Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Test inboxes for AI agents testing your app: block until the OTP or magic link arrives.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
MAILSOCKET_API_KEY, MAILSOCKET_BASE_URL, AuthorizationValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"mailsocket": {
"command": "uvx",
"args": [
"mailsocket-mcp"
],
"env": {
"MAILSOCKET_API_KEY": "your-value",
"MAILSOCKET_BASE_URL": "your-value"
}
}
}
}Run this in your terminal
claude mcp add --transport http mailsocket https://mcp.mailsocket.app/mcp --header 'Authorization: your-value'claude mcp add mailsocket --env MAILSOCKET_API_KEY=your-value --env MAILSOCKET_BASE_URL=your-value -- uvx mailsocket-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"mailsocket": {
"url": "https://mcp.mailsocket.app/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"mailsocket": {
"command": "uvx",
"args": [
"mailsocket-mcp"
],
"env": {
"MAILSOCKET_API_KEY": "your-value",
"MAILSOCKET_BASE_URL": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"mailsocket": {
"type": "http",
"url": "https://mcp.mailsocket.app/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Paste into .vscode/mcp.json in your project
{
"servers": {
"mailsocket": {
"type": "stdio",
"command": "uvx",
"args": [
"mailsocket-mcp"
],
"env": {
"MAILSOCKET_API_KEY": "your-value",
"MAILSOCKET_BASE_URL": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
MAILSOCKET_BASE_URL envAuthorization secret required HTTP headerThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified against the domain mailsocket.app (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: MAILSOCKET_API_KEY, Authorization
Either way works: install it on your computer or connect to the cloud version.
The GitHub repo last changed –, and the latest version (0.4.2) reached the registry 5 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, Dechonet MCP
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
30 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
An MCP server that exposes mailsocket to AI coding agents as native tools, so an agent can create a per-test inbox and block on the OTP or magic link without writing any polling code. For testing apps you own or are authorized to test. Not for creating accounts on services you don't control.
It wraps the Python SDK — no second HTTP client, no re-implemented polling.
| Tool | What the agent gets |
|---|---|
create_inbox(label?) | a fresh inbox id + address |
wait_for_otp(inbox_id, timeout?=60, min_confidence?=0, since?) | the headline — blocks (bounded: requested deadline clamped to 120s locally, 55s on the remote server) and returns the OTP string + confidence + subject/from/id/received_at. Default since omitted: only messages arriving after this call are matched. |
wait_for_link(inbox_id, timeout?=60, since?) | the extracted magic link (returned, *not* followed) + subject/from/id/received_at. Default since omitted: only messages arriving after this call are matched. |
list_inboxes(limit?, cursor?) | one page of inboxes owned by the key (server default page size 25) + next_cursor/has_more |
list_messages(inbox_id, has_otp?, subject_contains?, sender?, limit?, cursor?) | one page of messages, optionally filtered (server default page size 25) + next_cursor/has_more |
get_latest(inbox_id) | the newest message, without blocking |
send_test_code(inbox_id) | puts one sample OTP email straight into the inbox (no mail server) and returns its message_id + sent_at, so you can check the wait loop without real email. 5 per inbox / 20 per account per hour. |
delete_inbox(inbox_id) | remove an inbox when done |
Errors from the SDK (AuthError / NotFound / RateLimited / WaitTimeout) are turned into clean MCP tool errors — no stack traces, and the API key is never echoed back.
create_inbox needs no since — a fresh inbox only ever has new messages. By default, wait_for_otp/wait_for_link omit since entirely, so the server matches only messages arriving AFTER the call (the request start time). But if you reuse an existing inbox (e.g. to request a second OTP/link), pass since explicitly: otherwise a call with no since will correctly ignore anything already sitting in the inbox, which is right for most reuse, but if you actually WANT to catch a code that already arrived before you called the tool, pass either the time right before you triggered the new email (ISO8601 or unix seconds), or the id of the last message you saw (msg_..., meaning "only messages after that one") — both tools return id/received_at on the matched message so you can chain since= into the next call on that same inbox.
send_test_code does not go through the mail server, so the code is already in the inbox when the tool returns. Take a cutoff first: the id from get_latest (or since=0 if the inbox is empty), or the current time. Then call send_test_code(inbox_id), then wait_for_otp(inbox_id, since= ). Without since the wait only sees mail that arrives during the wait, so it would miss the test code.
