agentmail-to/agentmail-skills

agentmail-mcp

Configure or troubleshoot the hosted AgentMail MCP server for Codex, Claude Code, Cursor, Claude.ai, ChatGPT, or another Streamable HTTP MCP client.

Vedi sorgente
Documento Skill originale

Contenuto dal repository con titoli, esempi, codice, tabelle, link e immagini preservati.

AgentMail MCP

Prefer the hosted Streamable HTTP server:

text
https://mcp.agentmail.to/mcp

It avoids a local Node.js process and the slower release cadence of the published local MCP package.

Claude Code, Codex, and Cursor

Use OAuth. Do not put an empty API key in the configuration.

json
{
  "mcpServers": {
    "agentmail": {
      "type": "http",
      "url": "https://mcp.agentmail.to/mcp"
    }
  }
}

Claude Code can also install it directly:

bash
claude mcp add --transport http agentmail https://mcp.agentmail.to/mcp

Complete the browser sign-in on first connection. Multi-organization OAuth sessions can use the server's organization-selection tools.

Claude.ai, Claude Desktop, and ChatGPT connectors

These apps add the server as a connector and complete OAuth in the browser. No API key is needed.

  • Claude.ai and Claude Desktop: Settings → Connectors → Add custom connector. Name it AgentMail, set the URL to https://mcp.agentmail.to/mcp, then click Connect and sign in at console.agentmail.to.
  • ChatGPT: turn on Settings → Security and login → Developer mode (on a workspace plan, an admin must allow it first). Then open ChatGPT Plugins, click +, set the URL to https://mcp.agentmail.to/mcp, choose OAuth, and sign in at console.agentmail.to. In a chat, pick AgentMail from the + menu under Developer mode.

Connectors added on Claude.ai do not sync to Claude Code; add it there separately.

Per-client configuration

Add the same type: http server entry to the client's MCP config file:

  • Cursor: .cursor/mcp.json
  • VS Code: .vscode/mcp.json
  • Windsurf: its MCP config file
  • Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%/Claude/claude_desktop_config.json (Windows)

Auth options

  • OAuth — browser-based sign-in, for clients that support remote MCP OAuth. Use the bare URL with no credentials.
  • `x-api-key` header — recommended for clients without OAuth support (see below).
  • `Authorization: Bearer <am_...>` header — an alternative header form some clients require.
  • `apiKey` query param — supported but not recommended; prefer a header so the key doesn't end up in logs or history.

For a Streamable HTTP client that cannot complete OAuth, export AGENTMAIL_API_KEY and send it as a header:

json
{
  "mcpServers": {
    "agentmail": {
      "type": "http",
      "url": "https://mcp.agentmail.to/mcp",
      "headers": {
        "x-api-key": "${env:AGENTMAIL_API_KEY}"
      }
    }
  }
}

Avoid query-string credentials when header authentication is available.

Tool Discovery

MCP clients get the tool catalog and schemas live from the hosted runtime; do not rely on a copied tool count. The same generated contract is published at https://github.com/agentmail-to/agentmail-mcp/blob/main/mcp-manifest.json — treat the hosted runtime plus that manifest as the authoritative catalog. OAuth sessions can surface extra organization-selection tools beyond the base set.

The catalog covers more than mail. Point users at these groups when they ask what the connector can do:

  • Inboxes, threads, messages, drafts, attachments, and allow/block lists — the mail workflows in the sibling action skills.
  • AgentID apps and accounts — list_apps, search_apps, get_app, connect_app, and list_accounts create accounts for an agent at third-party apps (for example "create an account at Firecrawl") and show where each inbox already has one. Use the agentmail-agentid skill for that workflow.
  • Agent sign-up — agent_attach_human and agent_verify lift an unverified agent organization's limits.

Stdio Compatibility

For a stdio-only client, use the supported npm or PyPI agentmail-mcp package. Both are thin stdio bridges to the same hosted runtime: they discover tools dynamically and carry no separate AgentMail tool logic of their own.

Verify

  1. Restart the client or open a new session after installing the plugin.
  2. Inspect MCP status in the client and complete authentication.
  3. Call list_inboxes as a read-only smoke test. Call list_apps to confirm the AgentID tools are exposed.
  4. Confirm that read, write, and destructive tool annotations produce the expected approval behavior.

Troubleshoot

  • A 404 usually means the URL is missing /mcp.
  • "Invalid API key" or a 401 with API-key auth usually means the key is wrong, revoked, lacks the necessary permissions, or AGENTMAIL_API_KEY was not available to the client process.
  • "Unauthorized" or a 401 with OAuth usually means the sign-in is incomplete or the session expired — drop any apiKey query param and let the client complete the browser-based OAuth flow instead.
  • Use the full am_ key value and prefer the narrowest suitable organization, pod, or inbox scope.
  • For a stdio-only client, see Stdio Compatibility above.
dallo stesso repository

Altri Skills

Tutti gli Skills
agentmail-to
Community

agentmail

Build with the AgentMail TypeScript or Python SDK for inbox, message, thread, draft, attachment, domain, allow/block list, pod, webhook, and WebSocket workflows, including programmatic agent sign-up, domain/DNS administration, and deliverability triage (bounces, spam, blocked mail). Use when implementing or reviewing AgentMail API code; do not use for direct mailbox operations, CLI usage, MCP setup, or framework-toolkit integration.

installazioni
1
GitHub Stars
23
Aggiornato
6 ott
agentmail-to
Community

agentmail-check-email

Read, search, summarize, and triage AgentMail inboxes through the connected MCP server. Use for ANY request to look at, search, or process mail — even a simple 'search my inbox for X' or 'any new mail?'; the read workflow applies regardless of task size. Also use to summarize conversations, inspect attachments, manage read/unread labels, or find messages needing a reply; do not use for sending or drafting (agentmail-send-email), inbox administration (agentmail-manage-inboxes), or MCP connection

installazioni
1
GitHub Stars
23
Aggiornato
6 ott
agentmail-to
Community

agent-email-patterns

Architecture patterns for AI agents that communicate over email -- why agents need dedicated inboxes rather than human email accounts, infrastructure/provider tradeoffs, one-inbox-per-agent, two-way conversation loops, human-in-the-loop drafts, WebSocket vs webhook event design, multi-agent topologies, OTP flows, and the threat model (prompt injection, webhook spoofing, credential exposure, data leakage). Use when designing how agents send, receive, and manage email conversations, evaluating whe

installazioni
2
GitHub Stars
22
Aggiornato
2 ott
agentmail-to
Community

email-for-ai-agents

Deprecated alias of the agent-email-patterns skill, kept so existing installs and pinned URLs keep resolving. Prefer installing agent-email-patterns; this is an identical generated copy covering agent email architecture, security, and provider tradeoffs.

installazioni
2
GitHub Stars
22
Aggiornato
2 ott