cursorrules

Repository rules for a Sealgate MCP server, a small program that forwards AI tool requests to a Sealgate data-leak-prevention gateway. They document its Bun, TypeScript, validation, testing, and code-style setup.

In plain words
What is it for?
Use them when developing, configuring, testing, or reviewing the Sealgate MCP server and its gateway connection.
Why use it?
They give contributors clear boundaries for changing the proxy without exposing secrets or tying it to one server address.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/edison-watch/sealgate-mcp/cursorrules
Clone the repo
git clone --depth 1 https://github.com/Edison-Watch/sealgate-mcp

Made for: Cursor.

Per session 389 This file is loaded in full into every session.
When invoked 389 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00389 $0.00389
Opus 5 $0.00195 $0.00195
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 2d ago against content hash 67d083a78734, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

.cursorrules · 31 lines

What it actually says

Sealgate MCP server

This repo is the public MCP server for Sealgate, an AI data-leak-prevention platform. The server is a thin MCP proxy: it forwards tool calls to an Sealgate gateway, configured via SEALGATE_GATEWAY_URL and SEALGATE_API_KEY. Sealgate runs managed release hosts (the remote MCP gateway at mcp.sealgate.ai, advertised in the discovery manifests, and the Management API at dashboard.sealgate.ai), but demo and self-hosted orgs run their own, so this package stays host-agnostic: never hardcode a gateway URL or key.

Stack

  • Bun + TypeScript, MCP TypeScript SDK (@modelcontextprotocol/sdk), zod.
  • Biome for lint/format: 4-space indent, double quotes.

Layout

  • src/index.ts entrypoint (stdio by default, optional HTTP via env)
  • src/server.ts builds the McpServer and registers tools
  • src/config.ts validates the two env vars with zod
  • src/gateway.ts fetch wrapper that calls the Sealgate gateway with Bearer auth
  • src/tools/ one file per proxy tool

Working here

  • Build: bun run build (or bunx tsc --noEmit to typecheck)
  • Test: bun test
  • All checks: make ci (lint, deadcode, typecheck, tech-debt, duplicate-code, import boundaries, markdown links, AI-writing, Claude/Codex sync)
  • Run the server: bun run src/index.ts (add --help for usage)
  • No em dashes in any file; the AI-writing check fails on them.
  • Tools must fail gracefully (return an error result) when the env is unset, never throw at startup.
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.

  1. 2d ago First seen · 31 lines · 389 tokens per session scan A 67d083a78734

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository Edison-Watch/sealgate-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 389 tokens to every session, about $0.0019 per session on Opus 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.