What is mcp-gateway AGENTS.md?

Repository instructions for the FeelYourProtocol MCP gateway, a service that connects coding agents to an execution engine. They describe its identity, available tools, dependencies, and layout.

For maintaining the gateway, registering capability and bytecode-simulation tools, following naming conventions, and understanding its connection to the execution engine and documentation.

They clarify which component owns tool registration and which handles simulation, reducing the risk of adding logic or tools in the wrong repository.

How feelyourprotocol/mcp-gateway configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to feelyourprotocol/mcp-gateway. 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/feelyourprotocol/mcp-gateway/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/feelyourprotocol/mcp-gateway

Made for: Codex, OpenCode.

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/instructions/feelyourprotocol/mcp-gateway/agents-md/github.svg)](https://agentmods.dev/instructions/feelyourprotocol/mcp-gateway/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/feelyourprotocol/mcp-gateway/agents-md"><img src="https://agentmods.dev/badge/instructions/feelyourprotocol/mcp-gateway/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/feelyourprotocol/mcp-gateway/agents-md"><img src="https://agentmods.dev/badge/instructions/feelyourprotocol/mcp-gateway/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 927 This file is loaded in full into every session.

When invoked 927 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	$0.00927	$0.00927
Opus 5.5	$0.00371	$0.00371
Sonnet 5.5	$0.00185	$0.00185
Haiku 4.5	$0.00093	$0.00093

Measured 1mo ago against content hash a2bb3bdefb53, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-gateway AGENTS.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 1mo 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.

AGENTS.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent notes

Tool-agnostic entrypoint for coding agents working in mcp-gateway.

Read this file first. Then load .cursor/rules/ — mcp-surface.mdc, git.mdc (defers to the website git rule).

Depends one-way on mcp-execution-engine via LocalTaskProcessor. Human docs: mcp-docs.feelyourprotocol.org.

What this repo is

MCP transport + tool registry. Maps generic MCP tools to engine query shapes. No simulation logic here.

Agent → mcp-gateway (this repo) → mcp-execution-engine → EthereumJS

MCP identity

Constant	Value	Notes
`SERVER_NAME`	`FeelYourProtocol`	MCP handshake `name` — product id, not `-EVM` (server scope is broader than EVM)
`instructions`	`SERVER_INSTRUCTIONS`	Handshake routing: generic hardfork runs (Amsterdam default) without an EIP
Config key (docs)	`feel-your-protocol`	User-chosen in `mcp.json`; kebab-case
CLI / logs	`fyp-mcp`	Bin and stderr prefix

Live tools (v0.1)

MCP tool	Engine call
`describe_capabilities`	`describeCapabilities()`
`run_bytecode`	`simulateBytecode()`
`run_transaction`	`runTransaction()`
`run_block`	`runBlock()`
`generate_artifact`	`generateArtifact()`
`inspect_artifact`	`inspectArtifact()`

Do not add per-EIP MCP tools (e.g. simulate_eip8024) or per-fork tools (e.g. run_amsterdam). EIP and named-fork coverage is advertised via server instructions, tool descriptions, and live probe output.

Repo layout

Path	Role
`src/tools/`	MCP tool registration + descriptions
`src/schemas/`	Zod input shapes — runtime source of truth
`schemas/`	Published `*.input.json` + `manifest.json` — mirror to `website/mcp-docs/public/schemas/`
`src/engine/TaskProcessor.ts`	Seam: `LocalTaskProcessor` (stdio, tests) or `WorkerPool` (hosted HTTP, shared, one worker per core)
`src/engine/runSimulationTask.ts`	The one task-kind to engine-call switch, used by both processors and the worker
`src/index.ts`	stdio entry
`src/http/`	HTTP transport (planned production)

Read the full file on GitHub · 72 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.

1mo ago Changed · +1 lines · +76 tokens per session a2bb3bdefb53
1mo ago Changed · +3 lines · +75 tokens per session 2350f0dedf20
1mo ago Changed · +1 lines · +50 tokens per session b833c6df4879
1mo ago Changed · -1 lines · +5 tokens per session e5540f9f9c9b
1mo ago Changed · +1 lines · +11 tokens per session 3d6685433453
1mo ago Changed · +1 lines · +9 tokens per session dc80f4c19ed8
2mo ago First seen · 66 lines · 701 tokens per session scan A 7d71febee89c

Subscribe to this mod's changes

mcp-gateway AGENTS.md is an instructions file published in the GitHub repository feelyourprotocol/mcp-gateway (0 stars, last pushed 29d ago), licensed MIT. It adds 927 tokens to every session, about $0.0037 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.

Backend and APIs Building agents

mcp-gateway AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-gateway AGENTS.mdfeelyourprotocol/mcp-gateway	Instructions file	0	29d ago	MIT	A	927	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-gateway: Instructions file for Codex