MailFlat
PYPI · MAILFLAT-MCP · SCANNED SEP 20
Real email inboxes for AI agents: open an address, read the one-time code, send mail.
Available components
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 Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 0 of 30 dependencies flagged as unhealthy. View diagnostics → Pass
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 23 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 986 tokens (~82/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 Management80
- Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_email" 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
How do I install the MailFlat MCP server?
MailFlat runs locally as a PyPI package, launched with uvx mailflat-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · mailflat-mcp
claude mcp add mailflat-mailflat-mcp -- uvx mailflat-mcp
{
"mcpServers": {
"mailflat-mailflat-mcp": {
"command": "uvx",
"args": [
"mailflat-mcp"
]
}
}
} {
"servers": {
"mailflat-mailflat-mcp": {
"command": "uvx",
"args": [
"mailflat-mcp"
]
}
}
} codex mcp add mailflat-mailflat-mcp -- uvx mailflat-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mailflat-mailflat-mcp": {
"type": "local",
"command": [
"uvx",
"mailflat-mcp"
],
"enabled": true
}
}
} openclaw mcp add mailflat-mailflat-mcp --command uvx --arg mailflat-mcp
mcp_servers:
mailflat-mailflat-mcp:
command: "uvx"
args: ["mailflat-mcp"] {
"McpServers": {
"mailflat-mailflat-mcp": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"mailflat-mcp"
]
}
}
} assistant mcp add mailflat-mailflat-mcp -t stdio -c uvx -a mailflat-mcp
{
"mcpServers": {
"mailflat-mailflat-mcp": {
"command": "uvx",
"args": [
"mailflat-mcp"
]
}
}
} 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.
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 14 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 8 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 6 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
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 20 Sept 2026 · Analysed pypi/mailflat-mcp@0.9.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 30 packages
| Packages resolved | 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 →
burn_inbox ~41
Delete every message in an inbox but KEEP the address. Use between scenarios: the address stays registered wherever you already used it.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | – |
No output schema declared.
No examples provided.
create_inbox ~148
Open an email inbox and return its address. Use this when you need an address to sign up for a service or to receive a one-time code. The address is permanent and stays until you delete it, so a test suite can reuse one address across runs instead of opening a new inbox each time. Only the messages inside expire, on the retention window you choose. `label` needs a paid plan; on free it is reported back in `ignored_fields`. `retention_hours` is optional (0 = your plan's max); requests above your plan are capped.
| Name | Type | Req | Description |
|---|---|---|---|
| label | string | – | – |
| prefix | string | – | – |
| retention_hours | integer | – | – |
No output schema declared.
No examples provided.
delete_inbox ~30
Delete an inbox and all its messages by address. Irreversible.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | – |
No output schema declared.
No examples provided.
delete_message ~39
Delete a single message in an inbox by its id (the inbox itself stays).
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | – |
| message_id | integer | yes | – |
No output schema declared.
No examples provided.
list_inboxes ~19
List all inboxes available to this API key.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
mark_read ~35
Mark one message as read so later polls can skip it.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | – |
| message_id | integer | yes | – |
No output schema declared.
No examples provided.
read_messages ~89
Read messages in the given inbox address (newest first). `direction` is "in" for received mail (default), "out" for mail sent from this address, or "all" for both. Received mail is the default so that a reply you are waiting for is not confused with a message you just sent.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | – |
| direction | string | – | – |
No output schema declared.
No examples provided.
reply ~107
Reply to a message so it stays in the SAME conversation. Prefer this over send_email when answering: it fills in the recipient, an `Re:` subject and the threading headers. A plain send_email starts a new conversation in the recipient's client, which does not look like a reply.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | – |
| bcc | – | – | – |
| body | string | – | – |
| cc | – | – | – |
| html | string | – | – |
| message_id | integer | yes | – |
No output schema declared.
No examples provided.
send_email ~161
Send an email FROM the given inbox address (DKIM-signed via MailFlat's MTA). Use for replies or outbound automation. `html` is optional. Returns once the mail is ACCEPTED for delivery, not once it is delivered: delivery runs on a queue and the result arrives via webhook or by reading the message back. `cc` addresses appear in the mail's headers; `bcc` addresses never do — not even in their own copy. Attachments are not available here; send those from the SDK.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | – |
| bcc | – | – | – |
| body | string | – | – |
| cc | – | – | – |
| html | string | – | – |
| subject | string | – | – |
| to | string | yes | – |
No output schema declared.
No examples provided.
wait_for_message ~67
Poll the inbox until a new message ARRIVES (or timeout). Returns {email}. Only received mail counts, so you can send to a peer and then wait for their reply without matching your own outgoing message.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | – |
| timeout | integer | – | – |
No output schema declared.
No examples provided.
wait_for_otp ~43
Poll the inbox until an OTP code arrives (or timeout). Returns {otp_code, email}.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | – |
| timeout | integer | – | – |
No output schema declared.
No examples provided.
wait_until_sent ~207
Find out whether a mail you sent was actually delivered. send_email only means "accepted for delivery"; the mail goes out later on a queue. Call this with the message_id send_email returned to learn the outcome. Returns `delivered: true` once it went out. If it is still queued when the timeout elapses you get `timed_out: true` with `delivered: false` — that is NOT a failure and you must NOT send the mail again; the queue is still retrying. `status` tells you whether it has been attempted yet (`queued`) or attempted and rescheduled (`retrying`), and `error` carries what the last attempt reported. Permanent failure comes back the same way, as `status: failed` with the reason in `error` — read `note` before you resend anything.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | – |
| message_id | integer | yes | – |
| timeout | integer | – | – |
No output schema declared.
No examples provided.
What is the MailFlat MCP server?
MailFlat is an MCP server listed in the public MCP registry as io.github.MailFlat/mailflat-mcp. Real email inboxes for AI agents: open an address, read the one-time code, send mail. This page covers its PyPI package (mailflat-mcp).
Is the MailFlat MCP server safe to use?
MailFlat scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 MailFlat MCP server expose?
MailFlat exposes 12 tools: create_inbox, list_inboxes, read_messages, wait_for_otp, wait_for_message, and 7 more. Their descriptions and schemas cost roughly 986 tokens of context every time the server is loaded.
Is the MailFlat MCP server still maintained?
MailFlat is still listed as active in the MCP registry. We last reached this channel on 20 September 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 MailFlat MCP server under?
MailFlat declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.