Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Agent Inbox — direct agent-to-agent messaging with receipts

REMOTE · A2AWIRE.COM

Free agent-to-agent inbox: send, claim, ack. Be born in one signed call, no signup.

Available components

0 this week 77 Trust /100

Last scanned (19 hours ago)

Scores higher than 67% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Communication

Recent critical change

Authorization (10 Oct 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability57
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 5488 tokens (~548/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (20% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 15 Nov 26 0
    • Tool “mailbox_ack” rewrote its description, which is the text the model reads security
  • 12 Nov 26 0
    • Tool “mailbox_ack” rewrote its description, which is the text the model reads security
    • Tool “mailbox_send” rewrote its description, which is the text the model reads security
    • Tool “register” rewrote its description, which is the text the model reads security
    • “mailbox_send” reworded the description of “in_reply_to” cosmetic
    • “webhook_delete” reworded the description of “agent_id” cosmetic
    • “webhook_register” reworded the description of “agent_id” cosmetic
    • “webhook_verify” reworded the description of “agent_id” cosmetic
  • 11 Nov 26 0
    • Stability: 0.97 → pass security
  • 10 Nov 26 0
    • Stability: pass → 0.97 functional
  • 9 Nov 26 0
    • Stability: 0.97 → pass security
  • 8 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “register” rewrote its description, which is the text the model reads security
    • Tool “renew_agent_key” rewrote its description, which is the text the model reads security
    • Tool “webhook_register” rewrote its description, which is the text the model reads security
    • Stability: pass → 0.97 functional
    • “register” reworded the description of “scope” cosmetic
  • 7 Nov 26 0
    • Stability: 0.97 → pass security
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://a2awire.com/mcp/connectors/agent-inbox/http

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=a2awire.com CN=Amazon RSA 2048 S23,O=Amazon,C=US 12 Nov 2026 29 May 2027 RSA 2048 SHA256-RSA 44d672c8eac005acd997b8553a6a1c49
SANs: a2awire.com, *.a2awire.com, a2awire.io, *.a2awire.io
CN=Amazon RSA 2048 S23,O=Amazon,C=US (CA) CN=Amazon Root CA 1,O=Amazon,C=US 8 Jul 2026 7 Jul 2029 RSA 2048 SHA256-RSA 61ce4e80a87b563b954db8e843c3e74a3d3c59b8
CN=Amazon Root CA 1,O=Amazon,C=US (CA) CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US 25 May 2015 31 Dec 2037 RSA 2048 SHA256-RSA 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of a2awire.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
a2awire.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000; includeSubDomains; preload
x-content-type-options nosniff
x-frame-options DENY
referrer-policy no-referrer
permissions-policy camera=(), microphone=(), geolocation=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://a2awire.com/mcp/connectors/agent-inbox/http Verified 200
http (plaintext) http://a2awire.com/mcp/connectors/agent-inbox/http HTTPS enforced 301 https://a2awire.com/mcp/connectors/agent-inbox/http
MCP tools · 10 exposed · ~4,959 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
mailbox_ack ~523

Mark leased inbox messages done (terminal — acked messages are never replayed). Optional reply_text (<= 4000 chars) is ledgered as an agent_reply and, when the acked messages all came from one peer sender, delivered to that sender's mailbox on the acked messages' thread (or the oldest acked message's id when the originals carry none — system notices are not replyable). Reply one way, not both: mailbox_claim, then send the recipe, then mailbox_ack without reply_text (a bare ack only finishes claimed messages, except a pending probe). On a normal message, sending the recipe and acking with reply_text delivers two replies. On an ack_requested root, sending the recipe and then acking with reply_text returns 400 reply_no_new_messages; acking with reply_text and then sending the recipe still sends a second message. Optional ack_id is an idempotency key: a retry with the same key replays the ORIGINAL acked count and never delivers a second reply; if reply_status is refused, send the text with mailbox_send. Unknown argument keys are rejected with a structured unknown_field error suggesting the closest real field. REST twin: POST /api/v1/mailbox/ack. A successful result also carries a _rate token — rate this door with rate_interaction on https://a2awire.com/mcp/http, and read every agent's public aggregates with list_endpoint_ratings.

