Agent Relay
NPM · @ARELAY/CLI
End-to-end encrypted inbox where AI agents deliver files and request human approval.
Available components
Last scanned (4 hours ago)
Scores higher than 65% 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
- 30 of 94 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- 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 91 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability76
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 579 tokens (~144/item across 4 items; 4 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
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 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
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.
- 31 Oct 26 +1
- Stability: 0.97 → pass security
- 30 Oct 26 −1
- Stability: pass → 0.97 functional
- 24 Oct 26 −4
- CVE-2023-54404 affects this package: high ▼ security
- Known CVEs: pass → fail ▼ security
- Stability: 0.97 → pass security
- 23 Oct 26 −1
- Stability: pass → 0.97 functional
- 17 Oct 26 +1
- Stability: 0.97 → pass security
- 15 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Oct 26 +1
- Security disclosure: unverified → pass ▲ 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 5 Nov 2026 · Analysed npm/@arelay/cli@0.2.0
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 94 packages
| Packages resolved | 94 |
|---|---|
| Stale | 30 |
| 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 →
deliver_to_inbox Deliver files to the Agent Relay inbox ~119
Deliver finished work (reports, files, artifacts) to the human's end-to-end encrypted Agent Relay inbox. Creates a new session unless session_id is given. Use this when work is complete and a human should receive the result.
| Name | Type | Req | Description |
|---|---|---|---|
| files | array | yes | Files to deliver. |
| session_id | string | – | Existing session id to add files to instead of creating a new session. |
| summary | string | – | One or two sentences on what was delivered and why. |
| title | string | yes | Short human-readable title for the delivery session. |
No output schema declared.
No examples provided.
list_inbox_sessions List inbox sessions ~39
List delivery sessions in the Agent Relay inbox (ids, timestamps, read state). Titles are end-to-end encrypted and cannot be read by agents.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
submit_email_draft Submit an email draft for human review ~236
Submit an outbound email draft to the Agent Relay inbox for human approval before it is sent (requires the Email Review Relay plugin, enabled on arelay.app). Nothing is sent until the human approves.
| Name | Type | Req | Description |
|---|---|---|---|
| bcc | string | – | BCC email address (e.g. to keep a copy for the sender). |
| cc | string | – | CC email address. |
| from_email | string | yes | Sender email address (must be one the account can send from). |
| from_name | string | – | Sender display name. |
| html | string | yes | HTML body of the email. |
| idempotency_key | string | – | Stable key so retries return the existing draft instead of creating duplicates. |
| inline_images | array | – | On-disk images to inline into the html body. Each replaces a <img src="cid:CID"> reference with its base64 data URI (delivered as a CID inline attachment), so you pass a file path instead of embeddin… |
| subject | string | yes | Email subject. |
| text | string | – | Plain-text body. |
| to | string | yes | Recipient email address. |
No output schema declared.
No examples provided.
submit_spend_request Submit a spend request for human approval ~185
Propose a payment or purchase to the human's Agent Relay inbox for approval before any money moves (requires the Spend Review Relay plugin). Nothing is charged until the human approves; on approval a Stripe PaymentIntent is created in the account's Stripe (test) mode. Use this whenever an autonomous action would spend money.
| Name | Type | Req | Description |
|---|---|---|---|
| amount_minor | integer | yes | Amount in the smallest currency unit (cents for USD). $49.00 = 4900. |
| currency | string | yes | Three-letter ISO currency code, e.g. "usd". |
| description | string | yes | Why this spend is needed — shown to the human reviewer. |
| idempotency_key | string | – | Stable key so retries return the existing request instead of duplicating. |
| payee | string | yes | Who is being paid or what is being purchased, e.g. "OpenAI API credits". |
No output schema declared.
No examples provided.
How do I install the Agent Relay MCP server?
Agent Relay runs locally as an npm package, launched with npx -y @arelay/cli. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @arelay/cli
claude mcp add mmmikael-arelay -- npx -y @arelay/cli
What is the Agent Relay MCP server?
Agent Relay is an MCP server listed in the public MCP registry as io.github.mmmikael/arelay. End-to-end encrypted inbox where AI agents deliver files and request human approval. This page covers its npm package (@arelay/cli).
Is the Agent Relay MCP server safe to use?
Agent Relay scores 80 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 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 Agent Relay MCP server expose?
Agent Relay exposes 4 tools: deliver_to_inbox, list_inbox_sessions, submit_email_draft, submit_spend_request. Their descriptions and schemas cost roughly 579 tokens of context every time the server is loaded.
Is the Agent Relay MCP server still maintained?
Agent Relay is still listed as active in the MCP registry. We last reached this channel on 5 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 Agent Relay MCP server under?
Agent Relay declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.