Productivity
finemail.app
Provides AI-agent email management, allowing users to list inboxes, read, send, and manage messages.
ENDPOINT 1
https://finemail.app/api/mcp
MCP server metadata
- Name
- finemail-mcp
- Version
- 1.0.0
Known tools 38
finemail_list_inboxesList the authenticated user's AI-agent inboxes, their FineMail addresses, and mailbox counts.
Inferred read-onlyfinemail_list_messagesList owner-scoped FineMail messages, optionally filtered by agent, folder, or search text.
Inferred read-onlyfinemail_get_messageGet one full incoming or outgoing FineMail message owned by the authenticated user.
Potential side effectsfinemail_send_messageSend a rich RFC email from an owned AI agent identity and persist its delivery record.
Potential side effectsfinemail_check_address_availabilityValidate a requested @finemail.app address and check whether it is globally available.
Inferred read-onlyfinemail_get_configurationRead FineMail domain, sending, inbound-routing, and readiness configuration without exposing credentials.
Inferred read-onlyfinemail_create_inboxCreate an owned AI-agent inbox with a meaningful available address.
Potential side effectsfinemail_update_inboxUpdate an owned inbox identity, address, display name, or metadata.
Potential side effectsfinemail_delete_inboxSoft-delete an owned inbox while retaining its address and audit trail.
Potential side effectsfinemail_update_threadAdd or remove labels and update archive/read state across an owned thread.
Potential side effectsfinemail_reply_messageReply or reply-all to an owned message while preserving RFC thread headers.
Potential side effectsfinemail_forward_messageForward an owned message and optional original attachments.
Potential side effectsfinemail_update_messageUpdate labels, read, archive, or quarantine state on an owned message.
Potential side effectsfinemail_create_draftCreate a draft or schedule it with an ISO-8601 send_at value.
Potential side effectsfinemail_wait_for_emailLong-poll for a matching inbound email without frequent client polling.
Potential side effectsfinemail_get_attachmentGet safe metadata and an owner-authenticated download path for an owned attachment.
Inferred read-onlyfinemail_create_webhookCreate an HTTPS webhook and return its signing secret once.
Potential side effectsfinemail_create_domainStart custom-domain onboarding and return required DNS records.
Inferred read-onlyfinemail_verify_domainRefresh DNS and SES verification state for an owned custom domain.
Inferred read-onlyfinemail_create_security_ruleCreate an allow or block rule for an address or domain.
Potential side effectsfinemail_get_usageGet owner-scoped inbox, storage, sending, delivery, security, quota, and plan usage.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.finemail-mcp]
url = "https://finemail.app/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"finemail-mcp": {
"type": "http",
"url": "https://finemail.app/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: finemail-mcp
Remote MCP URL: https://finemail.app/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"finemail-mcp": {
"url": "https://finemail.app/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"finemail-mcp": {
"type": "http",
"url": "https://finemail.app/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "finemail-mcp",
"transport": "streamable-http",
"url": "https://finemail.app/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for finemail.app was fetched 2026-08-03T13:58:12.851Z and is being refreshed.
finemail.app is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.