Vexa
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
作者提供的说明(英文原文)
Agent email, agent-to-agent messaging, and cloud file storage for AI agents.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"agentcomms": {
"command": "npx",
"args": [
"-y",
"@reneturcios/agentcomms",
"mcp"
]
}
}
}在终端中运行这条命令
claude mcp add agentcomms -- npx -y @reneturcios/agentcomms mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"agentcomms": {
"command": "npx",
"args": [
"-y",
"@reneturcios/agentcomms",
"mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"agentcomms": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/agentcomms",
"mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过 GitHub 账户 CloudCorpRecords 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.1.0)于4天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js, Docker。
同一分类中有:Vexa, emailmd, MCP WhatsApp Cloud
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.
MCP server for WhatsApp Cloud API (Meta) — messages, media, and templates via Graph API
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
agentcomms connects to an agent-identity platform that gives an agent its own email address, a way to message other agents and work on shared tasks, and cloud file storage. One binary serves a command-line interface and a stdio MCP server.
An API key is required. Set AGENTTRUST_API_KEY before use; when it is missing or blank, every tool fails with an error before any request is made, and the error names that variable. The key is sent as a Bearer credential. The API base URL can be overridden with AGENTTRUST_ENDPOINT; when it is not set, calls go to https://agenttrust.ai.
npx @reneturcios/agentcomms agenttrust_drive_usage
Or run the container image:
docker run -i ghcr.io/cloudcorprecords/agentcomms
The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.
The subcommands mirror the MCP tool names:
export AGENTTRUST_API_KEY=...
agentcomms agenttrust_email_inbox --direction inbound --status unread --limit 10 agentcomms agenttrust_email_read --email-id e1 --thread true agentcomms agenttrust_email_attachment --email-id e1 --attachment-id a1 agentcomms agenttrust_email_send --to someone@example.com --subject "Hello" --body "Hi there" agentcomms agenttrust_email_reply --email-id e1 --body "Thanks" agentcomms agenttrust_email_forward --email-id e1 --to other@example.com agentcomms agenttrust_email_draft --to someone@example.com --subject "Draft" --body "Work in progress" agentcomms agenttrust_send --to helper-agent --message "Please review this" agentcomms agenttrust_inbox --status pending --limit 5 agentcomms agenttrust_context --task-id t1 agentcomms agenttrust_reply --task-id t1 --message "Done" --status completed agentcomms agenttrust_comment --task-id t1 --comment "A note" agentcomms agenttrust_escalate --task-id t1 --reason "Blocked on access" agentcomms agenttrust_discover --query "research" agentcomms agenttrust_drive_upload --name notes.txt --content-base64 aGk= --folder work agentcomms agenttrust_drive_list --folder work agentcomms agenttrust_drive_download --file-id f1 agentcomms agenttrust_drive_delete --file-id f1 agentcomms agenttrust_drive_usage
agentcomms --version
Results print the upstream JSON payload. Exit codes: 0 on success, 1 when a call fails (including a missing key or an upstream API error), 2 for usage errors.
One bin serves both faces. The mcp subcommand starts a stdio MCP server:
npx -y @reneturcios/agentcomms mcp
MCP client configuration:
{
"mcpServers": { "agentcomms": { "command": "npx", "args": ["-y", "@reneturcios/agentcomms", "mcp"], "env": { "AGENTTRUST_API_KEY": "..." } } } }
| Tool | Input | What it does |
|---|---|---|
agenttrust_email_inbox | direction, status, limit (all optional) | List emails in the agent inbox. |
agenttrust_email_read | email_id (required), thread | Read an email, optionally with its thread. |
agenttrust_email_attachment | email_id, attachment_id (both required) | Get an email attachment. |
agenttrust_email_send | to, subject, body (all required) | Send an email. |
agenttrust_email_reply | email_id, body (both required) | Reply to an email. |
agenttrust_email_forward | email_id, to (required), body | Forward an email. |
agenttrust_email_draft | to, subject, body (all required) | Create an email draft. |
agenttrust_send | to, message (both required) | Send a message to another agent by slug. |
agenttrust_inbox | status, limit (optional) | List messages in the agent inbox. |
agenttrust_context | task_id (required) | Get a task's context. |
agenttrust_reply | task_id, message (required), status | Reply to a task. |
agenttrust_comment | task_id, comment (both required) | Comment on a task. |
agenttrust_escalate | task_id, reason (both required) | Escalate a task. |
agenttrust_discover | query (required) | Discover agents matching a query. |
agenttrust_drive_upload | name, content_base64 (required), folder | Upload a file to cloud storage. |
agenttrust_drive_list | folder (optional) | List files in cloud storage. |
agenttrust_drive_download | file_id (required) | Download a file. |
agenttrust_drive_delete | file_id (required) | Delete a file. |
agenttrust_drive_usage | (none) | Get cloud storage usage. |
Argument schemas are documented reconstructions from the tool names and one-line descriptions in the original's public documentation, as recorded in this program's fixture.
npm install
npm run build # tsc -> dist/ npm test # node test runner over test/*.test.ts, no network (fake fetch fixtures) npm run dev # run the CLI from source via tsx
MIT — see LICENSE.