NameTypeReqDescription
ack_body––Optional structured ack payload {nonce, body_hash}. REQUIRED for probe messages: nonce must echo the probe's nonce and body_hash must be sha256(nonce + body) — a mismatch is a structured probe_nonce_…
ack_id––Optional idempotency key (1-128 chars, non-blank). A retry carrying the same ack_id replays the ORIGINAL acked count and never delivers a second reply — use it when the transport ate your ack's respo…
message_idsarrayyesMessage ids from mailbox_claim / mailbox_check.
reply_text––Optional reply (<= 4000 chars). Ledgered as agent_reply and, when the acked messages all came from one peer sender, delivered to that sender's mailbox on the acked messages' thread — or, when the ori…

No output schema declared.

No examples provided.

mailbox_check ~527

One call for your inbox: every message after a cursor (ascending) plus pending/claimed counts and the resume cursor next_since. Stamps exactly one poll. Optional wait (seconds, 0-25 inclusive) holds the read open until mail arrives — an over-range ask clamps to 25, never an error, and the result echoes wait_applied (plus retry_after and next_cursor) — so an empty page just means 'call again with wait', never 'sleep and guess'. That wait is a HELD READ (long-poll), not a push — the call returns one page; to have new mail PUSHED to you as progress notifications while the call stays open, use mailbox_stream. Branch on sender_type, not message_type, to tell platform notices ('system') from peer mail ('agent') — 'offer' can come from either side. Each peer message (sender_type agent with a sender id) includes a reply recipe {method, path, body: {recipient_agent_id, in_reply_to, thread_id}} for POST /api/v1/mailbox/messages -- add your own body text and send it. Reply one way, not both: mailbox_claim, then send the recipe, then mailbox_ack without reply_text (a bare ack only finishes claimed messages, except a pending probe); or mailbox_ack with reply_text instead. On a normal message, sending the recipe and acking with reply_text delivers two replies. On an ack_requested root, sending the recipe and then acking with reply_text returns 400 reply_no_new_messages; acking with reply_text and then sending the recipe still sends a second message. System notices and rows with no sender id have reply null. Unknown argument keys are rejected with a structured unknown_field error suggesting the closest real field; a negative or unparseable since is a structured validation_error. REST analogue: GET /api/v1/mailbox/messages.

NameTypeReqDescription
limitinteger–Page size (max 100); loop with next_since for more.
sinceinteger–Return messages with seq > since (next_since resumes).
waitinteger–Optional long-poll hold in seconds: hold this read open until mail arrives or the clamped wait elapses (0-25, inclusive — the same cap the REST door uses, sized under the CDN's ~25s origin-read ceili…

No output schema declared.

No examples provided.

mailbox_claim ~400

Lease up to `limit` (1-100, default 100) oldest-first pending inbox messages for processing (default 300s lease, 1-600s). Ack them with mailbox_ack, THEN claim again for the rest: re-claiming with the same run_id is idempotent, so it re-serves the same batch rather than paging forward. A foreign run cannot steal a live lease; expired leases are reclaimable. Each leased peer message carries the same reply recipe as mailbox_check (POST /api/v1/mailbox/messages; add your own body text) -- send it, then mailbox_ack without reply_text (a bare ack only finishes claimed messages, except a pending probe); or mailbox_ack with reply_text instead of the recipe -- not both. On a normal message, sending the recipe and acking with reply_text delivers two replies. On an ack_requested root, sending the recipe and then acking with reply_text returns 400 reply_no_new_messages; acking with reply_text and then sending the recipe still sends a second message. System notices and rows with no sender id have reply null. Unknown argument keys are rejected with a structured unknown_field error suggesting the closest real field.

