搜索「Agent Behavior」的结果

io.github.runbook-ai/browser-agent

由 AI 智能体驱动的浏览器自动化 MCP 服务器。

io.github.rwaldman/agentbits

Machine-readable utilities and datasets for AI agents.

io.github.sandeep-antier/abstraxn

Abstraxn: public Web3 MCP server for read-only chain data and pay-per-call relays.

io.github.inity13/agentstack-mcp

Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.

dev.cr8/commons

面向 AI 代理的公开留言板：读取信息流、发帖与回复，无需鉴权，身份由自述。

io.github.Modellix/agent-canvas

Local MCP canvas for Modellix image generation, editing, task recovery, and visual project work.

email.fixture/email-testing

真实域名上的一次性测试邮箱：发送、接收并对真实邮件做断言。

io.github.justuncase1210-del/ai-agent-hub

Pay-per-call APIs for AI agents: queries, storage, ads. Billed in USDC via x402.

com.agentio/brand-connector

只读查询你的 Agentio 活动、创作者合作，以及在 YouTube 与 Meta 上的投放表现。

io.github.rubenmarcus/portfolio

Public portfolio MCP for resume, services, availability, project evidence, and introductions.

io.github.lennney/agent-search-mcp

Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.

com.agentbrink.www/mcp

给你的 AI 智能体一个身份：独立邮箱、webhook、仓库、密钥库、记忆与技能。

io.github.sbosscher/relay-agents

7 anonymous read-only tools. Authority-bounded autonomous onboarding guide. No financial authority.

io.github.flovoice53-tech/agent-identity-mcp

Gives an AI agent a disposable email and a real UK phone number to test signup flows.

io.github.mldlbs/mio-cua

Control this Windows desktop from any MCP client: files, windows, keyboard and mouse.

nl.svv-schatzoekers/public-selling-agent

Read-only product discovery, merchant trust, shipping and returns for SVV-Schatzoekers.

io.github.RudrenduPaul/agenticworkspace

Wraps the AgenticWorkspace CLI as a single generic MCP tool for repo workspace scans.

io.github.uantum/agents-u-cash

Non-custodial HTTP-402 crypto payments for AI agents. 77-tool MCP server.

io.github.ciinkwia/agent-tool-finder

Free search across ~35,000 agent tools (x402 bazaar + MCP registry) by plain-language need.

dev.kgninja.agent-economy/agent-verification-utility

确定性的 JSON 检查，附签名证据，执行需经 x402 付费。

io.github.mlawsonking/agent-firewall-mcp

AI 代理的输入输出安全：已知模式的提示注入与混淆扫描、URL/IP 检查与密钥识别。

io.github.mlawsonking/agent-guards

All six agent guard suites in one local MCP server, with optional cloud intelligence.

io.github.RudrenduPaul/agent-observability

AI agent observability with deterministic record/replay for debugging agent failures.

io.github.RudrenduPaul/agent-eval

Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.