Mailcycle
NPM · MAILCYCLE-MCP
An email address for your AI agent. Read, wait for and reply to mail, decrypted on your machine.
Available components
Last scanned (17 minutes ago)
Scores higher than 36% 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 Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency6
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Licence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.Unverified
- Actively maintained (last published 1 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability67
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 672 tokens (~96/item across 7 items; 7 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 Coverage87
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 62% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 7 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
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.
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.
- 15 Oct 26 +29
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Stability: Stability not yet verified: this package installed, but its server did not start, so we have no schema to compare. security
- Tool safety: Tool safety not yet verified: this package installed, but its server did not start, so we have no tool text to scan. security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Schema quality: fail functional
- First check of Tool coverage: 62 functional
- First check of Destructive annotations: 100 functional
- First check of Schema quality: pass functional
- First check of Schema quality: good functional
- Schema quality: Schema quality not yet verified: this package installed, but its server did not start, so we have no schema to assess. functional
- Capabilities: Protocol version not yet verified: this package installed, but its server did not start, so we never saw its MCP handshake. functional
- Tool coverage: Tool coverage not yet verified: this package installed, but its server did not start, so we have no tool definitions to assess. functional
- Package version: 0.6.1 → 0.6.2 functional
- 14 Oct 26 31
First indexed and scored.
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 17 Oct 2026 · Analysed npm/mailcycle-mcp@0.6.2
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 →
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 →
list_addresses List email addresses ~22
This agent's email addresses, and what it is allowed to send.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_messages List messages ~54
The newest messages, newest first, with a short preview of each. Use read_message for the full text.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | Only this address. Leave out for all of them. |
| limit | integer | – | – |
No output schema declared.
No examples provided.
read_attachment Read an attachment ~142
Opens one attachment of a message, by its number in read_message. Text comes back as text and images as images. Anything else, like a PDF, needs save_to: a folder inside the agent's files folder (by default ~/.config/mailcycle/files, or the folders set in MAILCYCLE_FILES_DIR). The file is written there, without overwriting anything, and the path is returned.
| Name | Type | Req | Description |
|---|---|---|---|
| index | integer | yes | The number shown in brackets in read_message, starting at 0. |
| message_id | string | yes | – |
| save_to | string | – | A folder inside the agent's files folder to write the file to, instead of returning it. |
No output schema declared.
No examples provided.
read_message Read a message ~34
One message in full.
| Name | Type | Req | Description |
|---|---|---|---|
| message_id | string | yes | The id from list_messages or wait_for_message, like msg_… |
No output schema declared.
No examples provided.
reply Reply to a message ~143
Replies to the sender of a message, from the address it was sent to, threaded under it. Works in reply-only mode.
| Name | Type | Req | Description |
|---|---|---|---|
| attachments | array | – | Paths of files to attach, inside the agent's files folder only (by default ~/.config/mailcycle/files, or the folders set in MAILCYCLE_FILES_DIR). Up to 10, 3.5 MB between them. Files outside that fol… |
| html | string | – | An HTML version, if wanted. The plain text is always sent too. |
| message_id | string | yes | – |
| text | string | yes | The reply, as plain text. |
No output schema declared.
No examples provided.
send_message Send a message ~151
Sends a new message. Needs the agent to be allowed to send to anyone; in reply-only mode use reply instead.
| Name | Type | Req | Description |
|---|---|---|---|
| attachments | array | – | Paths of files to attach, inside the agent's files folder only (by default ~/.config/mailcycle/files, or the folders set in MAILCYCLE_FILES_DIR). Up to 10, 3.5 MB between them. Files outside that fol… |
| from | string | – | One of this agent's addresses. Can be left out if it has only one. |
| html | string | – | – |
| subject | string | yes | – |
| text | string | yes | – |
| to | string | yes | – |
No output schema declared.
No examples provided.
wait_for_message Wait for a message ~126
Waits for a new message to arrive and returns it in full. Use it right after signing up somewhere to catch a verification code or link. Only mail that arrives after the call starts counts, unless after_message_id is given.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | Only mail to this address. |
| after_message_id | string | – | Count mail after this message instead of from now. |
| from_contains | string | – | Only mail whose sender contains this, like "github.com". |
| subject_contains | string | – | Only mail whose subject contains this. |
| timeout_seconds | integer | – | – |
No output schema declared.
No examples provided.
How do I install the Mailcycle MCP server?
Mailcycle runs locally as an npm package, launched with npx -y mailcycle-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · mailcycle-mcp
claude mcp add email-mailcycle-mailcycle -- npx -y mailcycle-mcp
What is the Mailcycle MCP server?
Mailcycle is an MCP server listed in the public MCP registry as email.mailcycle/mailcycle. An email address for your AI agent. Read, wait for and reply to mail, decrypted on your machine. This page covers its npm package (mailcycle-mcp).
Is the Mailcycle MCP server safe to use?
Mailcycle scores 60 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 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 Mailcycle MCP server expose?
Mailcycle exposes 7 tools: list_addresses, list_messages, read_message, read_attachment, wait_for_message, and 2 more. Their descriptions and schemas cost roughly 672 tokens of context every time the server is loaded.
Is the Mailcycle MCP server still maintained?
Mailcycle is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.