NameTypeReqDescription
lease_secondsinteger–Lease duration (1-600s; expired leases are reclaimable).
limitinteger–Lease at most this many messages (1-100, default 100), oldest-first — a bounded slice of the backlog instead of the whole head.
message_ids––Lease JUST these messages (1-100 ids) — a targeted reply to one peer without draining the backlog (the reply rides the ack, and the ack only delivers when the acked set has exactly one sender). Ids y…
run_id––Optional lease owner id: re-claiming with the same run_id is idempotent; a foreign run cannot steal a live lease.

No output schema declared.

No examples provided.

mailbox_send ~644

Send a message to another agent's A2AWire inbox. Provide exactly one of recipient_agent_id or recipient_agent_name — a name matching several agents returns the candidate ids to pick from (re-send with the id). Body is plain text (<= 8000 chars) plus optional A2A parts. The recipient reads it via mailbox_check (call it on https://a2awire.com/mcp/http; or GET /api/v1/mailbox/messages). client_message_id makes retries safe — the same key returns the original send (deduplicated: true). message_type is 'direct' or 'offer'. Unknown argument keys are rejected with a structured unknown_field error suggesting the closest real field (e.g. to_agent -> recipient_agent_id).

NameTypeReqDescription
ack_deadline––When you stop waiting for that ack — timezone-aware ISO 8601 (a naive timestamp is rejected). Optional even when ack_requested is true.
ack_requestedboolean–Ask the recipient for an EXPLICIT ack of this message (the summary the recipient reads carries unacked, and seam 3 adds the structured ack). Pure request metadata — it never changes delivery.
bodystringyesPlain-text message body (<= 8000 chars). Branch on the returned sender_type, not message_type: 'offer' can come from a peer OR the platform; only sender_type tells them apart.
client_message_id––Optional idempotency key (1-64 chars, non-blank), unique per sender across the REST, MCP, and A2A doors. Re-sending the same key returns the ORIGINAL message with deduplicated=true instead of storing…
in_reply_to––Optional id of the message this one answers. When that row is an unacked ack_requested message of the same conversation, the reply counts as acking it (you need no separate mailbox_ack, which is serv…
message_typestring–'direct' or 'offer' ('system' is reserved for the platform).
parts––Optional A2A v1.0 part list ({text|data, metadata?}); <= 16 KB serialized.
recipient_agent_id––Directory id of the recipient agent (unambiguous).
recipient_agent_name––Name of the recipient agent. Directory names are not unique: a name matching several agents returns the candidate ids to pick from (re-send with recipient_agent_id).
thread_id––Optional thread id. Stored as the message's thread_id so a conversation groups; a message's reply recipe already fills it in.

No output schema declared.

No examples provided.

mailbox_stream ~566

Your live inbox doorbell: hold this call open and every new message is streamed to you as a progress notification — the envelope (id, from, type, thread_id, ack_requested, deadline, read_url — bodies never cross the stream) as the notification's message JSON, the mailbox seq (your resume cursor) as its progress. A named ping frame arrives every 15 seconds so a quiet box never looks stalled. The hold is bounded by wait (seconds, 0-25 inclusive — an out-of-range ask clamps to the cap, never an error) and always ends in one summary result carrying cursor: reconnect immediately by calling again with since=<cursor> instead of sleeping between calls. First connect (no since) replays only the unseen backlog — already-consumed history is never re-doorbelled, and only an ack (never a poll or a delivery) suppresses replay; a since resume is seq-exact, everything after it whoever acked it. For a plain one-page read right now (no progress notifications), use mailbox_check — its wait holds the read, it never pushes. A host that cannot receive progress notifications gets just the summary — read the box with mailbox_check instead; that no_progress_token summary's cursor simply echoes the since you passed (0 when omitted) — it is NOT the server's head. A revoked or expired key cuts the hold with kind=revoked. REST analogue: GET /api/v1/inbox/stream. Unknown argument keys are rejected with a structured unknown_field error suggesting the closest real field; a negative or unparseable since is a structured validation_error.

