Skip to main content
Glama

Server Details

Paid replay-safe callback inboxes for asynchronous agent tasks with structured MCP results.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
63.6% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2026-07-28
URL
ChatGPT
–
Claude
–

TDQS

A4/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no possibility of tool-to-tool confusion. Its purpose—provisioning an A2A callback mailbox—is stated unambiguously.

Naming Consistency5/5

The single name follows a clear verb_noun snake_case convention (create_a2a_callback_mailbox). With one tool there is no inconsistency, and the name reads predictably.

Tool Count3/5

The surface is extremely thin: one tool that bundles creation, message retention, deduplication, cursor retrieval, and lifetime configuration into a single opaque call. It is defensible for a narrowly scoped provisioning service, but leaves no granular operations for an agent to compose.

Completeness3/5

Creation is covered, but there is no exposed way to fetch messages by cursor, check mailbox status, or tear down/expire a mailbox early—essential steps for the suspend/resume workflow the tool advertises. Agents must rely on out-of-band HTTP access for the read side, which is a notable gap.

Available Tools

1 tool
create_a2a_callback_mailboxTemporary Authenticated A2A Callback InboxAInspect

Create a temporary private authenticated webhook inbox for asynchronous A2A task completion. Let an expensive reasoning agent suspend instead of spending model calls polling for completion; a lightweight worker can receive and persist the callback, then resume the agent when useful data exists. One payment includes up to 1,000 ordered callback messages, replay-safe deduplication, cursor retrieval, a configurable 1-minute to 24-hour lifetime, and up to 4 MiB storage.

Inputs: expectedTaskId (required), ingressCredential (required), retrievalCredential (required), maxBytes, +2 more. Returns: max_bytes, expires_at, mailbox_id, max_events, +2 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables two AI agents to share a persistent task mailbox over remote MCP, so one can leave work, the other can claim and complete it, and results are written back with optional webhook wake-ups.
      3,505 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables coding agents such as Codex and Claude Code to exchange durable, locally stored messages through shared MCP tools for listing enrolled recipients, sending and replying to messages, reading pending inbox items, acknowledging receipt, and checking message status. Delivery uses each runtime's native session interface, so messages persist across broker restarts without resuming or launching conversations.
      AGPL 3.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables agents to communicate asynchronously via private inboxes and to ask a human a question and block until answered. Provides MCP tools for sending messages, checking unread messages, and listing peers.
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Provides asynchronous messaging infrastructure for AI agents, enabling them to get permanent addresses and send/receive encrypted messages via MCP tools.
      1
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources