Read email/chat conversations, messages, contacts and teams; draft, send and update threads. Hosted by usefulapi — connect from Claude, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"missive": {
"url": "https://missive.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"missive": {
"type": "http",
"url": "https://missive.usefulapi.io/mcp"
}
}
}Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
The login page asks for your Missive API token.
Find it in Missive → Settings → API (create a new token; requires a Productive plan). Your token is used only to call the API on your behalf and to derive a private account id; it is never shown to anyone.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Missive API token. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the Missive connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
missive_list_conversations | read | List conversations List conversations (email/chat threads). Missive requires EXACTLY ONE mailbox-type filter — one of inbox / assigned / closed / flagged / snoozed / trashed / all / shared_label / team_inbox / team_all / organization. Missive: GET /conversations. |
missive_get_conversation | read | Get conversation Get a single conversation by id. Missive: GET /conversations/{id}. |
missive_list_conversation_messages | read | List conversation messages List the messages (emails) in a conversation. Missive: GET /conversations/{id}/messages. |
missive_get_message | read | Get message Get a single message, including the full body. Missive: GET /conversations/{conversation_id}/messages/{id}. |
missive_list_conversation_comments | read | List conversation comments List internal comments (team chat) on a conversation. Missive: GET /conversations/{id}/comments. |
missive_list_conversation_drafts | read | List conversation drafts List draft messages on a conversation. Missive: GET /conversations/{id}/drafts. |
missive_list_conversation_posts | read | List conversation posts List posts (integration/app-generated items) on a conversation. Missive: GET /conversations/{id}/posts. |
missive_list_contacts | read | List contacts List contacts in a contact book. Missive: GET /contacts. |
missive_get_contact | read | Get contact Get a single contact by id. Missive: GET /contacts/{id}. |
missive_list_contact_books | read | List contact books List contact books (address books). Missive: GET /contact_books. |
missive_list_contact_groups | read | List contact groups List contact groups or organizations within a contact book. Missive: GET /contact_groups. |
missive_list_teams | read | List teams List teams in the organization(s). Missive: GET /teams. |
missive_list_users | read | List users List users (team members). Missive: GET /users. |
missive_list_shared_labels | read | List shared labels List shared labels (team-shared folders/tags). Missive: GET /shared_labels. |
missive_list_organizations | read | List organizations List organizations you belong to. Missive: GET /organizations. |
missive_list_responses | read | List responses List canned responses / templates. Missive: GET /responses. |
missive_create_draft | write | Create draft Create a draft email/message. WARNING: setting send=true SENDS a real email immediately (send_at schedules it) instead of saving a draft. Attach to an existing thread with `conversation`. Missive: POST /drafts. |
missive_update_conversation | write | Update conversation Update a conversation — assign/unassign users, add/remove shared labels, close/reopen, move to inbox, or set subject/color/team. Missive: PATCH /conversations/{id}. |
missive_create_contact | write | Create contact Create a contact in the given contact book. Missive: POST /contacts. |
missive_usage_status | Usage status (free-tier meter) Report the caller's current free-tier usage this month: calls used, monthly limit, remaining, and whether the cap is reached. Read-only; does not count against the meter. | |
missive_request_feature | Request a missing feature Tell usefulapi that the user needs something the Missive tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
missive_upgrade | Upgrade to Pro (unlimited) Subscribe to the Pro plan for UNLIMITED Missive tool calls (the free tier caps monthly usage). Choose monthly ($9/month) or yearly ($90/year — 2 months free) billing. Returns a Stripe Checkout link to open in your browser; after payment your account upgrades automatically. Does not count against the meter. | |
missive_cancel_subscription | Cancel the Pro subscription Cancel the caller's Missive Pro subscription at the end of the paid period (no refund for the current period; unlimited calls continue until then, then the free tier applies). Requires confirm: true. Run missive_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 100 tool calls / month |
| Proper user | $9/mo · $90/yr | Unlimited |
Pro covers this Missive server only. Subscribe with missive_upgrade (it returns a Stripe Checkout link). Cancel any time with missive_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running missive_upgrade before then undoes the cancel. Or write to [email protected].
No. usefulapi is an independent service. It is not affiliated with or endorsed by Missive. The server calls the Missive API with your own Missive access, so it sees only the data that your account can see.
The login page asks for your Missive API token. See Before you connect for where to find it.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Missive API token. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Missive API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Missive.
Yes, if you approve it. 3 of the 19 Missive tools can create or change data. The other 16 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 100 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls, for this Missive server only. Run missive_usage_status to see how many calls you used.
Ask the AI to run missive_upgrade: it returns a Stripe Checkout link. To cancel, run missive_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with missive_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.