POST /api/v1/agents/register.No install needed with uv:
uvx mailsocket-mcp
Or install with pip:
pip install mailsocket-mcp
mailsocket-mcp
Either way, it reads MAILSOCKET_API_KEY (and optional MAILSOCKET_BASE_URL) from the environment. If the key is missing it exits with a clear message and status 2; the key is never logged.
Add this to your client's MCP config file — claude_desktop_config.json for Claude Desktop, ~/.cursor/mcp.json for Cursor:
{
"mcpServers": { "mailsocket": { "command": "uvx", "args": ["mailsocket-mcp"], "env": { "MAILSOCKET_API_KEY": "ms_live_..." } } } }
claude mcp add mailsocket -e MAILSOCKET_API_KEY=ms_live_... -- uvx mailsocket-mcp
Any other MCP-compatible client works the same way: point it at the mailsocket-mcp executable (or uvx mailsocket-mcp) over stdio and pass the key through the environment.
The same tools are hosted at `https://mcp.mailsocket.app/mcp` over Streamable HTTP. Send your key on every request as a header: Authorization: Bearer ms_live_.... Never put the key in the URL; a ?api_key= request is rejected.
claude mcp add --transport http mailsocket https://mcp.mailsocket.app/mcp \
--header "Authorization: Bearer ms_live_..."
~/.cursor/mcp.json){
"mcpServers": { "mailsocket": { "url": "https://mcp.mailsocket.app/mcp", "headers": { "Authorization": "Bearer ms_live_..." } } } }
.vscode/mcp.json){
"servers": { "mailsocket": { "type": "http", "url": "https://mcp.mailsocket.app/mcp", "headers": { "Authorization": "Bearer ms_live_..." } } } }
Any client that can set a custom HTTP header works the same way (OpenAI Agents SDK, the n8n MCP Client node, your own code).
Things to know:
wait_for_otp / wait_for_link wait at most 55s per call, which keeps each response under proxy timeouts. On a timeout, call the tool again.mailsocket-mcp-http runs the same server (see mailsocket_mcp/remote.py for its env vars).| Variable | Required | Description |
|---|---|---|
MAILSOCKET_API_KEY | yes (secret) | Your mailsocket API key (ms_live_...). |
MAILSOCKET_BASE_URL | no | Override the API base URL. Defaults to https://dash.mailsocket.app/api/v1. |
pip install -e ".[dev]"
pytest
Tests make no external or live-API requests. The SDK client is faked, and the remote-transport tests talk to a local fake upstream on 127.0.0.1.
mailsocket>=0.3.1: wait_for_otp / wait_for_link called without since no longer miss a message that lands between the SDK's internal long-poll calls (each follow-up call sends the cutoff the server reported in Mailsocket-Wait-Since). No tool signature changes.send_test_code(inbox_id) tool (stdio and the hosted remote server, under the same per-key caps as the other non-wait tools): puts one sample OTP email into your own inbox without going through the mail server. Requires mailsocket>=0.3.0 (Client.send_test_code).mailsocket>=0.2.0): wait_for_otp / wait_for_link now omit since by default instead of forwarding 0 ("any message already in the inbox"). The old default could return a STALE OTP/link already sitting in a reused inbox; the new default matches only messages arriving after the call. Pass since=0 explicitly to keep the old behaviour. Hosted server (mcp.mailsocket.app, deployed from the repo, no new PyPI release): per-key concurrent waits raised 3 → 10 (= the Pro plan cap; the API still enforces each plan's own cap) and the shared wait pool 16 → 32, following the backend's raised wait capacity (global 64).wait_for_otp / wait_for_link accept an optional since (ISO8601, unix seconds or a message id) so a reused inbox returns the NEW code; results include the message id and received_at.mailsocket>=0.1.3 (stricter _seg id validation in the underlying Python SDK).