搜索「Agent Behavior」的结果

io.github.riponcm/projectmem

编码智能体记忆——一个本地 MCP 服务器服务所有项目，重复失败修复前会预警。

io.github.init-computer/init

Init is the backend engineer for your coding agent.

io.github.allooloo/rco-records

The record of what the agent relied on: a signed, chained receipt per cleared read. Verify by id.

io.github.sadri-dridi/wake-site-readiness

How an AI agent sees a public website: robots, llms.txt, sitemap, agent card, scored fixes. Host in.

com.xn--5kvtwv52d/jizhineng-mcp

Host any HTTP API as MCP tools with a tamper-evident cross-agent settlement ledger.

io.github.BarredEwe/prefire

Render SwiftUI #Preview as PNG images, so an AI agent sees the views it changes

io.github.dgesteves/onsystem

Catches palette colors, native elements and APIs your design system lacks in agent-written React.

com.fooguard/library

Search and read free, scanned AI agent skills and configs. Read-only, no account.

dev.kitrank/kitrank

Read-only catalog of 1,900+ real, sourced AI agent use cases with tools, cost and setup prompts.

is.amplify/amplify

Build, edit and preview browser games and web apps in your Amplify account from your AI agent.

io.github.itcustomsolution/approval-gate-mcp

Fail-closed human approval gates for AI agent actions. Default-deny, TTL expiry, audit log.

io.github.vuluu2k/sbuilder-mcp

Design, fill with real store data, render and publish Store Builder pages from an AI agent.

io.github.VibeTensor/attestix

AI 智能体身份、W3C 可验证凭据、欧盟 AI 法案合规，提供 47 个 MCP 工具。

io.github.soyeladice-svg/bursia-tools

Free read-only tools for agents: agent-readiness audit, TLS/DNS/header checks, MCP search, utils.

com.ngrok/mcp

Manage ngrok from your agent: endpoints, domains, and traffic policy.

io.github.CyberStrategy1/agency-check

A second look before your AI agent buys, sends, books, shares, signs up, or connects an app.

io.github.babelize/mcp

Make apps global-ready from your coding agent: analyze, translate, check and review i18n locally.

io.github.GuardBee/unbounded-consumption-auditor

Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)

io.github.GuardBee/memory-poisoning-scanner

Scans agent code for untrusted input poisoning persistent cross-session memory

com.usedamper/mcp

Feedback, roadmap, agent task execution with review, changelog, status pages and error logs.

io.github.bck-stack/sitecheck-jobs-property

112 pay-per-call agent tools: job market and real estate data tools. x402

com.botsket/search

Product search over independent US stores, with whether an AI agent can check out at each

studio.shawarma/music

Make and edit instrumental music from your agent: songs you can keep changing, MP3/WAV export

directory.arche/mcp

Hand-picked landing pages as design references for your agent: design systems, motion, sections.