MCP servers › io.github.voidly-ai › mcp-email
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
io.github.voidly-ai/mcp-email
Local MCP tools for server-readable agent inboxes and sending to owner-approved recipients. — the publisher's description
Summary
io.github.voidly-ai/mcp-email is a local MCP server listed in the official MCP registry at version 2.1.1. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 21 tools, 3 resources and 0 prompts.
Record checks
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- met: Repository publishes a security policy (SECURITY.md)
- met: Package names its licence with a standard (SPDX) identifier
- met: The version the registry lists can be installed and is not withdrawn
- not met: npm package carries build provenance (attestation)
- met: No known critical or high advisory in the package or its dependencies
- #1,405 of 15,112 packages by monthly downloads
- Not ranked by stars: 0 stars (ranked from 10)
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Key facts
- Runs
- local package
- Transport
- standard input/output
- Package
- npm · listed version current
- License
- MIT
- Dependencies
- no known high or critical advisories
- Repository
- public
- Tools
- 21
- Described as changing data
- 11 of 21 toolsAI-classified
- Mainly works on
- email, chat or social accountsAI-classified
- Topic
- communication-and-socialAI-classified
- Last tested
- 2026-10-23
Worth knowing before you connect it
- 11 tools are described as changing something (voidmail_create_account, voidmail_read_email, voidmail_send_email, …): our AI model's reading of the descriptions, not something we tested. We did not call them.
Each line comes from a section below, with its source and date.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-23
- Mode
- read-only (no tool calls)
- Latest version
- 2.1.1, published 2026-10-16 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-05 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 5 versions listed, 2026-10-05 to 2026-10-16; 5 in the 90 days before the 2026-10-23 snapshot.(versions still listed in the registry only)
Most recent 5 versions
2.1.1· 2026-10-162.1.0· 2026-10-162.0.2· 2026-10-152.0.1· 2026-10-141.2.1· 2026-10-05
- Registry data
- snapshot 2026-10-23
- Package and repository
- checked 2026-10-23
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Changes since the last refresh
New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 2.1.1 (published 2026-10-16).
Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.
What it is
What does this server offer?
Observed inventoryWhat it mainly works on, as our AI model read its tool descriptions: email, chat or social accounts.
11 of 21 tools are described as changing something (creating, editing, deleting, sending or running).
- voidmail_create_accountcreates or changes datadescribed as changing data
“Create a new @voidmail.ai inbox.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs
namestring“Agent name (optional)”addressstring“Preferred local part, for example myagent; the exact myagent@voidmail.ai address is also accepted.”
- voidmail_account_inforeads or searches
“Get information about the current agent email account, including whether a mail encryption key for it is on this machine.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
“List emails in the agent inbox.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs
limitinteger“Max emails to return (default 50, max 100)”offsetinteger“Pagination offset”unreadboolean“Only return unread emails”categorystring“Filter by category”
“Read a specific email by ID and mark it as read.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
1 input, 1 required
email_idstringrequired“Email ID to read”
- voidmail_search_inboxreads or searches
“Search emails by keyword on this machine.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs, 1 required
querystringrequired“Nonempty search query (case-insensitive substring; surrounding spaces are ignored)”limitinteger“Max results (default 20, max 100)”scaninteger“How many of the newest messages to search (default 200, max 1000)”full_textboolean“Also download and search whole encrypted bodies (slower; downloads stop after about 64 MiB per search)”
- voidmail_wait_for_emailreads or searches
“Wait up to 25 seconds for a new email, such as a sign-up verification message.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs
fromstring“Exact sender address (case-insensitive)”subjectstring“Text the subject must contain (case-insensitive)”sincestring“Only messages received at or after this ISO UTC time, for example 2026-10-16T12:00:00Z”timeout_secondsinteger“Maximum wait, 1-25 seconds (default 25)”
- voidmail_extract_codereads or searches
“Find a likely one-time code and HTTPS verification link in one email: the message with email_id, or else the newest message matching the optional filters (exact sender, subject contains, received sin…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs
email_idstring“Message id from voidmail_wait_for_email or voidmail_list_inbox”fromstring“Exact sender address (case-insensitive)”subjectstring“Text the subject must contain (case-insensitive)”sincestring“Only messages received at or after this ISO UTC time, for example 2026-10-16T12:00:00Z”
“Read sending limits before planning email work.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
- voidmail_send_emailsends messagesdescribed as changing data
“Legacy send without durable status.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs, 2 required
tostringrequired“Recipient email address”subjectstringrequired“Email subject”textstring“Plain text body”htmlstring“HTML body (optional)”
“Preferred send: one message bound to a stable operation ID saved by the host before this call.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
6 inputs, 3 required
operationIdstringrequired“Stable ID generated and saved by the host before dispatch.”tostringrequiredsubjectstringrequiredtextstringhtmlstringreplyTostring
“Read a retained send operation owned by this mailbox.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
operationIdstringrequired“Stable ID generated and saved by the host before dispatch.”
