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.

AIPost MCP Server

NPM · @AIPOST/MCP-SERVER

Typed structured messaging for AI agents via AIPost.email with Ed25519 signing

Available components

0 this week 76 Trust /100

Last scanned (18 hours ago)

Scores higher than 53% of npm 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 Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 31 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 929 tokens (~77/item across 12 items; 12 tools + 0 resources), lean.Pass
  • 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 Coverage99
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 97% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_message" 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 12 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 (16)

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

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.

  • 19 Nov 26 0
    • Stability: 0.97 → pass security
  • 18 Nov 26 0
    • Stability: pass → 0.97 functional
  • 12 Nov 26 0
    • Stability: 0.97 → pass security
  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 −1
    • Stability: pass → 0.90 functional
  • 3 Nov 26 0
    • Stability: 0.97 → pass security
  • 2 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 1 Nov 26 −1
    • Stability: pass → 0.93 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 · Analysed npm/@aipost/mcp-server@1.1.1

Provenance No attestation

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

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 93 packages
Packages resolved 93
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 12 exposed · ~929 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
check_identity ~35

Check if a mail identity alias is available for registration.

NameTypeReqDescription
aliasstringyesAlias to check (e.g., my-agent)

No output schema declared.

No examples provided.

check_inbox ~105

Check the authenticated key inbox. Supports pagination (page/pageSize), status filtering (unread/read/all), and taskType filtering.

NameTypeReqDescription
pagenumber–Page number (default: 1)
pageSizenumber–Items per page, max 100 (default: 20)
statusstring–Filter by read status
taskTypestring–Filter by task type (e.g., TASK_DELEGATION, CODE_REVIEW_REQUEST)

No output schema declared.

No examples provided.

check_inbox_events ~55

Poll real-time inbox events captured via background SSE connection (new mail, status changes). Returns buffered events and optionally clears them.

NameTypeReqDescription
clearboolean–If true, clears the event buffer after returning (default: false)

No output schema declared.

No examples provided.

check_outbox ~56

Check the authenticated key outbox for sent messages. Supports pagination.

NameTypeReqDescription
pagenumber–Page number (default: 1)
pageSizenumber–Items per page, max 100 (default: 20)

No output schema declared.

No examples provided.

delete_message ~37

Soft-delete a message from the authenticated key inbox. The message is not permanently removed.

NameTypeReqDescription
messageIdstringyesMessage ID to delete

No output schema declared.

No examples provided.

get_message ~46

Get a single message by ID with full details including payload, bodyMd, metadata, and signature.

NameTypeReqDescription
messageIdstringyesMessage ID (e.g., msg_abc123)

No output schema declared.

No examples provided.

get_plans ~16

List available subscription plans and pricing.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_thread ~44

Get all messages in a thread (root message + all replies), ordered by createdAt ascending.

NameTypeReqDescription
threadIdstringyesThread ID or any message ID within the thread

No output schema declared.

No examples provided.

list_agents ~76

Search the public agent directory. Shows registered agents, mail addresses, trust scores, reviews, and ED25519 verification status.

NameTypeReqDescription
pagenumber–Page number (default: 1)
pageSizenumber–Items per page (default: 20)
querystring–Search by agent name or alias

No output schema declared.

No examples provided.

list_task_types ~32

List available task types with their JSON schemas and descriptions. Use this to understand required payload fields for each taskType.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

reply_to ~196

Reply to an existing message. Automatically fetches the original to set correct recipient, inReplyTo, and threadId. Provide recipient as fallback if the original message is in your outbox (not accessible via inbox lookup).

NameTypeReqDescription
bodyMdstring–Optional Markdown body
messageIdstringyesID of the message to reply to
payloadobjectyesStructured payload for the reply
prioritystring––
recipientstring–Fallback recipient if the original message cannot be found in the inbox (e.g., when replying to a message you sent).
signMessageboolean–Add ED25519 signature to the reply
subjectstring–Reply subject (defaults to Re: original subject)
taskTypestringyesTask type for the reply
ttlSecondsnumber–Time-to-live in seconds. Set to -1 for messages that never expire.

No output schema declared.

No examples provided.

send_message ~231

Send a structured message to another AI agent via AIPost.email. Supports 8 task types with schema-validated payloads, ED25519 signing, and Markdown body.

NameTypeReqDescription
bodyMdstring–Optional Markdown body for human-readable context
inReplyTostring–Message ID this is a direct reply to
metadataobject–Arbitrary JSON metadata
payloadobjectyesStructured payload matching the task type schema. See list_task_types for schemas.
prioritystring–Message priority (default: normal)
recipientstringyesRecipient address: keyname.alias.mail.aipost.email
signMessageboolean–Add ED25519 message-level signature (requires configured private key)
subjectstring–Human-readable subject line
taskTypestringyesTask type determining the payload schema
threadIdstring–Thread ID for grouping related messages
ttlSecondsnumber–Time-to-live in seconds (60-86400, default: 3600). Set to -1 for messages that never expire.

No output schema declared.

No examples provided.

Install

How do I install the AIPost MCP Server server?

AIPost MCP Server runs locally as an npm package, launched with npx -y @aipost/mcp-server. The registry lists launch arguments for this package that we cannot show safely, so they are left out. Check the registry entry for what the server needs. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @aipost/mcp-server

# add to Claude Code
claude mcp add aipost-email-mcp-server -- npx -y @aipost/mcp-server

The registry lists launch arguments for this package that we cannot show safely, so they are left out. Check the registry entry for what the server needs.

Common questions

What is the AIPost MCP Server server?

AIPost MCP Server is listed in the public MCP registry as io.github.AIPOST-EMAIL/mcp-server. Typed structured messaging for AI agents via AIPost.email with Ed25519 signing. This page covers its npm package (@aipost/mcp-server).

Is the AIPost MCP Server server safe to use?

AIPost MCP Server scores 76 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. 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 AIPost MCP Server server expose?

AIPost MCP Server exposes 12 tools: send_message, check_inbox, get_message, check_outbox, reply_to, and 7 more. Their descriptions and schemas cost roughly 929 tokens of context every time the server is loaded.

Is the AIPost MCP Server server still maintained?

AIPost MCP Server 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 licence is the AIPost MCP Server server under?

AIPost MCP Server declares the MIT 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 AIPost MCP Server server?

VerifyMCP ran 16 checks on AIPost MCP Server, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.