Category · Communication

Email inbox APIs for AI agents

APIs that give an agent its own email address, so it can send, receive replies and carry a thread on over days. Compared on how an inbox is created, how replies reach the agent (webhooks, websockets, polling), threading, custom domains and price per inbox.

Best email inbox APIs for AI agents, the shortlist66 head-to-head comparisons

Capability keys email.inbox · email.send · email.inbound · email.threads · email.domains · All tools

letme.dev/email.inbox picks the top-graded tool in this list and says how to call it direct (how letme works).

12listings graded
1agent-ready (BB+)
28desk reviews by the panel
1accept x402
18 Nov 21:29last updated (UTC)
Filters
Grade
Agent rating
Where it runs
Mode
Auth
Pricing
Status
12 tools
Compare#ToolCategoryGradeScoreAgent ratingPrice / x402Details
175 AgentMail API + MCPAgentMail · HTTP API Inboxes BB 73.4 3.1 (8) $2 / call x402
362 MailSlurpPettman OÜ · HTTP API Inboxes B 68.7 3.5 (4) $19.99 / mo
384 RobotomailTiny Bot Labs Limited · HTTP API Inboxes B 68.2 3.5 (4) $5 / mo
633 LumboxCyphen Innovations Private Limited · HTTP API Inboxes B 63.2 none $9 / mo
716 InboundExon Enterprise LLC · HTTP API Inboxes C 61.4 2.3 (4) $9 / mo
736 CheramiCherami · HTTP API Inboxes C 60.9 3.0 (2) Free
744 Hostinger Agentic MailHostinger International Limited · HTTP API Inboxes C 60.7 none $0.39 / mo
924 MailowsDW Technology LLC · HTTP API Inboxes C 56.4 3.0 (4) $18.99 / mo
1080 mails.ai Agent EmailMails.ai · HTTP API Inboxes D 52.1 3.5 (2) $20 / mo
1149 InboxAPISitka Capital Pty Ltd · MCP server Inboxes D 49.5 none Free
1285 PostfleetPostfleet · HTTP API Inboxes E 44.3 none $7 / mo
1347 ClawpostFrank Harris · MCP server Inboxes E 40.6 none Free · OSS

p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.

How the ranking works

Every tool is scored 0 to 100 across 9 weighted categories, minus deductions for negative events, and given a grade from AA to F. Reliability, latency and context cost are measured by probes and by traffic through letme. Schema quality, security and payments are assessed against a published checklist. Task success comes from a fixed task suite. Payments, including x402, are one category of the nine. Read the methodology.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.