agentmods.dev

sealgate-mcp: Instructions file for Claude Code

CLAUDE.md

sealgate-mcp CLAUDE.md is an instructions file for Claude Code from Edison-Watch/sealgate-mcp. It costs 974 tokens per session, scanned A, original, MIT.

A project-instructions document for working on Sealgate's public MCP server. MCP is a standard way for AI systems to call tools; this server forwards those calls to Sealgate's security gateway.

In plain words
What is it for?
Use it when modifying, building, testing, or troubleshooting the Sealgate MCP server and its gateway configuration.
Why use it?
It gives coding agents the project's architecture, environment-variable rules, commands, and error-handling expectations in one place.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is Edison-Watch/sealgate-mcp's own configuration. It tells Claude Code how to work on sealgate-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sealgate-mcp configures →

not rated 0repo 3d ago A scan 974 tokens original MIT
View source ↗ Edison-Watch/sealgate-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to Edison-Watch/sealgate-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/Edison-Watch/sealgate-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Edison-Watch/sealgate-mcp

Made for: Claude Code.

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.

agentmods badge for sealgate-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/edison-watch/sealgate-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/edison-watch/sealgate-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/edison-watch/sealgate-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/edison-watch/sealgate-mcp/claude-md/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.

agentmods 80×15 button for sealgate-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/edison-watch/sealgate-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/edison-watch/sealgate-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 974 This file is loaded in full into every session.
When invoked 974 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00974 $0.00974
Opus 5 $0.00487 $0.00487
Sonnet 5 $0.00195 $0.00195
Haiku 4.5 $0.00097 $0.00097

Measured 8d ago against content hash d672a0190b12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sealgate-mcp CLAUDE.md 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 8d 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.

CLAUDE.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code and other agents working in this repository. AGENTS.md is a symlink to this file.

Project Overview

The public MCP server for Sealgate, an AI data-leak-prevention platform (a security gateway and data firewall for AI agents). The server is a thin MCP proxy: it forwards tool calls to a Sealgate gateway. 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: the gateway URL and API key are supplied by the user through SEALGATE_GATEWAY_URL and SEALGATE_API_KEY. Never hardcode or fabricate a gateway URL or key in the package code. Tools must fail gracefully (return an error result) when the env is unset, never throw at startup, so registry probes and --help do not crash.

Common Commands

bun install                 # Install dependencies
bun run src/index.ts        # Run the server over stdio (add --help for usage)
bun run dev                 # Run in watch mode
bun run build               # Bundle to dist/
bun test                    # Run tests
make ci                     # All checks: lint, deadcode, typecheck, tech-debt,
                            #   duplicate-code, import boundaries, links,
                            #   AI-writing, Claude/Codex sync
make fmt                    # Auto-fix formatting with Biome

Architecture

  • src/index.ts - entrypoint. Handles --help/--version, picks the transport (stdio by default; streamable HTTP when SEALGATE_MCP_TRANSPORT=http).
  • src/server.ts - builds the McpServer and registers the tools.
  • src/config.ts - validates the two env vars with zod; returns a result rather than throwing.
  • src/gateway.ts - fetch wrapper that calls the configured Sealgate gateway with Bearer auth.
  • src/tools/ - one file per proxy tool (list_mcp_servers, get_session_status); helpers.ts holds the shared config-check and result-marshalling logic.
  • test/ - bun test suite; drives the server through an in-memory MCP client.

Read the full file on GitHub · 91 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.

  1. 8d ago First seen · 91 lines · 974 tokens per session scan A d672a0190b12

Subscribe to this mod's changes

sealgate-mcp CLAUDE.md is an instructions file published in the GitHub repository Edison-Watch/sealgate-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 974 tokens to every session, about $0.0049 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.

Building agentsSecurity
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens