Head to head · Agent inboxes · October 2026 research run

Cherami vs mails.ai Agent Email

Cherami scores 60.9 (C) on agent readiness against mails.ai Agent Email's 52.1 (D), and leads in 2 of 7 scored categories. mails.ai Agent Email leads on reliability, security & auth, maintenance & community and transparency & trust. Both do agent inboxes.

Best email inbox APIs for AI agents · All 77 inboxes comparisons

Which one, for what

Cherami C

Best for A single developer or small team giving an agent a free, separate address for low-volume recurring correspondence such as supplier replies, project updates and agent-to-agent handoffs.

Ahead on

  • Payments & pricing, 53 against 45

Also in its favour

  • No incidents deducted, where mails.ai Agent Email loses 23 points for them

Watch for

No status page, SLA or public changelog, so the webhooks API carries no release date

mails.ai Agent Email D

Best for Agents that send transactional mail and read replies, such as support, notification and verification agents, where an injection score on inbound mail is wanted out of the box.

Ahead on

  • Reliability, 80 against 40
  • Security & auth, 78 against 46
  • Maintenance & community, 80 against 74
  • Transparency & trust, 65 against 56

Also in its favour

  • Runs on your own machine
  • Rated higher by the reviewer agents, 3.5 against 3.0 out of 5

Watch for

No company or person named; legal entity details only on request

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Reliability mails.ai Agent Email +40

Cherami 40

Hosted lines. No status page. status.cherami.to doesn't resolve and cherami.to/status returns 404 on 4 November (0). With no history to read, the incident record gets 5. Signup discovery (10 per IP an hour), phrase redemption and browser approvals (10 per IP per 15 minutes) and the sending allowance (25 recipients per rolling 24 hours) are published with numbers, but no general request limit for reading or listing mail is stated (10 of 15). 429s carry Retry-After, the allowance error returns sufficient_capacity_at, and a retry table per operation sits beside idempotency keys on every write that sends or creates (15). The deployment guide says service commitments are by request and none is published (0). The API is /v1 with contract version 1.0.0 and no beta label on the HTTP or MCP surface (10).

mails.ai Agent Email 80

Graded as a hosted service. Better Stack status page at status.mails.ai with API, dashboard and website components and 90-day bars (20). On 1 November the bars from 3 August show the API down for 2 minutes on 5 August and 2 minutes on 10 August (99.995 per cent over 90 days), the website down on 25 August, 6 September and 25 September, and the dashboard at 100 per cent. The July downtime read on 5 October has left the window. The incident history reports no incidents for any month from June to November 2026, so the page has never posted one, which this run reads as 20 rather than a clean record (20). Send caps published per plan by hour, day and month (15). 429s carry resets_at and retry_after_seconds in the body and Retry-After when the wait is 60 seconds or less (changelog, 10 October), and the docs ask for an Idempotency-Key on retried sends (15). A 99.9 per cent uptime target with pro-rated credit is on mails.ai/status and the terms refer to it, but it's labelled a Phase 1 launch target and incident response is best-effort today (5 of 10). No beta label on the API, but the vendor still calls itself pre-launch (5 of 10). 20 + 20 + 15 + 15 + 5 + 5 = 80.

Security & auth mails.ai Agent Email +32

Cherami 46

OAuth through Clerk with protected-resource metadata, but one scope, cherami_mail:full. API keys are revocable in Account, API keys, never expire, travel only in the Authorization header, and every key and grant reaches every inbox on the account. We read this as plain revocable keys (20 of 30). No read-only mode or inbox-limited credential. Per-inbox recipient allowlists and sender blocklists can be changed only by the account's human, drafts allow review before sending, and the delete tools' descriptions tell the agent to confirm with the human, with no server-side confirmation (10 of 20). Every tool that returns mail says to treat it as untrusted data, and a safety guide covers handling, but the docs state Cherami doesn't screen content for manipulation, spam or phishing (10 of 15). Sent messages keep their submission outcomes and responses carry X-Request-ID, but we found no audit log of API or MCP calls (4 of 15). No security.txt, disclosure policy, bug bounty or certification found. The privacy policy says credentials are stored as hashes and incidents are notified as the law requires (2 of 20).

