Email inboxes for agents by the hour: wait for a mail, get the code or link. Pay per call.
Scored across 9 tools
Most tools have clearly distinct purposes (name check, buy, delete, extend, list, read). However, get_otp, read_message, and wait_for_message all return message content and overlap somewhat, though descriptions (get_otp returns only code/link, wait_for_message blocks) help distinguish them.
Nearly all tools follow a consistent verb_noun snake_case pattern (check_name, create_inbox, delete_inbox, extend_inbox, get_otp, list_messages, read_message, wait_for_message). The lone 'feedback' noun breaks the pattern slightly but is still readable.
Nine tools is well-scoped for an inbox lifecycle service, with each tool earning its place across purchase, lifecycle management, and message retrieval.
The full inbox lifecycle is covered: availability check, purchase, extend, delete, list, read, wait, OTP extraction, and feedback. A status/info tool to inspect an inbox's remaining time is a minor gap but core workflows have no dead ends.
Check whether a name is free to use as the local part of an address, before buying an inbox. Free.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | the local part, 3 to 32 characters: letters, digits, dots, dashes, underscores |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful trait, 'Free' (no cost), but omits other relevant behavior such as whether the result reserves the name or how it is reported.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, purpose front-loaded and the pre-purchase timing stated second, with no filler. Every clause contributes.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter read check with no output schema, the description covers purpose, timing and cost but says nothing about the shape of the result (e.g. boolean availability) or whether a positive check holds the name. Those are the remaining gaps an agent would care about.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the single parameter is fully documented with length and allowed characters, so the schema carries the load. The description's mention of 'local part' mirrors the schema description rather than adding new syntax or constraint detail.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Names a specific verb (check) and a precise resource (a name's availability as the local part of an address), which an agent can distinguish from create_inbox. It stops short of naming a sibling tool explicitly, so it is clear but not fully differentiated within the toolset.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'before buying an inbox' supplies clear timing/context, telling the agent to call this prior to create_inbox. It gives a positive condition but no explicit exclusions or statement of what to do instead on failure.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Buy an email address for an hour, four hours or a day: name@agmail.shveik.dev with the name you choose (or a random one). Paid in stablecoins with x402: call it without a payment to get the quote, then again with the signed payment in _meta. The result has the inbox id and the secret (shown once, keep it); the inbox takes mail once the payment has settled.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | the local part of the address; omit it for a random name | |
| duration | Yes | how long the inbox lasts: 1h, 4h or 24h |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare the mutation profile (readOnlyHint=false, idempotentHint=false), but the description adds material context they don't carry: payment is required via x402 stablecoins, the secret is returned once and must be kept, and mail delivery only begins after settlement. It stops short of covering post-expiry behavior, name-collision errors, or irreversibility of the purchase.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tightly packed sentences that lead with what the tool does, then the payment mechanism, then the return-value caveat. No filler; every clause carries operational information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description correctly discloses the return shape (inbox id plus one-time secret) and the payment prerequisite. It omits edge cases an agent would need — name-taken handling (which ties to the check_name sibling), what happens when the duration expires, and whether purchase is refundable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%: the 'name' parameter already documents the random fallback and 'duration' already carries the 1h/4h/24h enum. The description mostly restates these, adding only the resulting address format, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource ('Buy an email address') with concrete scope (1h/4h/24h) and the exact address format produced. An agent can distinguish this from siblings like check_name (availability), extend_inbox (renewal), and delete_inbox without opening any schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Clearly describes the two-step invocation protocol: call without payment to obtain a quote, then call again with the signed payment in _meta. It gives strong invocation context but never names siblings (e.g. check_name for verifying a desired name, extend_inbox for renewing) or states when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Delete an inbox and all its mail now. There is no refund. Free; needs the inbox id and secret.
| Name | Required | Description | Default |
|---|---|---|---|
| secret | Yes | the inbox secret returned by create_inbox | |
| inbox_id | Yes | the inbox id returned by create_inbox |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description says the tool deletes all mail irreversibly ('There is no refund'), but the annotations declare destructiveHint=false. This directly contradicts the structured safety profile, so the description cannot be trusted on behavior without resolving the inconsistency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short sentences with the core action front-loaded. The warning and cost note are compact, though the semicolon construction in 'Free; needs the inbox id and secret.' is slightly awkward.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple delete tool with complete parameter documentation and no output schema, the description covers the destructive effect and required inputs. However, it omits usage alternatives, permission requirements, and fails to reconcile the behavioral contradiction with annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with both parameters already documented. The description only restates that the inbox id and secret are needed, adding no syntactic or semantic detail beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb and resource: 'Delete an inbox and all its mail now.' This is clear and distinct from siblings like create_inbox and extend_inbox, though it does not explicitly differentiate itself from any alternative.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites. The 'no refund' warning describes an effect, not usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Extend an inbox you own by one, four or twenty-four hours, keeping its address and its mail. Paid in stablecoins with x402 like create_inbox. Needs the inbox id and its secret. An inbox cannot be paid for more than 72 hours ahead.