- voidmail_policyreads or searches
“Read this mailbox's sending policy: recipient policy (open or allowlist), content policy, approved recipients and pending approval requests.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
Show 9 more tools
- voidmail_request_recipientcreates or changes datadescribed as changing data
“Ask the human mailbox owner to approve one recipient address.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
1 input, 1 required
recipientstringrequired“Exact recipient email address to request”
- voidmail_revoke_recipientdeletesdescribed as changing data
“Remove an approved recipient (exact address or @domain) from this mailbox.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
1 input, 1 required
patternstringrequired“Exact address or @domain to revoke”
- voidmail_mark_readcreates or changes datadescribed as changing data
“Mark an email as read.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
1 input, 1 required
email_idstringrequired“Email ID to mark as read”
- voidmail_delete_emaildeletesdescribed as changing data
“Delete an email from the inbox.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
1 input, 1 required
email_idstringrequired“Email ID to delete”
- voidmail_create_aliascreates or changes datadescribed as changing data
“Create a disposable email alias that routes to this agent's inbox.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input
namestring“Alias name (random if not specified)”
- voidmail_list_aliasesreads or searches
“List all email aliases for this agent.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
- voidmail_delete_aliasdeletesdescribed as changing data
“Delete an email alias.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
1 input, 1 required
aliasstringrequired“Alias to delete (without @voidmail.ai)”
- voidmail_set_webhookcreates or changes datadescribed as changing data
“Set a webhook URL to get notified when new email arrives on an open-policy inbox that has no owner key.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
2 inputs, 1 required
urlstringrequired“HTTPS webhook URL”secretstring“Signing secret for the X-Voidmail-Signature-256 HMAC header, at least 32 characters (server-generated if omitted)”
- voidmail_get_statsreads or searches
“Get inbox statistics — total emails, unread count, storage used.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
- Says what the tool does
- 100% of 21 tools
- Says what it returns
- 60% of 20 tools
- States limits, defaults or errors
- 15% of 20 tools
- Says when to use it
- 0% of 21 tools
- Items covered per tool
- 1.7 of 4 on average
Counted from the listing
- Parameters with a description
- 87% of 38
- Tools with a description
- 100% of 21
- Typical description length
- 241 characters
The tool set
Counted from the listing
- Tools
- 21
- Size of the list
- about 3,892 tokens for an agent to load (characters ÷ 4)
- Naming
- 21 of 21 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 21 of 21 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the npm package @voidly/mcp-email
Our sandbox started this package on 2026-10-23 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below. The command runs the publisher’s code on your machine.
Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)
{
"mcpServers": {
"mcp-email": {
"command": "npx",
"args": [
"-y",
"@voidly/mcp-email@2.1.1"
]
}
}
}Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"mcp-email": {
"command": "npx",
"args": [
"-y",
"@voidly/mcp-email@2.1.1"
]
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"mcp-email": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@voidly/mcp-email@2.1.1"
]
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"mcp-email","type":"stdio","command":"npx","args":["-y","@voidly/mcp-email@2.1.1"]}'Claude Code
claude mcp add --transport stdio mcp-email -- npx -y @voidly/mcp-email@2.1.1
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 -- npx -y @voidly/mcp-email@2.1.1
- This runs the publisher's code on your machine (npx). Read its README first.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
Can it be installed, and is it up to date?
Version pin · advisories
Listed version
- Registry lists
- 2.1.1
- Latest stable
- 2.1.1
- Status
- current
- Withdrawn
- no
Source: registry.npmjs.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.
