Skip to main content
Glama

Server Details

Before sending crypto, check the recipient for address poisoning: lookalikes and bad checksums

The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Uptime
0.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
devx-agent/address-poisoning-check
GitHub Stars
0
Server Listing
devx-address-poisoning-check
ChatGPT
–
Claude
–

TDQS

A3.5/5.0

Scored across 2 tools

Disambiguation4/5

The two tools have mostly distinct roles: check_recipient_lookalike performs a free offline check, while onchain_check_info explains how to purchase a paid on-chain check. The 'info' suffix helps, though an agent could initially mistake the latter for a tool that actually performs an on-chain check.

Naming Consistency3/5

Both names use snake_case, but they follow different conventions: one is verb_noun (check_recipient_lookalike) and the other is noun/info-oriented (onchain_check_info). The set is small and readable, but not a single predictable pattern.

Tool Count3/5

Two tools is borderline thin for an address-poisoning checking server. Only one tool actually performs a check, while the other is informational, so the surface feels underpowered for its apparent purpose.

Completeness2/5

The free lookalike and checksum check is useful, but the advertised on-chain history scan is not exposed as an invocable tool; onchain_check_info only describes how to buy it and explicitly does not pay. This leaves a significant gap for an agent trying to perform the full poisoning check workflow.

Available Tools

2 tools
check_recipient_lookalikeA
Read-only
Inspect

Free, offline, read-only: before sending crypto, check whether the recipient address is a lookalike (same first/last hex characters, different middle) of any address you trust, and whether its EIP-55 checksum is valid. Address poisoning stole $76M+ in 12 months by planting such lookalikes in wallet histories.

Inputs: to (required), known.

onchain_check_infoA
Read-only
Inspect

How to buy the on-chain check (scans the sender's real transfer history on Ethereum/Base/Avalanche for poisoning transfers and lookalikes) via x402 for 0.005 USDC. Does not pay.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to check a payment recipient against the sender's own on-chain history before funds move, flagging address-poisoning look-alikes, spoofed 'from you' transfers, and fake tokens via the Blockscout PRO API. It also scans a wallet for poisoning attempts aimed at it, returning a verdict of OK, CAUTION, or STOP.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables checking whether a crypto link is a phishing lookalike of a wallet, exchange or dapp by comparing it against official domains and flagging lookalike characters, typosquats, punycode and bait words, fully offline. An optional paid full check adds domain registration age, DNS, redirect tracing and a page scan for seed-phrase prompts and drainer code.
      2
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables MCP-compatible AI agents to scan crypto transactions for scam addresses, clipboard-hijack patterns, and typos, as well as report scam addresses and check usage, directly in conversation.
      -
    • A
      license
      A
      quality
      A
      maintenance
      Read-only safety checks before an agent acts: scan untrusted text for prompt injection and phishing (locally), check npm packages for malware, hijacked releases and typosquats, scan crypto addresses and tokens, and compare two addresses to catch address poisoning. Zero dependencies.
      4
      AGPL 3.0
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.