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.

a2a-mailbox

MCPB · A2A-MAILBOX.MCPB

Cross-CLI agent mailbox: tmux-injected messaging for Claude Code, Codex, Pi and ZCode

Available components

39 Trust /100

Last scanned (2 hours ago)

Scores higher than 72% of MCPB servers

Category Communication

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security12
  • No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
  • Known CVEs were checked across the 15 of 15 dependencies we could resolve, so this covers what we could see, not the whole tree.Partial
  • Install-script risk not yet assessed.Unverified
  • 1 of 15 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability67
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 404 tokens (~67/item across 6 items; 6 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "mail_send" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

What we tested

Checks we ran (13)

  • Known CVEs
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (3)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain SecurityNo malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  • Install scripts in Supply Chain SecurityInstall-script risk not yet assessed.
  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

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.

  • 5 Nov 26 39

    First indexed and scored.

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 6 Nov 2026 · Analysed mcpb/https://github.com/RegretSSS/a2a-mailbox/releases/download/v0.1.0/a2a-mailbox.mcpb

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem mcpb
Reason No attestation published

Background: How many MCP packages publish verified provenance →

Dependencies 15 packages
Packages resolved 15
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~404 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
mail_ack ~52

确认一条消息(幂等)。ack_id 用 mail_read 返回的;跨主机传输不可见时自证落盘 self_attested。

NameTypeReqDescription
ack_idstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

mail_group ~137

群组权限五合一。action=join 申请加入对方 group(agent_id=门主,note=来意);action=pending 列自己的待审申请;action=admit 批准 agent_id 可发给自己;action=revoke 移出 agent_id;action=gate 开关仅准入名单收件闸(group_only=true 开,group 为展示名)。错误返回含完整用法。

NameTypeReqDescription
actionstringyes–
agent_idstring––
groupstring––
group_onlyboolean––
notestring––
NameTypeReqDescription
resultstringyes–

No examples provided.

mail_poll ~26

列出自己邮箱待处理消息的摘要(不消费,可反复查)。

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes–

No examples provided.

mail_read ~33

读自己邮箱一条消息全文(含 ack_id——业务确认用)。

NameTypeReqDescription
msg_idstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

mail_send ~84

发消息给另一 agent。in_reply_to 用 mail_read 返回的 msg_id(可自动确认原消息);expect_reply=True 唤醒词尾加『[需回函]』。

NameTypeReqDescription
bodystringyes–
contextstring––
expect_replyboolean––
in_reply_to–––
tostringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

mail_who ~72

列出在册 agent(默认只列在线 active,含同目录分身行 agent_id@session短码 可定向发信;all=true 附已下线 stale)。group-only 标记与成员计数,附联邦 peers 状态。

NameTypeReqDescription
allboolean––
NameTypeReqDescription
resultstringyes–

No examples provided.

Install

How do I install the a2a-mailbox MCP server?

a2a-mailbox ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 3635d09a48c2669f1af8c0d0e32a48b5414099ed162997b6ab35fc956c3f8d5a; the commands to do that are on this page. If it does not match, do not open it.

mcpb · a2a-mailbox.mcpb

Download bundle

Check the download matches the SHA-256 the MCP registry declares before you open it. If it does not match, do not open the file.

SHA-256

3635d09a48c2669f1af8c0d0e32a48b5414099ed162997b6ab35fc956c3f8d5a

macOS / Linux

echo "3635d09a48c2669f1af8c0d0e32a48b5414099ed162997b6ab35fc956c3f8d5a  a2a-mailbox.mcpb" | shasum -a 256 -c

Windows (PowerShell)

(Get-FileHash -Algorithm SHA256 .\a2a-mailbox.mcpb).Hash -eq "3635d09a48c2669f1af8c0d0e32a48b5414099ed162997b6ab35fc956c3f8d5a"

Run it in the folder you saved the bundle to, then open the file with an MCPB-capable host such as Claude Desktop.

Common questions

What is the a2a-mailbox MCP server?

a2a-mailbox is an MCP server listed in the public MCP registry as io.github.RegretSSS/a2a-mailbox. Cross-CLI agent mailbox: tmux-injected messaging for Claude Code, Codex, Pi and ZCode. This page covers its MCPB bundle (https://github.com/RegretSSS/a2a-mailbox/releases/download/v0.1.0/a2a-mailbox.mcpb).

Is the a2a-mailbox MCP server safe to use?

a2a-mailbox scores 39 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 a2a-mailbox MCP server expose?

a2a-mailbox exposes 6 tools: mail_send, mail_poll, mail_read, mail_ack, mail_who, mail_group. Their descriptions and schemas cost roughly 404 tokens of context every time the server is loaded.

What licence is the a2a-mailbox MCP server under?

a2a-mailbox declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the a2a-mailbox MCP server?

VerifyMCP ran 13 checks on a2a-mailbox, covering Known CVEs, Dependency health, Source repository, Provenance and 9 more. 3 items could not be completed, a gap on our side rather than a finding about a2a-mailbox: Malware scan, Install scripts and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an MCPB bundle, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.