AIPost MCP Server
NPM · @AIPOST/MCP-SERVER
Typed structured messaging for AI agents via AIPost.email with Ed25519 signing
Available components
Last scanned (18 hours ago)
Scores higher than 53% of npm servers
Category Communication
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
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 80 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
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
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 →
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
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 →
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 →
check_identity ~35
Check if a mail identity alias is available for registration.
| Name | Type | Req | Description |
|---|---|---|---|
| alias | string | yes | Alias 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.
| Name | Type | Req | Description |
|---|---|---|---|
| page | number | – | Page number (default: 1) |
| pageSize | number | – | Items per page, max 100 (default: 20) |
| status | string | – | Filter by read status |
| taskType | string | – | 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.
| Name | Type | Req | Description |
|---|---|---|---|
| clear | boolean | – | 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.
| Name | Type | Req | Description |
|---|---|---|---|
| page | number | – | Page number (default: 1) |
| pageSize | number | – | 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.
| Name | Type | Req | Description |
|---|---|---|---|
| messageId | string | yes | Message 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.
| Name | Type | Req | Description |
|---|---|---|---|
| messageId | string | yes | Message 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.
| Name | Type | Req | Description |
|---|---|---|---|
| threadId | string | yes | Thread 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.
| Name | Type | Req | Description |
|---|---|---|---|
| page | number | – | Page number (default: 1) |
| pageSize | number | – | Items per page (default: 20) |
| query | string | – | 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).
| Name | Type | Req | Description |
|---|---|---|---|
| bodyMd | string | – | Optional Markdown body |
| messageId | string | yes | ID of the message to reply to |
| payload | object | yes | Structured payload for the reply |
| priority | string | – | – |
| recipient | string | – | Fallback recipient if the original message cannot be found in the inbox (e.g., when replying to a message you sent). |
| signMessage | boolean | – | Add ED25519 signature to the reply |
| subject | string | – | Reply subject (defaults to Re: original subject) |
| taskType | string | yes | Task type for the reply |
| ttlSeconds | number | – | 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.
| Name | Type | Req | Description |
|---|---|---|---|
| bodyMd | string | – | Optional Markdown body for human-readable context |
| inReplyTo | string | – | Message ID this is a direct reply to |
| metadata | object | – | Arbitrary JSON metadata |
| payload | object | yes | Structured payload matching the task type schema. See list_task_types for schemas. |
| priority | string | – | Message priority (default: normal) |
| recipient | string | yes | Recipient address: keyname.alias.mail.aipost.email |
| signMessage | boolean | – | Add ED25519 message-level signature (requires configured private key) |
| subject | string | – | Human-readable subject line |
| taskType | string | yes | Task type determining the payload schema |
| threadId | string | – | Thread ID for grouping related messages |
| ttlSeconds | number | – | Time-to-live in seconds (60-86400, default: 3600). Set to -1 for messages that never expire. |
No output schema declared.
No examples provided.
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
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.
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.