Dependency advisories
Counted in the full dependency tree as resolved on 2026-10-23 (npm audit). Bars share one scale. The package itself has no known vulnerability (OSV.dev).
Integrity, provenance, license
- Integrity
- sha512-g6aMVFw7ITA26YAix…
- Signature
- signed
- License
- MIT
Source: the package registry · 2026-10-23.
Usage
- Downloads
- 1,724 in the last month
Source: api.npmjs.org · 2026-10-23.
Does the registry listing match what we found?
Feature #6The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Published package can be started | Started and answered | matches | our test · 2026-10-23 |
| Version 2.1.1 on npm | Exists and can be installed | matches | npm · 2026-10-23 |
| Repository github.com/voidly-ai/mcp-email | Opens publicly | matches | api.github.com · 2026-10-23 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.voidly-ai · 8 servers
- GitHub owner
- an organization (voidly-ai)
- Build record
- signed
- Repository
- github.com/voidly-ai/mcp-email
- Stars
- 0
- Repository age
- 181–365 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- SECURITY.md
Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.
Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.
Choosing
Record checks
Public records · not a safety rating8 of 9 record checks met
- #1,405 of 15,112 packages by monthly downloads
- Not ranked by stars: 0 stars (ranked from 10)
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- MetSource repository link opensThe linked GitHub repository is public.
- MetRepository is not archivedNot archived.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- MetRepository publishes a security policy (SECURITY.md)SECURITY.md found.
- MetPackage names its licence with a standard (SPDX) identifierMIT
- MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
- Not metnpm package carries build provenance (attestation)Signed by npm, but no build attestation.
- MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards
Common questions about io.github.voidly-ai/mcp-email
Answered from the data aboveIs io.github.voidly-ai/mcp-email safe to install?
We do not rate servers as safe or unsafe. 8 of its 9 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. 11 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Has io.github.voidly-ai/mcp-email been security tested?
Partly. 3 of the 12 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.
What can io.github.voidly-ai/mcp-email do?
It lists 21 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete and send messages. We did not call any tool, so this describes the text, not the behaviour.
Can io.github.voidly-ai/mcp-email change or delete data?
11 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.
Does io.github.voidly-ai/mcp-email publish a security policy?
Yes: its repository has a public security policy (github.com/voidly-ai/mcp-email/blob/HEAD/SECURITY.md). That is the publisher's statement, not permission for us to test the server, and we call none of its tools.
Is the listed version current?
Yes. The registry lists 2.1.1, the latest stable release on npm.
Where is the source code of io.github.voidly-ai/mcp-email?
In github.com/voidly-ai/mcp-email, which opens publicly.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Similar servers
Same topic · AI-read
- io.github.agenticmail/mcpalso has tools that creates or changes data, deletes, reads or searches, sends messagescompare with this one
- io.github.ihuzaifashoukat/x-useX-Use - X (Twitter) MCP Serveralso has tools that creates or changes data, deletes, reads or searches, sends messagescompare with this one
- io.github.nikolausm/imap-mcp-serveralso has tools that creates or changes data, deletes, reads or searches, sends messagescompare with this one
- io.github.mpalermiti/outlook-mcpOutlook MCPalso has tools that creates or changes data, deletes, reads or searches, sends messagescompare with this one
- io.github.parasxos/apple-mail-mcpalso has tools that creates or changes data, deletes, reads or searches, sends messagescompare with this one
- com.mcparmory/mailersendalso has tools that creates or changes data, deletes, reads or searches, sends messagescompare with this one
Active servers whose topic is also “communication-and-social” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Not probed (read-only run)
We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: exercised
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not applicable
- Consent handling: not applicable
- Sign-in metadata: not applicable
3 exercised9 not run (reason given)6 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 12 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 12Hidden content
audience-hidingChecks resources that hide content from the user.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
Source: our own test in an isolated sandbox, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted the published package in an isolated sandbox (read-only mode)
- 5,157 msConnected after 0 redirects.
- Read the inventory: 21 tools, 3 resources, 0 prompts.
- 6,648 msFinished: 3 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “io.github.voidly-ai/mcp-email: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.voidly-ai/mcp-email
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/io.github.voidly-ai/mcp-email)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.
Write to hello@protocolprobe.com · corrections log · methodology