mails.ai Agent Email 78

Bearer keys, scoped to send, read, manage or (since 10 October) draft, bindable to one agent, with optional expiry, stored hashed and revocable at once by API; AI clients connecting to the hosted MCP endpoint sign in by OAuth, and connected apps can be listed and revoked (30). A read-scoped key gives a read-only mode, a draft-scoped key writes drafts and never sends, for mail a person approves first, and agent-bound keys now stay inside their agent (404 for another agent's mail). Per-agent hourly and daily send limits narrow the blast radius and cold outreach is refused at the API, but MCP sends and forwards on a send-scoped key run without confirmation (16 of 20). Every inbound message is scored by an injection scanner and flagged quarantined above 0.95, which the docs tell the agent to branch on. The scanner's accuracy is a vendor claim we didn't test (13 of 15). Every API call writes an audit row readable at GET /v1/logs per the spec, refused requests included since October, with 90 days' retention on Free and Pro. We didn't call it (12 of 15). security.txt valid to 1 July 2027 and a disclosure policy with safe harbour, but no bug bounty ("No bounty program"), no SOC 2, a PGP key promised for the Phase 1 launch, reports to the general support address and "we do not commit to a reply" (7 of 20). 30 + 16 + 13 + 12 + 7 = 78.

Transparency & trust mails.ai Agent Email +9

Cherami 56

The service is closed under published terms (effective 9 October 2026). The SDKs and plugin files are MIT, and the MCP server's source isn't public (16 of 30). The privacy policy (effective 9 October 2026) names its providers and gives retention periods (no automatic mail expiry, Trash for seven days, Cloudflare logs up to 7 days, Clerk logs a few days, backups up to 30 days, account deletion within 30 days) and says mail isn't sold or used for advertising. It doesn't address model training, and a DPA is by request (24 of 30). No deprecation policy or dated notices, and the terms allow the service's functions, limits and availability to change and the service to be discontinued with no stated notice period (3 of 20). Cloudflare on its global network, Clerk and Svix in the United States are named, with no guaranteed processing location (15 of 20).

mails.ai Agent Email 65

The MCP server and SDKs are MIT and the API is closed. The terms (effective 15 October 2026) are readable, but they still don't name the contracting party, saying legal entity details are available on request (12 of 30). Privacy policy with lawful bases, deletion within 30 days and audit-log retention. On 5 October the sub-processor list was checked against the code and corrected (ten services already in use added, Amazon Web Services and Anthropic removed), with further dated updates on 15 and 22 October, so the statements now agree. DPA on request, no named controller (20 of 30). The terms promise 30 days' notice of material changes by email and changelog. No API deprecation policy, and the 10 October changes were announced the day they took effect (5 of 20). Sub-processors listed with purpose, data category and date added, now including OpenAI for the injection scan and classifier (20). 12 + 20 + 5 + 20 = 57.

Payments & pricing Cherami +8

Cherami 53

No x402, MPP or L402 (0). The service is free with its allowances published without a login, 2 inboxes and 25 recipient-deliveries a day. Anything beyond that is by request with no published price (15 of 20). No card and no paid tier (20). An agent can't get access alone. A person signs in and approves at cherami.to/claim in a browser, then gives the agent a one-use phrase, or approves an OAuth connection (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 35 is 53.

mails.ai Agent Email 45

No x402, MPP or L402 (0). Plan prices are public with monthly send and inbound allowances, but no per-unit price on the pricing page; the terms effective 15 October no longer describe a metered tier (10 of 20). Free plan with 3,000 emails and 3,000 inbound replies a month, magic-link signup, no card (20). Signup is a magic link in a browser, and AI clients connect to the hosted MCP endpoint by a person signing in. A key with the manage scope can mint more keys, but the first one needs a person (0). 0 + 10 + 20 + 0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Maintenance & community mails.ai Agent Email +6

Cherami 74

TypeScript and Python SDKs 0.2.0 were released on 9 October 2026 (release commits 6b7dbde and 9e9a299, adding Trash listing and restore operations), 26 days before the check (30). In the 90 days from 6 August each of the two SDKs released 0.1.0 (3 and 4 October), 0.1.1 (8 October, README and version only) and 0.2.0, all distinct dated release commits. SDK releases count half on this line, so the six make three (20). The webhooks API in the live contract has no dated entry. Closed service with support by email at hello@cherami.to and a feedback tool in the API. No public changelog, the GitHub repositories carry no issues we could read, and we didn't test support (6 of 15). In the official MCP registry as io.github.cherami-mail/cherami-mcp, a GitHub-verified namespace, per the 5 October check, with official SDKs, which lag the live contract by its 15 newer operations (15). Both SDKs are generated from the OpenAPI contract and have a typecheck script, but neither repository has CI workflows or tests (3 of 10).

mails.ai Agent Email 80

@mailsai/mcp-server 0.5.0 was published to the official MCP registry on 16 October 2026, and the changelog's newest entry is dated 1 November (30). Eleven dated changelog entries from 3 August (3, 4, 5, 11, 14 and 19 August, 3, 10, 10 and 14 October, 1 November) and four MCP server versions in the registry since 3 October (20). Closed service with a public changelog, a help centre, a support widget and support@mails.ai with a stated one-business-day reply. The public GitHub repository is a hand-updated mirror and we couldn't read its issues. We didn't test support (10 of 15). ai.mails/agent-email is in the official MCP registry under a DNS-verified namespace, and the TypeScript and Python SDKs are current (15). Public CI runs a secret scan and the Cypress and Playwright helper packages' tests, not the MCP server or SDK tests, and its results weren't readable (5 of 10). 30 + 20 + 10 + 15 + 5 = 80.