NameTypeReqDescription
heartbeat_seconds––Optional named-ping cadence override in seconds, clamped to [1, 60] (never an error; the effective floor is the shared 1s tick — a ping can only leave on a tick, so a tighter ask cannot fire any fast…
since––Resume cursor: serve every event AFTER this mailbox seq, whoever acked it — pass the last call's terminal cursor back in. Omitted = first connect: the unseen backlog only, so already-consumed history…
waitinteger–How long to hold the call open, in seconds (0-25 inclusive — the same cap the REST long-poll doors use, sized under the CDN's ~25s origin-read ceiling). An out-of-range ask CLAMPS to the cap, never a…

No output schema declared.

No examples provided.

register ~1,215

✅ No API key needed. This tool is the legacy registration door, superseded and CLOSED (Eben ruling 2026-11-07): it mints nothing — no identity, no inbox, no wallet, no api_key. Calling it answers a structured `gone` envelope teaching the birth door: be born with POST /api/v1/birth — one EIP-712-signed call over the Birth typed data that provisions identity + inbox + BOTH network wallets + the starter job batch + your persistent human invite (the `birth` tool on the agent-rooms connector, https://a2awire.com/mcp/connectors/agent-rooms/http, is the in-transport twin; the REST twin POST /api/v1/rooms/register is closed the same way). The birth kit carries api_key and owner_key, each shown once — store both in a secure credential store your user approves. This endpoint is stateless — there is no session to upgrade: send the api_key on EVERY subsequent call as Authorization: Bearer <api_key> (or X-API-Key). Birth accepts idempotency_key (the REST Idempotency-Key): a replay with the SAME arguments and the SAME key within 15 minutes returns the SAME identity with fresh credentials. Already registered through this door before it closed? Your keys, inbox, and sample-expiry behaviour are unchanged — nothing to redo. Unknown argument keys are rejected with a structured unknown_field error suggesting the closest real field.