| Name | Required | Description | Default |
|---|---|---|---|
| secret | Yes | the inbox secret returned by create_inbox | |
| duration | Yes | how long the inbox lasts: 1h, 4h or 24h | |
| inbox_id | Yes | the inbox id returned by create_inbox |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations mark this as a non-readonly, non-idempotent, non-destructive mutation, and the description adds real value beyond them: stablecoin/x402 payment, the secret requirement, and the 72-hour forward-payment cap. The additive nature of 'extend by one, four or twenty-four hours' also aligns usefully with idempotentHint=false. It stops short of describing payment failure or whether the extension is applied before or after payment settles.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences, front-loaded with the action and scope, then cost model, then the hard limit. No filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so the description carries return-value burden, and it is largely adequate: it covers ownership, credentials, payment, and the 72-hour cap. It omits what a successful call yields (e.g. new expiry) and what happens on payment failure, which would fully close the gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and each parameter already carries a description, so the schema does the heavy lifting. The description restates that the id and secret are needed but adds no format or constraint detail beyond what the schema and enum already provide; baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Extend an inbox you own by one, four or twenty-four hours') plus the key preservation guarantee ('keeping its address and its mail'). This distinguishes it cleanly from create_inbox and the other inbox siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Clear context: you must own the inbox, and you need its id and secret; the 72-hour ceiling tells the agent when the call will be rejected. No explicit 'when not to use' or named alternative beyond the passing reference to create_inbox for the payment model.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free. Tell the people who run this service what worked, what failed or what you miss: a bug, an idea or a thanks. A person reads it. No payment, no account; limited to a few messages an hour.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | other | |
| route | No | the route the feedback is about, if any | |
| contact | No | optional: how we can reach you or your operator | |
| message | Yes | what worked, what did not, what you miss; no secrets or private data |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare write/non-destructive/non-idempotent; the description adds genuinely new traits: no payment, no account required, a human reads the message, and a rate limit of a few messages per hour. It stops short of saying what happens on rejection or whether the message is retained or published.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences with zero waste; the free/no-account framing is front-loaded before the behavioral caveats.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 4-param write tool with no output schema, the description conveys cost, auth requirements, rate limits, and downstream human handling. It is nearly complete, missing only what the agent gets back or what happens if the rate limit is hit.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 75% and the schema itself documents kind (enum), route, contact, and message. The description adds no format or semantic detail for any parameter — 'route' and 'contact' are never mentioned, and the kind list omits 'other'. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (tell) and audience (the people who run this service) plus the content domain (bug, idea, thanks). No sibling tool (check_name, create_inbox, list_messages, etc.) competes for this intent, so an agent can route here unambiguously.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies when to use it by enumerating the sendable content types ('a bug, an idea or a thanks'), which map onto the kind enum. It gives context (free, no account, rate limited) but never states when not to use it or points to an alternative channel.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Wait for a message that carries a verification code or link and return only the code and the link. Free; needs the inbox id and secret.
| Name | Required | Description | Default |
|---|---|---|---|
| from | No | only a message whose sender contains this text | |
| after | No | only a message with a sequence number above this (the seq of the last one you saw) | |
| secret | Yes | the inbox secret returned by create_inbox | |
| timeout | No | seconds to wait for a message | |
| inbox_id | Yes | the inbox id returned by create_inbox | |
| subject_contains | No | only a message whose subject contains this text |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, non-destructive, and non-idempotent, so the safety profile is covered. The description adds genuinely new context: the call blocks while waiting, it is free, and it filters the response down to just the code and link. It does not disclose what happens on timeout expiry, which is the remaining gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences with no filler; the core behavior is front-loaded and the cost/prerequisite fragment is short. Minor redundancy in restating required inputs the schema already marks as required, but nothing bloats the definition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema the description carries the burden of return values, and it does say only the code and link come back. But for a blocking, timeout-bounded wait tool it never states the failure/timeout outcome, and the 'after' rationale (re-polling without re-seeing messages) is left entirely to the schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all six parameters including the timeout bounds and the after/from/subject_contains filters are already documented in the schema. The description only restates that inbox_id and secret are required, adding no semantics beyond the structured fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('wait for a message') plus the resource (a message carrying a verification code or link) and pins down the return shape ('only the code and the link'). That output-filtering detail implicitly distinguishes it from siblings like wait_for_message and read_message, though no sibling is named outright.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Free; needs the inbox id and secret' supplies a cost property and prerequisites, which is useful. However, it never says when to pick this over wait_for_message or read_message, nor when not to use it (e.g. for non-OTP mail), so usage is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the messages of an inbox (sender, subject, size) after a sequence number. Free; needs the inbox id and secret.
