agiscorecard-web3-calls
Server Details
Decode supported token calls and flag recipient or amount mismatches; no wallet or safety verdict.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- f-tiger/agi-site
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
decode_token_call has a clearly distinct purpose (local decoding/comparison of token calls), while search and fetch form a conventional lookup-then-retrieve pair that is easy to tell apart since search returns IDs and fetch consumes them. Boundaries are clear, though fetch/search are generic enough that an agent could briefly hesitate about which resource domain they serve.
decode_token_call uses a descriptive snake_case verb_noun_verb pattern, but fetch and search are bare single verbs, so the set mixes two conventions. Still readable, but not a predictable pattern across all three tools.
Three tools is thin for a server whose namesake capability is Web3 call decoding plus a documentation surface. The scope is narrow and coherent, but the set is borderline under-scoped rather than well-scoped.
The search-to-fetch pair fully covers the documentation lifecycle, and decode_token_call covers the core decode/compare operation. However, there is no way to enumerate supported token-call shapes or standards, no encode/validate counterpart, and decode is limited to whatever shapes are already supported, leaving notable gaps.
Available Tools
3 toolsdecode_token_callCall LensARead-onlyIdempotentInspect
Call Lens decodes supported token-call shapes locally and compares the recipient, spender and atomic amount with your expectations. It distinguishes ERC-20 allowances from ERC-721 token IDs using the declared standard. It never connects a wallet or evaluates contract safety. No chain simulation, malicious-contract detection, token identity lookup, balance inspection or safety verdict. Retrieve calls with fetch or read its example resource to obtain exact inputs. Parameters are processed remotely without application persistence.
Inputs: to (required), data (required), network (required), tokenStandard (required), +3 more. Returns: report, toolId, version, citation, +5 more
fetchRead a Web3 method and sourcesARead-onlyIdempotentInspect
Retrieve a public tool reference by the ID returned from search. Contains methodology, limits, official source links and fictional worked examples; no user records. Cite the returned canonical URL.
Inputs: id (required). Returns: id, url, text, title, +1 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Read-only crypto safety: token honeypot checks, EIP-712 signature decode, approval scans.
Decode Base txs: plain English, strict JSON, risk flags, no LLM. 50 free/24h per IPv4 or /64, $0.02.
Read-only honeypot, holder and liquidity scam checks for tokens across 64 networks.
Token intent checks; no simulation/signing. Free trial ends 2026-09-25. No NFT required.
Related MCP Servers
- AlicenseAqualityCmaintenanceDecodes Ethereum calldata and returns a safety verdict with plain-English explanations of what the transaction does, flagging dangerous actions like unlimited approvals or gasless permits.2MIT
- AlicenseBqualityDmaintenanceProvides on-chain forensic checks for evaluating transaction risks, including token verification, rug-pull detection, and fund tracing, using public blockchain endpoints.1239 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to turn raw calldata, transaction objects, JSON-RPC requests, EIP-712 typed data and personal_sign messages into short plain-English briefings covering what a request asks for, which risky allowances or permissions need attention, and what could not be verified. Runs entirely offline with no RPC, wallet, API key or safety verdict, using three read-only tools exposed to any MCP client.MIT
- AlicenseAqualityBmaintenanceOn-chain rug-pull & honeypot risk screen for ERC-20 tokens, providing a SAFE / CAUTION / HIGH-RISK verdict based on live public RPC reads.2MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.