate",
      "mcp__crypto-safety__simulate_free"
    ],
    "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 crypto-safety. Review it before you use it.

Capability tags behind 2 rules

mcp__crypto-safety__simulate outbound
mcp__crypto-safety__simulate_free outbound

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.zvmzaretsky/crypto-safety/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

8 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:52 UTC.

For agents: Markdown · JSON · report this listing