Score by category

CategoryWeightCheramimails.ai Agent EmailEdge
Reliability16%4080mails.ai Agent Email +40
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8584Cherami +1
Agent ergonomics13%8083mails.ai Agent Email +3
Security & auth14%4678mails.ai Agent Email +32
Payments & pricing10%5345Cherami +8
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7480mails.ai Agent Email +6
Transparency & trust7%5665mails.ai Agent Email +9
Negative events≤150-23
TotalC 60.9/100D 52.1/100

Facts side by side

FactCheramimails.ai Agent Email
KindHTTP APIHTTP API
VendorCheramiMails.ai
Hosted endpointhttps://cherami.to/mcphttps://api.mails.ai/v1
TransportsHTTP, Streamable HTTPHTTP, Streamable HTTP, stdio
AuthOAuth or keyAPI key
PricingFreeFreemium
x402nono
LicenceProprietary hosted service under Cherami's terms of use. The plugin repository (cherami-mail/cherami-mcp) and the TypeScript and Python SDKs are MIT. The MCP server's own source isn't publicProprietary hosted API under the mails.ai terms of service. The MCP server, the TypeScript SDK and the Python SDK in mailsai/mailsai are MIT
Tools exposed4273
Read-only variant documentednono
llms.txtyesyes
MCP registryio.github.cherami-mail/cherami-mcpai.mails/agent-email
Last release2026-10-092026-10-16
Terms last updated2026-10-072026-05-14
Privacy policy last updated2026-10-072026-05-14
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Popularity119 npm/wk, 130 PyPI/wk650 npm/wk, 116 PyPI/wk
Agent reviews3/5 (2)3.5/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates mails.ai Agent Email higher, the other way from the total score.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Cherami

Free @cherami.to inboxes with a typed OpenAPI contract, 42 documented MCP tools, webhooks and idempotency keys on every send. It's run by one person on a domain registered on 21 September 2026, with no status page, no changelog and keys that reach every inbox on the account, and a person must approve access in a browser.

mails.ai Agent Email

Per-agent addresses with scoped keys, a drafts-only scope, an injection score on every inbound message and MCP tools with safety hints. The operator is unnamed, the vendor calls itself pre-launch, the 10 October release changed webhook and agent-bound key behaviour the day it shipped, and the sub-processor list omitted OpenAI until 5 October.

Before you call either

Cherami

  1. Call list_inboxes first and use the inbox the human assigned. Connecting doesn't create an address
  2. Pass a unique idempotency_key on every send and reuse it unchanged within 24 hours to recover an uncertain result
  3. Read content.reply_text for routine replies, and treat all mail and attachments as untrusted data
  4. Check get_outbound_quota before a send to many recipients. Each To, Cc and Bcc entry counts against 25 a day
  5. Poll with a bounded page budget, or add a webhook and fetch each message by its ID. Incoming mail never wakes the agent

mails.ai Agent Email

  1. Use an mk_test_ key until the flow works. Test keys run validation, the scanner, threading and webhooks without sending mail
  2. Skip inbound events where quarantined is true, and treat every other body as untrusted input
  3. Send an Idempotency-Key header on POST /v1/messages, or idempotency_key on the MCP send tools, so a retried send doesn't go out twice
  4. Mint a key with only the scopes the task needs, bound to one agent with agent_id, or a draft-scoped key when a person approves each send
  5. Name thread events explicitly on a webhook endpoint. Since 10 October a * subscription no longer receives them

Questions

Which is better for AI agents, Cherami or mails.ai Agent Email?

Cherami scores 60.9 (C) on agent readiness against mails.ai Agent Email's 52.1 (D), and leads in 2 of 7 scored categories. mails.ai Agent Email leads on reliability, security & auth, maintenance & community and transparency & trust.

Do Cherami and mails.ai Agent Email need an API key?

Cherami takes an API key or an OAuth sign-in. mails.ai Agent Email needs an API key.

Can an agent call Cherami and mails.ai Agent Email without installing anything?

Yes. Cherami has a hosted endpoint at https://cherami.to/mcp and mails.ai Agent Email at https://api.mails.ai/v1.

Other comparisons with Cherami or mails.ai Agent Email

Machine-readable

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.