# @mailsai/mcp-server

A real inbox for AI agents: send, receive and thread email, behind a prompt-injection firewall.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the package rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.2.9
- **Author:** io.github.RolloutsAI
- **License:** MIT
- **npm:** @mailsai/mcp-server
- **Source:** https://mails.ai
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

60/100 (B), scored on the package rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 18 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-05T12:52:58.528Z
- **Version scanned:** 0.2.9
- **CVEs:** none found by OSV at scan time

## Tools

20 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `mails.send` — Send an email. `agent` is OPTIONAL: omit it and the workspace's single agent is used, or one is created for you (named from `from`) — so a first send needs no s
- `mails.reply` — Reply to a previously-received message. Sets In-Reply-To + Re: subject server-side.
- `mails.forward` — Forward a message to new recipients.
- `mails.list_threads` — List threads (conversations) for the workspace or a specific agent.
- `mails.get_thread` — Get a full thread with all messages in chronological order.
- `mails.list_received` — List recently received messages.
- `mails.get_received` — Get one received message including extracted reply text.
- `mails.list_agents` — List the agents in the workspace. Returns SENDABLE agents by default (status=live); archived agents cannot send, so they are excluded unless you ask for them. P
- `mails.create_agent` — Create a new agent.
- `mails.list_replies` — List recent reply events (reply.received) for an agent.
- `mails.list_messages` — List recent cold/first-contact inbound (message.received) for an agent — senders that are NOT replying to one of your sends.
- `mails.get_event` — Get a specific inbound event by ID.
- `mails.get_reputation` — Get an agent's sending-reputation health (0-1) + its 30-day bounce/complaint/reply counts. The firewall auto-suspends an agent that crosses a 0.3% complaint rat
- `mails.check_suppression` — Check if an address is suppressed.
- `mails.allowlist_address` — Override suppression for one address with a >=20 char attestation.
- `mails.create_draft` — Stage a draft. Optionally pass send_at to schedule.
- `mails.send_draft` — Send a previously-created draft.
- `mails.get_usage` — Get the current billing period usage.
- `mails.me` — Who am I — returns the authenticated workspace, agent, tier, and API-key scopes. Call this first to confirm the connection is live.
- `mails.test_inbound`

## Install

**Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for.
**Cautions** (coverage gaps and advisories — never blocking)
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"mcp-server\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@mailsai/mcp-server\"\n      ],\n      \"env\": {\n        \"MAILS_API_KEY\": \"<YOUR_MAILS_API_KEY>\"\n      }\n    }\n  }\n}"
```
**Credentials it will ask for** (names only — Forge never holds a value):
- `MAILS_API_KEY` — Mails API Key (required)
Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each <YOUR_NAME> in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one.
- This entry needs 1 credential (1 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset.

## Blast radius

Moderate blast radius — holds an api key; runs on your machine.
- Floor 23, ceiling 23 (tier: moderate)
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40mailsai%2Fmcp-server
- Install plan: https://forgeregistry.com/api/v1/packages/%40mailsai%2Fmcp-server/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40mailsai%2Fmcp-server
- HTML page: https://forgeregistry.com/registry/%40mailsai%2Fmcp-server
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.