AI and MCP

translate and compose each spend one AI action from the workspace allowance for the day, and a spent allowance stops with exit code 8. compose and summarize run through the MCP tools composeEmail and getThreadSummary, which is why they need a browser sign-in: an API key cannot reach the MCP server.

openemail ai translate --to de --subject "Your invoice" --text "The invoice is attached."openemail ai translate --to Japanese --body-file reply.html --no-originalcat notes.txt | openemail ai translate --to fropenemail ai languages --search port

It runs the translation a translated send would run and prints the result, so you can read it before anything leaves. Nothing is stored or sent. --to takes a code, an English name or the language’s own name. The body comes from --text, --html, --body-file or stdin, and --text and --html also read a file with @path.

• —Your original text is kept below the translation, unless you pass --no-original.
• —The detected source language is printed on stderr, and --json prints the whole translation.
• —To translate as you send, use openemail send --translate de.

openemail ai compose "thank Ada for the invoice and ask for a PDF copy" --to [email protected]openemail ai compose "say yes to Tuesday at 3pm" --thread CAHk7pQ2x9LmZ4 --tone friendlyopenemail ai compose "decline politely" --thread CAHk7pQ2x9LmZ4 | openemail send --to [email protected] --subject "Re: Proposal"openemail ai summarize CAHk7pQ2x9LmZ4

• —compose prints a body written in your style and sends nothing, so pipe it into openemail send when you are happy with it. With --thread it reads the latest messages of the thread first and writes a reply. --tone is one of formal, friendly, casual, concise, direct or warm.
• —summarize prints the summary with the subject, sender and date. Summaries are written when mail arrives, and a thread that holds an encrypted message has none, which exits with code 5.

The OpenEmail MCP server gives an AI client the tools the assistant in the app uses: it can read and send mail and manage contacts, templates, domains and more, limited to what you approve. A client connects in one of two ways, and openemail mcp config prints both for the client you use:

• —The remote server. The client runs its own browser sign-in, you approve it on the OpenEmail consent page, and it appears in Account → Connected apps. This is the simpler choice when the client supports it.
• —The local bridge, openemail mcp serve, which the client starts through npx. It uses the sign-in of this CLI, so run openemail login first. It suits clients that only start local servers.

openemail mcp configopenemail mcp config --client claude-codeopenemail mcp config --client cursor --profile workopenemail mcp config --client vscode --json

claude mcp add --transport http openemail https://api.openemail.uk/mcp

claude mcp add openemail -- npx -y @openemail/cli mcp serve

After adding the remote server, Claude Code signs in from /mcp and Codex with codex mcp login openemail. Claude Desktop adds it under Settings → Connectors → Add custom connector. openemail mcp config --client <name> also says which file each client reads.

openemail mcp serve reads newline-delimited JSON-RPC on stdin, forwards each message to the MCP server with your saved browser sign-in, and writes each answer to stdout as one line. It refreshes an expired access token without the client noticing, answers a batch as one array, and stops when stdin closes. Only protocol reaches stdout, and stderr stays quiet unless you pass --debug.

echo '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | openemail mcp serveopenemail mcp serve --profile workopenemail mcp serve --debug 2> mcp.log

openemail mcp toolsopenemail mcp tools composeEmailopenemail mcp call whoAmIopenemail mcp call listThreads --arg folder=inbox --arg maxResults=5openemail mcp call getThread --args '{"threadId":"CAHk7pQ2x9LmZ4"}'

• —mcp tools lists the tools this sign-in may use, which already leaves out any your role or the approval does not allow. Name a tool to see its description and arguments.
• —mcp call takes the arguments as one JSON object in --args (inline, @file or -), and --arg key=value sets one at a time. A value is read as JSON when it parses, so quote a number you mean as text.
• —The MCP server never asks for confirmation, so a tool that sends or deletes acts at once.
• —A result that starts with Refused ( exits with code 4. An unknown tool exits with 5, invalid arguments with 7, and a spent AI allowance with 8.

Six tools make a change the REST API guards with a verification code, and they ask for the same code: createRule, setRuleEnabled, removeDomain, removeDomainAddress, deleteAudience for an audience you created, and emptyAudience for an audience you created that still has contacts. In a terminal, mcp call asks for the code and calls the tool again. Unattended it exits with code 4, so run openemail verify first.

openemail docs ask "how do I verify a domain?"openemail docs open cli/authenticationopenemail docs read cli/commandsopenemail docs read

• —docs ask puts a question to the docs assistant and prints the answer as it is written, then the pages it came from. It answers only from this documentation, needs no sign-in and never sends your credentials. A question can be up to 600 characters, and each network can ask a limited number a day.
• —docs open opens a page in your browser, and --print prints its link instead.
• —docs read prints a page as Markdown. With no page it prints the index of every page.