| Name | Required | Description | Default |
|---|---|---|---|
| after | No | only messages with a sequence number above this | |
| limit | No | ||
| secret | Yes | the inbox secret returned by create_inbox | |
| inbox_id | Yes | the inbox id returned by create_inbox |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare a safe read (readOnlyHint true, destructiveHint false, openWorldHint false), so the safety profile is covered. The description adds auth prerequisites ('needs the inbox id and secret') and a cost signal ('Free'), which are genuine additions beyond structured data. It does not mention pagination/limit behavior, keeping it short of a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two compact clauses, front-loaded with the operation and its result fields, followed by cost and auth notes. No filler, though the second clause is terse enough to be slightly telegrammatic.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read-only 4-parameter listing tool with no output schema, the description covers what is returned (sender, subject, size), the paging anchor, cost, and auth. Minor gaps remain around limit/pagination behavior, but nothing critical is missing for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 75% and the schema documents after, secret, and inbox_id; only limit lacks a schema description. The description restates the 'after a sequence number' semantics but adds nothing about limit or default/max bounds, so it is baseline-level when the schema does most of the work.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Specific verb (list) plus resource (messages of an inbox) and it names the returned fields (sender, subject, size) and the paging anchor (after a sequence number). It is not explicitly differentiated from read_message or wait_for_message, but the resource and shape are clear enough to separate it from create_inbox/delete_inbox.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'after a sequence number' implies incremental polling, and the mention that it 'needs the inbox id and secret' gives a prerequisite, but there is no explicit when-to-use vs read_message, wait_for_message, or get_otp. Usage is implied rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read one message of an inbox: its text, codes, links and attachment names. Free; needs the inbox id and secret.
| Name | Required | Description | Default |
|---|---|---|---|
| secret | Yes | the inbox secret returned by create_inbox | |
| inbox_id | Yes | the inbox id returned by create_inbox | |
| message_id | Yes | the message id from list_messages |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/destructive/idempotent/openWorld, so the safety profile is covered. The description adds genuinely new behavioral context: the operation is free (no billing side effect) and it requires inbox credentials, plus a preview of the returned content. It omits any note on errors for missing/expired messages, but that is a minor gap given annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short clauses with zero filler; the core action is front-loaded and the credential/cost notes follow compactly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, and the description compensates by naming the returned fields (text, codes, links, attachment names); annotations carry the safety profile. The only shortfall is silence on failure modes (invalid/expired message) and the required message_id.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents all three parameters including their provenance (create_inbox, list_messages). The description restates inbox_id and secret but notably omits message_id, which is also required, so it adds no meaning beyond the schema and slightly under-describes the call.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Specific verb + resource + scope: 'Read one message of an inbox', which cleanly separates it from the sibling list_messages (all messages) and wait_for_message (blocking retrieval). It also enumerates the payload the agent gets back (text, codes, links, attachment names).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives a precondition ('needs the inbox id and secret') and cost context ('Free'), but never states when to prefer this over get_otp or wait_for_message, nor when-not to use it. Usage is only implied by the fact that a message_id is needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Wait until a message arrives in an inbox (up to 55 seconds) and return it with its text, codes and links. Returns at once if a matching message is already there. Free; needs the inbox id and secret.
| Name | Required | Description | Default |
|---|---|---|---|
| from | No | only a message whose sender contains this text | |
| after | No | only a message with a sequence number above this (the seq of the last one you saw) | |
| secret | Yes | the inbox secret returned by create_inbox | |
| timeout | No | seconds to wait for a message | |
| inbox_id | Yes | the inbox id returned by create_inbox | |
| subject_contains | No | only a message whose subject contains this text |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only cover the safety profile (readOnly/non-destructive), so the description usefully adds the 55-second cap, immediate return when a message already exists, and that it returns text, codes and links. It also flags the auth need ('needs the inbox id and secret'). It stops short of explaining polling semantics or failure/timeout behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences with no filler, leading with the blocking behavior and the cap before the fallback and auth note. Every sentence carries weight.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description earns credit by naming the return payload (text, codes, links) and the timing/backoff behavior. The filtering parameters are left entirely to the schema, which is acceptable given 100% coverage, but a note on match semantics would round it out.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so from/after/timeout/subject_contains semantics are fully documented by the schema. The description only restates the required inbox_id and secret, adding nothing beyond the structured fields; baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Specific verb ('Wait until a message arrives') plus the resource (inbox) and what is returned (text, codes, links). It is clearly distinct from sibling read_message/list_messages, which read existing messages rather than block for a new one.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It implies the use case (blocking for an incoming message) and notes 'Returns at once if a matching message is already there' and that it is 'Free'. However, it never names the alternatives (read_message, list_messages, get_otp) or states when not to use it, leaving routing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_namecreate_inboxdelete_inboxextend_inboxfeedbackget_otplist_messagesread_messagewait_for_messageReal email inboxes for AI agents: create inboxes, catch verification codes, extract OTPs, reply.
Disposable email inboxes for AI agents: create an address, wait for the OTP or verify link.
Disposable email for agents: create an inbox, wait for the message, read the code. No key needed.
Real email inboxes for AI agents: create addresses, send, wait for mail and verification codes.
Add one secure layer between your agents and this server.
