io.github.acarchidi/agentforge

MCPcommunitylive
v1.5.0io.github.acarchidiUnknownUpdated 2mo agoGitHub

DeFi safety layer for AI agents: wallet safety, token risk, tx decode/simulate. 20 tools.

Endpoint healthlive
checked 6 days ago · 210ms
40% of the last 5 checks reached this endpoint
Works in
ClaudeCursorCopilotChatGPTGemini

Inferred from the transports this listing declares (streamable-http). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
2mo agoLast update
Package
Authorio.github.acarchidi
LicenseUnknown
Version1.5.0
Sourcemcp-registry
GitHubacarchidi/agentforge
SBOMCycloneDX 1.6 ↓
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/30
→ Publisher: run `forge publish` from the repo to claim ownership
—Domain verification+0/10
→ Not currently available for this listing type — the domain-verification check only runs for npm-backed packages today, so this row cannot be earned here yet regardless of what's hosted at the domain.
✓Prompt-injection scan · clean+30/30
✓Obfuscation / exfil scan · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
DependenciesNot audited
Tool surface16 tools · none privileged
Security scan✓ CleanvHEAD · 3mo agoHow well does this scan work?
CODE…ipts/buyerAgentFull.tsDynamic require of a computed module name
CODE…ripts/verifyPrompts.tsDynamic require of a computed module name
EvalsNone
IndexedJul 9, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

16 tools · none privileged
Statically extracted from the published packagevHEAD · 3mo ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

token_intelNo description published

This tool published no description. Forge does not invent one.

token_researchNo description published

This tool published no description. Forge does not invent one.

code_reviewNo description published

This tool published no description. Forge does not invent one.

contract_docsNo description published

This tool published no description. Forge does not invent one.

contract_monitorNo description published

This tool published no description. Forge does not invent one.

token_compareNo description published

This tool published no description. Forge does not invent one.

tx_decodeNo description published

This tool published no description. Forge does not invent one.

approval_scanNo description published

This tool published no description. Forge does not invent one.

gas_oracleNo description published

This tool published no description. Forge does not invent one.

sentimentNo description published

This tool published no description. Forge does not invent one.

summarizeNo description published

This tool published no description. Forge does not invent one.

translateNo description published

This tool published no description. Forge does not invent one.

wallet_safetyNo description published

This tool published no description. Forge does not invent one.

pool_snapshotNo description published

This tool published no description. Forge does not invent one.

token_risk_metricsNo description published

This tool published no description. Forge does not invent one.

registry_lookupNo description published

This tool published no description. Forge does not invent one.

0 of 16 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

DeFi safety layer for AI agents: wallet safety, token risk, tx decode/simulate. 20 tools.

Keywords
mcp
Alternatives
Comparing tool surfaces…

Tools exposed

16 tools · none privileged · observed by static extraction. A tool surface is what one scan read on one day, not a live capability list.

Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.