搜索「Agent Behavior」的结果

io.github.CSOAI-ORG/eudi-wallet-mcp

EUDI 钱包 MCP——eIDAS 2.0 下的欧盟数字身份钱包，用于 AI 智能体认证。

io.github.Hugelidus/pointcast

Talk and Alt+click on your web app: your agent gets the exact elements and the code behind them.

io.github.Continuum-AI-Corp/orcareplay

Read, replay and fork recorded coding-agent runs.

io.github.pedroknigge/arkgate

When the agent writes a bad import, the write doesn’t land. The same check fails the pull request.

com.decaframe/decaframe

Presentations, slides, reports and one-pagers your agent designs and you edit. Exports to one file.

io.github.ApparelHub-AI/apparelhub-mcp

Run a custom-merch store from an agent: design, build products, list on every channel, fulfill.

io.github.4hmetuyar/memory-poisoning-scanner

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

io.github.4hmetuyar/unbounded-consumption-auditor

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

io.github.Servosity/datagate-mcp

DataGate telecom billing lookups - customers, agreements, invoices, and more - for any MCP agent.

io.github.loopg/pramana-mcp

Read your recorded AI agent runs, and what changed when you swapped a model or prompt.

io.github.Servosity/acronis-mcp

首个真正面向 Acronis Cyber Protect Cloud 平台的 CLI——覆盖每个租户。

io.github.cherninlab/ennodia

Connects the AI agents you use: your agent hands a task to another and gets the answer back

com.skeletiq/mcp

把已定版的 SkeletIQ 架构交给编码智能体：任务简报、构建顺序与偏移检查。

io.github.MerzoukeMansouri/mozaic

Mozaic Design System (ADEO): tokens, components, icons, docs and style guides for any agent.

io.github.cqnce-app/cqnce-mcp

Add human approval to AI agent workflows through cQnce authorization tools.

io.github.ashlrai/lexicon

Fixes the names and jargon speech-to-text gets wrong before your agent acts on a dictated prompt.

com.random-profiles/mcp

生成虚假用户档案与公司数据，用于测试、种子数据与 AI 智能体演示。

io.github.pawvej/vidgrid

给 AI 代理一双看视频的眼睛：把视频片段转成编号帧网格 + 文字稿。

io.github.delentia-labs/delentia-mcp

Stop rogue AI-agent tool calls before they run: deterministic policy gate + audit digest.

io.github.forevercrab321-svg/leevar

Grade an AI agent's transcripts on 18 reliability tests. Thin evidence is NOT TESTED, not guessed.

dev.citadeldb/mcp

以加密为先的嵌入式数据库，支持向量检索与代理记忆，以 MCP 工具形式对外提供。

io.github.devmster/x402-trinity

Give an agent a wallet. Pays for x402 resources within hard limits. Base + USDC, gasless.

ai.hiddencontent/mcp

在智能体读取文档前检查其中的隐藏文本，支持 PDF、Office、RTF、HTML。

io.github.raimondasl/isitdone

Make a coding agent prove it: run the repo's real tests, typecheck and lint before it says done.