Instructions for using an email server with tools for sending, receiving, searching, and managing messages. It supports services such as SMTP, IMAP, SendGrid, Mailgun, Resend, and local test servers.

Use it to inspect inboxes, search and manage messages, send requested emails, and work with mailing-list updates.

It provides a consistent way to work with email across different providers and helps check connected services and inbox activity before a task.

How sandraschi/email-mcp configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to sandraschi/email-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sandraschi/email-mcp/master/.cursorrules

Clone the repo

git clone --depth 1 https://github.com/sandraschi/email-mcp

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/rules/sandraschi/email-mcp/cursorrules/github.svg)](https://agentmods.dev/rules/sandraschi/email-mcp/cursorrules)

Your own site

<a href="https://agentmods.dev/rules/sandraschi/email-mcp/cursorrules"><img src="https://agentmods.dev/badge/rules/sandraschi/email-mcp/cursorrules/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/rules/sandraschi/email-mcp/cursorrules"><img src="https://agentmods.dev/badge/rules/sandraschi/email-mcp/cursorrules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 629 This file is loaded in full into every session.

When invoked 629 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00629	$0.00629
Opus 5.5	$0.00252	$0.00252
Sonnet 5.5	$0.00126	$0.00126
Haiku 4.5	$0.00063	$0.00063

Measured 23d ago against content hash 40d2c21f1ffd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cursorrules scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

windsurfrules — 100% identical, 0 lines differ

.cursorrules · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Context (Email MCP)

You have access to an email server with 32+ tools for sending, receiving, searching, and managing email across SMTP/IMAP, SendGrid, Mailgun, Resend, and local test servers.

Before starting work:

Check connected services: list_services() or email_status()
Check recent inbox activity: check_inbox(service="default", unread_only=True, limit=10)

At end of work:

Send any drafted emails the user requested
Mark relevant messages as read/starred
Use mailing_list_latest() to stay current on subscribed newsletters

Fleet context — required reading

Before any task in this fleet, read mcp-central-docs/standards/AGENT_READING_ORDER.md. It carries the AGENTS.md chain, the 13-file Primary Read List, the domain read list, the pitfalls docs and the bug depot. There are 124 files under standards/; that file is the index that makes them usable.

Search mcp-central-docs/troubleshooting/BUGS_DEPOT.md by symptom before debugging anything — a bug the fleet has already paid for is a lookup, not an investigation.

These few are repeated here rather than linked, because a rule whose violation produces no error cannot depend on anyone following a link:

Never author multi-line file content with a Bash heredoc (cat > file <<'EOF') — it intermittently writes nothing on this Windows/Git-Bash setup. Use the Write tool. (BUG-031)
Never patch files with inline Python (python - <<'PY', python -c) — Python's string parser silently converts backslash escapes, so "D:\Dev\repos\x" becomes D: + \D + ev + CR + epos + CR + x. One observed case deleted dict entries while staying valid Python with a clean lint. Use Edit and Write. (BUG-039)
Never hardcode a port. Claim one with mcp-central-docs/fleet-gate/claim_ports.py, which checks operations/WEBAPP_PORTS.md and every fleet-start.config.ps1.
Max 5 files per commit and per script invocation; 3+ file edits need a timestamped .bak per file written first.
Never restart an NSSM service by killing its child — sc.exe stop/start, then verify a NEW PID owns the port.
Never invent a date or location; read the clock or write UNKNOWN-DATE.
Prove changes by running them. A gate that reports success having examined nothing is this fleet's most common failure mode.

Read the full file on GitHub · 46 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

23d ago Changed · +33 lines · +501 tokens per session 40d2c21f1ffd
2mo ago First seen · 13 lines · 128 tokens per session scan A 766d6bd641ec

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository sandraschi/email-mcp (4 stars, last pushed 6d ago), licensed MIT. It adds 629 tokens to every session, about $0.0025 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

email mcp-server webapp

cursorrules next to 6 cursor rules from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cursorrulessandraschi/email-mcp	Cursor rule	4	6d ago	MIT	A	629	Cursor
reactDataCovey/nornweave	Cursor rule	30	10d ago	Apache-2.0	A	0	Cursor
design-principlesDataCovey/nornweave	Cursor rule	30	10d ago	Apache-2.0	A	0	Cursor
mainDataCovey/nornweave	Cursor rule	30	10d ago	Apache-2.0	A	2,102	Cursor
implementation-honestysandraschi/virtualization-mcp	Cursor rule	19	today	MIT	A	114	Cursor
performance-optimization-ruleDataCovey/nornweave	Cursor rule	30	10d ago	Apache-2.0	A	0	Cursor
ui-and-styling-ruleDataCovey/nornweave	Cursor rule	30	10d ago	Apache-2.0	A	0	Cursor

email-mcp: Cursor rule for Cursor