AgentShield

io.github.atmflow55Published by GitHub account atmflow55v1.2.0Updated Oct 24, 2026

Smart contract security for AI agents — verify, monitor, freeze, x402 payments

The publisher's own server: agentshield.live facts

VerifiedSTDIODesktop onlyFinanceSecurity & Monitoring

Overview

AI-generated overview

AgentShield is a local MCP server that gives AI agents smart contract security tooling: verification, monitoring, freezing and x402 payments.

What you can do
  • Verify smart contracts before an agent interacts with them.
  • Monitor contracts or activity for security-relevant changes.
  • Freeze contracts or accounts to stop activity.
  • Handle x402 payments in agent workflows.
  • No tool list is published, so the exact operations are not documented.
When to use it
Consider it when an assistant or agent needs to check, watch over, or halt smart contracts, or to work with x402 payments, and you are willing to run a local process for that.
Requirements
Runs as a local stdio process installed from the npm package agentshield-protocol, so a Node.js runtime is needed. No authentication, environment variables or headers are declared. Desktop-only; not available as a web executable.
Before you install
The description mentions freezing contracts and x402 payments, so actions may change on-chain state or move funds; confirm what each tool does before granting use. No tool list, README or instructions are published, so behavior and required credentials are unverified. No credentials are declared, but blockchain access may still need keys or RPC endpoints.

Installation

In SourceWeft

  1. Open AgentShield in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.2.0LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.

Other Agentshield integrations

agentshield.live facts

live.agentshieldOfficial publisher

A remote MCP server that lists and describes paid "fact" routes with their prices and limits, without calling or paying for them.

Streamable HTTPWeb executable
Web Search & Scraping2 toolsOct 30, 2026

Agentshield Mcp

Published by GitHub account dl-eigenart

A local MCP server that lets an assistant screen text for prompt-injection, jailbreak and social-engineering attempts via the AgentShield classification API.

STDIODesktop only
Security & MonitoringNot validated yetOct 24, 2026