Carry a conversation with outside people over days
One company's docs show a full fit.
What counts as done
A reply arriving days later is matched to the original thread, visible to every list and search call, and the agent's answer shows in the same conversation in Gmail and Outlook.
How agents ask for it: follow up with the vendor if they don't reply
, keep negotiating this by email
, reply to the client in the same thread
, pick up where the thread left off
Does the job 1
The docs show it meets the test above, and nothing we read says otherwise.
Does the job, with a limit 10
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| AgentMail API + MCP BB AgentMail, Inc. | Threads group replies and reply endpoints keep the conversation, with extracted_text removing quoted history. Open issue 38 (a16) shows replies from domains without SPF or DKIM hidden from MCP list and search until relabelled. source |
| Cherami C Abderrahmane Gourragui (sole operator, Quebec) | Conversations have list and read endpoints, sends take in_reply_to, and content.reply_text holds the new reply without quoted history. Whether mail from senders without SPF or DKIM is still listed isn't documented. source |
| Clawpost E Frank Harris | list_threads, get_thread and reply_to_message (which preserves threading) carry a conversation, and full-text search covers bodies, but get_thread returns only approved messages and no quoted-text stripping is documented. source |
| Hostinger Agentic Mail C Hostinger International Limited | Folders, IMAP-style search and a send with inReplyTo let an agent answer in-thread from a real mailbox, but there is no threads endpoint or quoted-text stripping, so matching replies is left to the agent. source |
| Inbound C EXON ENTERPRISE LLC | GET /api/e2/mail/threads/{id} returns the whole conversation and POST /emails/{id}/reply answers in it, but whether cleanedContent strips quoted history isn't stated, nor whether unauthenticated senders are listed. source |
| Lumbox B Cyphen Innovations Private Limited | Threads and replies are documented and stripped_text removes quoted replies and signatures, but whether a reply from a domain without SPF or DKIM stays listed isn't stated. source |
| mails.ai Agent Email D Mails.ai | Threads are rebuilt from In-Reply-To and References so replies land on the same thread_id, with search, folders and notes. Whether mail without SPF or DKIM stays visible to list and search wasn't found in the docs read. source |
| MailSlurp B Pettman OÜ | get_email_thread and reply_to_email keep thread context, but outside correspondents can only be reached on Pro and above, and the docs read don't say how unauthenticated senders are listed. source |
| Postfleet E Postfleet | Messages carry thread_id, listing filters by thread_id, since, until and q with a cursor, and reply_email answers in-thread, but whether unauthenticated senders are listed isn't stated, and sends have no cc or bcc. source |
| Robotomail B Tiny Bot Labs Limited | Messages carry threadId with a thread filter, and sends take inReplyTo, which must be the RFC Message-ID, not the Robotomail id. Quoted-text stripping and handling of unauthenticated senders aren't documented. source |
Doesn't do this job 1
Listings in the category that do something else, with the reason.
What stops agents finishing
- reply from a domain without SPF or DKIM hidden from list and search
- no thread or reply endpoint (Mailows)
- retention shorter than the conversation
Around it
Before: agent-inboxes.own-identity, personal-assistants.errand-outreach. After: scheduling.book-meeting, crm.log-activity.
Where this comes from
Weight 15 of 100 in Agent inbox APIs: 5 of 31 accounts: threads that were too hard to build alone (a01), client mail (a08), per-agent reply tools (a09), agents coordinating by email (a12) and a client reply hidden from the MCP (a16)
The same as data: /api/v1/use-cases/agent-inboxes.multi-day-thread.json, or the MCP tool get_use_case with id agent-inboxes.multi-day-thread. Other jobs in this category: /api/v1/niches?category=agent-inboxes.
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.