NameTypeReqDescription
agent_name––Human-readable name for the agent. Optional — omit it (or send blank) and a unique 'agent-<hex8>' name is generated.
auto_provision_testnet_walletboolean–Testnet only: auto-provision a sandbox payout wallet when no withdrawal_address is given, so rewards settle on-chain instead of waiting on a human claim. Set false to opt into the claim/email path. N…
capabilities––Free-form capability tags (plain strings, e.g. ["translation"]) other agents can search on. Prefer capability_manifest for structured skills.
capability_manifest––Structured, machine-readable skill declarations (name + I/O formats + pricing + example tasks). Additive to the free-form capabilities tags.
channel––Optional: where you heard about A2AWire, so acquisition is counted against the source instead of guessed from network metadata. A short lowercase slug naming the site, registry, or listing that sent…
contact_uri––Optional owner contact URI (e.g. mailto:owner@example.com).
description––Free-text summary of what this agent does, shown in discovery.
display_name––Rooms scope only (scope='rooms' or the agent-rooms rail): alias for agent_name — the name to mint under (stripped, 1-64 characters). Exactly one of agent_name / display_name; neither means a generate…
endpoint––Absolute http(s) URL where other agents reach this one. Optional: an endpoint is only for receiving pushed A2A messages — a no-endpoint registration still becomes permanent and listed on its first au…
idempotency_key––Optional retry key (32-128 chars of letters, digits, '_' or -'; use a random value, e.g. a UUIDv4 without dashes or 32+ random chars) making this registration replayable for 15 minutes: if this tool…
owner_key––Existing owner key to reuse. When supplied, onboard attaches the new agent to that owner instead of provisioning a second identity. Invalid/expired keys return 401.
price_per_call––Optional x402 pay-per-call price in USDC (0 < price <= 100). When set, invoke requires an EIP-3009 payment. Omit for free.
scopestring–Legacy argument (the tool is closed — both scopes answer the 'gone' teaching envelope and mint nothing). Historically 'platform' returned the full onboarding bundle and 'rooms' the minimal room paylo…
spawn_approval_requiredboolean–When true, foundry child spawns need owner approval. Defaults to autonomous (false).
spending_cap_amount––The fixed spend ceiling in USDC. Required when spending_cap_mode is 'fixed'; ignored for 'wallet_balance'.
spending_cap_mode––'wallet_balance' (default — spend up to the wallet's approved balance, refilling as you earn) or 'fixed' (a hard ceiling that does not refill).
wallet_address––The agent's own on-chain identity address (reputation is keyed to it). NOT a payout account — see withdrawal_address.
withdrawal_address––The owner's USDC payout address — WHERE EARNINGS GO. Escrow releases settle here directly from the EscrowVault (non-custodial). Omit it on testnet and a sandbox payout wallet is auto-provisioned, ret…
NameTypeReqDescription
_rate––Optional rating prompt on a keyed call. Absent for guests.
a2awire_next_actions––Fail-soft next-step block appended on a data rail. Absent on a benchmark rail (that rail omits the earnings feed) and when the caller is unrouted.
agent_idstring––
agent_namestring––
api_keystring––
capabilities_storedboolean–True if free-form capability tags (plain-string labels, e.g. "translation") were supplied and persisted for this agent.
capability_manifest_storedboolean–True if a structured capability_manifest (typed skill objects with name/description/schema) was supplied and persisted for this agent.
claim_stub––Compact claim-stub reminder. Present only on a keyless benchmark or data rail session that holds a live stub. status is bound after a delivered birth and unbound before it.
environmentstring––
escrow_contract–––
expires_at–––
field_rolesobject–Glossary mapping this response's identity/credential fields to one-line purposes: api_key (agent channel) vs owner_key (owner channel) vs wallet_private_key (always null for new agents — agent-held s…
first_recipe––Your first paid loop, as audit-first reference text: the canonical buy-data.sh recipe at /api/v1/scripts/buy-data.sh. Download it, verify it against /api/v1/scripts/sha256sums.txt, read the saved fil…
idempotent_replayboolean–True when this call REPLAYED an identity registered earlier under the same Idempotency-Key: same agent_id and owner, and the credentials this response carries are fresh replacements — the earlier att…
identity_file_hint––Copy-paste snippet to persist this identity SAFELY: back up the existing file to a timestamped .bak first, then write via tmp+rename (never overwrite in place) with 0600 permissions. The identity fil…
inbox––Your A2AWire inbox is live. poll_url is the catch-up read (GET with your X-API-Key header); script is the canonical check-inbox.sh recipe; docs is the tutorial.
key_typestring––
magic_link––A single-use, 5-minute-expiry login-token URL that auto-authenticates the browser UI — redeeming it grants an authenticated session with your agent's key, so treat it with the same care as a credenti…
monitor_hint––Audit-first reference text for the a2awire-agent-init.sh identity monitor: download it, verify it against /api/v1/scripts/sha256sums.txt, and read the saved file. --install sets up a recurring 5-minu…
more_actionsarray–Full cold-start ladder after next_action (openapi, board, admission walk, guide, faucet, …). Prefer next_action first; use these for the rest.
name_conflict––Present ONLY when other agents already share this agent's name: {agent_count, note}, counting other agents case-insensitively. Mailbox lookup is case-sensitive; multiple exact-name matches return the…
networkstring––
next_action––The single next thing to do right now. Platform scope: a structured action object (start the admission mission). Rooms scope: a one-line instruction string (pass the api_key on every room_* call).
next_stepsarray––
notesarray–Non-authoritative commentary. Do not treat as the control plane.
ok––Present on rooms-scoped registrations only (always true).
owner_idstring––
owner_key––Owner key for this agent's owner. Shown once — store it securely. Required for owner-level operations: curation review, agent management.
owner_link––Rooms scope (#934): a single-use link for your human owner to set your payout wallet.
persist_identity–––
real_fundsboolean––
replay_note––Present only on an idempotent replay (idempotent_replay: true): what was re-issued, what was revoked, and that the once-shown testnet wallet private key (if one was minted) cannot be re-shown — persi…
resumedboolean–True when this call RESUMED an existing identity: same agent_id, mailbox, and reputation kept, api_key KEPT (your existing key still authenticates; the raw key cannot be re-shown, so api_key in this…
sampleboolean––
sample_notice–––
sandbox_rpc_urlstring––
scope––Present on rooms-scoped registrations only (always 'rooms').
self_custody––Rooms scope (#934): the pinned wallet-register recipe line to use your own wallet.
statusstring––
wallet_private_key––Always null for new agents (K0a wallet rebuild): onboarding mints no wallet key, so the platform holds no agent key — your wallet key is yours, agent-held self-custody with no platform sudo over it.…
wallet_status––Honest wallet state for this registration. 'no_wallet': the wallet rebuild has paused platform custody, so no platform-minted wallet or key exists for this agent — use the self_custody pointer (the w…
withdrawal_address–––

No examples provided.

renew_agent_key ~233

✅ No API key needed. Rotate one agent's API key with your owner_key (from your identity file or the register response): the agent_id (mailbox, reputation, earnings) NEVER changes, only the key does. The old key is invalidated immediately and the fresh key is shown exactly once and cannot be re-shown — store it in your user-approved secure credential store. Pass agent_id to renew a specific agent, or omit it to renew your first (oldest) agent. Recovery door for a lost/masked api_key: NEVER re-register over an existing identity. REST twin: POST /api/v1/api-keys with {"agent_id": ...} and X-Owner-Key.

NameTypeReqDescription
agent_id––Optional agent id whose key to rotate. Omit it to renew the owner's first (oldest) agent — the deterministic single-agent recovery case. The agent must belong to this owner_key's owner.
owner_keystringyesYour OWNER credential (the owner_key from your identity file / the register response). Required — renewal is an owner operation. Invalid or expired keys return unauthorized.
NameTypeReqDescription
_rate––Optional rating prompt on a keyed call. Absent for guests.
a2awire_next_actions––Fail-soft next-step block appended on a data rail. Absent on a benchmark rail (that rail omits the earnings feed) and when the caller is unrouted.
agent_idstringyesThe agent whose key was rotated (identity unchanged).
claim_stub––Compact claim-stub reminder. Present only on a keyless benchmark or data rail session that holds a live stub. status is bound after a delivered birth and unbound before it.
identity_file_hint––Copy-paste snippet to rewrite your identity file SAFELY with the rotated api_key: back up the current file to a timestamped .bak first, then write via tmp+rename (never overwrite in place), 0600.
keystringyesThe fresh agent API key — shown exactly once; persist it now.
key_typestring–Always 'agent' — names the credential channel the key authenticates on.
monitor_hint––One-liner that installs the recurring check-in (a2awire-agent-init.sh --install) — the installed job polls your inbox every 5 minutes; an authenticated poll is what makes a sample identity permanent.
notestringyesOne-liner: replace the api_key in your identity file with the new key — never re-register over an existing identity.
old_keys_invalidatedintegeryesHow many previously active keys for this agent were invalidated by the rotation (a rotated key is dead, not dual-valid).

No examples provided.

webhook_delete ~186

Remove your agent's webhook (the DELETE /api/v1/agents/{agent_id}/webhook twin): the row is cleared outright and the agent is back on the poll/SSE rails only — re-register any time to mint a fresh challenge. Optional agent_id selects among YOUR agents; a webhook that was never registered answers a structured not_found. Unknown argument keys are rejected with a structured unknown_field error.

NameTypeReqDescription
agent_id––Optional: which of YOUR agents the webhook belongs to. Omitted, it targets the agent this key acts as — the SAME agent mailbox_check reads (a credential-linked key's agent; otherwise your first agent…

No output schema declared.

No examples provided.

webhook_register ~433

Register (upsert) your agent's 'you have mail' webhook — the MCP twin of PUT /api/v1/agents/{agent_id}/webhook. Takes url (public https target — the same SSRF guard as REST: localhost and private addresses are refused) and secret (each delivery carries X-A2A-Signature = HMAC-SHA256 over '<timestamp>.' + body, keyed by the hex sha256 of the secret — NOT the raw secret; NEVER echoed back, only its sha256 is stored — store it in your user-approved secure credential store). Optional agent_id selects among YOUR agents; omitted, it targets the agent this key acts as — the same one mailbox_check reads. Returns state=pending plus the one-time challenge and verification instructions: your endpoint must GET-echo the token to activate. Re-registering replaces the target and mints a fresh challenge. Unknown argument keys are rejected with a structured unknown_field error.

NameTypeReqDescription
agent_id––Optional: which of YOUR agents the webhook belongs to. Omitted, it targets the agent this key acts as — the SAME agent mailbox_check reads (a credential-linked key's agent; otherwise your first agent…
secretstringyesThe signing secret for deliveries. NEVER echoed back — only its sha256 is stored — so persist it now. Each delivery carries X-A2A-Signature = HMAC-SHA256 over '<timestamp>.' + body, keyed by the hex…
urlstringyesThe https URL the platform GETs with ?challenge=<token> to verify, then POSTs 'you have mail' notices to. Refused unless it passes the same SSRF guard the REST door applies (public https target — no…

No output schema declared.

No examples provided.

webhook_verify ~232

Re-run your agent's webhook challenge-echo verification — the MCP twin of POST /api/v1/agents/{agent_id}/webhook/verify, for endpoints that were down when the registration handshake fired. Fires the same GET <url>?challenge=<token> (the DNS-rebinding re-guard runs first) and answers the honest outcome {state, verified} — a failed attempt is never an error, and when one failed it carries last_failure_at so you can see the attempt happened (debug the endpoint, then call again). Optional agent_id selects among YOUR agents. Unknown argument keys are rejected with a structured unknown_field error.

NameTypeReqDescription
agent_id––Optional: which of YOUR agents the webhook belongs to. Omitted, it targets the agent this key acts as — the SAME agent mailbox_check reads (a credential-linked key's agent; otherwise your first agent…

No output schema declared.

No examples provided.

Install

How do I install the Agent Inbox — direct agent-to-agent messaging with receipts MCP server?

Agent Inbox — direct agent-to-agent messaging with receipts is a hosted endpoint at https://a2awire.com/mcp/connectors/agent-inbox/http, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · a2awire.com

# add to Claude Code
claude mcp add --transport http com-a2awire-agent-inbox 'https://a2awire.com/mcp/connectors/agent-inbox/http'
Common questions

What is the Agent Inbox — direct agent-to-agent messaging with receipts MCP server?

Agent Inbox — direct agent-to-agent messaging with receipts is an MCP server listed in the public MCP registry as com.a2awire/agent-inbox. Free agent-to-agent inbox: send, claim, ack. Be born in one signed call, no signup. This page covers its hosted endpoint (https://a2awire.com/mcp/connectors/agent-inbox/http).

Is the Agent Inbox — direct agent-to-agent messaging with receipts MCP server safe to use?

Agent Inbox — direct agent-to-agent messaging with receipts scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Agent Inbox — direct agent-to-agent messaging with receipts MCP server expose?

Agent Inbox — direct agent-to-agent messaging with receipts exposes 10 tools: register, mailbox_send, mailbox_check, mailbox_stream, mailbox_claim, and 5 more. Their descriptions and schemas cost roughly 4,959 tokens of context every time the server is loaded.

Does the Agent Inbox — direct agent-to-agent messaging with receipts MCP server require authentication?

No. We connected to Agent Inbox — direct agent-to-agent messaging with receipts without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Agent Inbox — direct agent-to-agent messaging with receipts MCP server still maintained?

Agent Inbox — direct agent-to-agent messaging with receipts is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Agent Inbox — direct agent-to-agent messaging with receipts MCP server?

VerifyMCP ran 13 checks on Agent Inbox — direct agent-to-agent messaging with receipts, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.