A set of rules for an MCP gateway, a service that gives coding agents access to tools. It keeps the gateway small, makes agents check available capabilities first, and uses live descriptions as the source of truth.

For designing and maintaining MCP tools, capability checks, bytecode simulation access, validation schemas, builds, and related documentation.

It prevents the gateway from filling up with separate tools for every protocol feature and reduces errors caused by outdated documentation or unsupported requests.

mcp-surface — Cursor rule for Cursor by feelyourprotocol/mcp-gateway

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.

Clone the repo

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

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/feelyourprotocol/mcp-gateway/mcp-surface/github.svg)](https://agentmods.dev/rules/feelyourprotocol/mcp-gateway/mcp-surface)

Your own site

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

Per session 700 This file is loaded in full into every session.

When invoked 700 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	$0.00700	$0.00700
Opus 5.5	$0.00280	$0.00280
Sonnet 5.5	$0.00140	$0.00140
Haiku 4.5	$0.00070	$0.00070

Measured 20d ago against content hash b4bf264e6f1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-surface 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 20d 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.

.cursor/rules/mcp-surface.mdc · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP surface (gateway)

Few generic tools

Tools are verbs (probe, simulate, transaction, block, generate, inspect), not per-EIP or per-fork endpoints. MCP names: describe_capabilities, run_bytecode, run_transaction, run_block, generate_artifact, inspect_artifact
Do not add simulate_eip8024 or run_amsterdam — EIP modules and named forks live in the engine catalog
New query shape → one new generic tool + engine function

Descriptions are the prompt

Server instructions must claim generic hardfork prompts (run under Glamsterdam / Fusaka / Pectra with no EIP named)
Tool description strings must mention Glamsterdam, generic fork runs, runnable EIPs, and which verb to pick (run_bytecode vs run_transaction vs run_block vs generate_artifact vs inspect_artifact)
describe_capabilities: probe first — named forks as capabilities, runnable modules, opcodes/encoding, queryShapes + tools (not shapes), spec snapshot (specUrl, specDate, status, testReleaseName)
run_bytecode: generic bytecode under a fork; opcodes / precompiles / traces / program-gas SSTORE; optional accounts prestate; point at probe; no demo programs
run_transaction: generic paid tx under a fork; receipts, wallet gasLimit, txStateGas; point at probe
run_block: 1–8 txs as a lab block, optional header slot/number/timestamp; not BAL JSON
generate_artifact: derive lab artifacts (BAL first) — same inputs as run_block
inspect_artifact: judge caller-supplied structures (BAL JSON/RLP) without chain state

Probe-first for runtime agents

Human and runtime agents should call describe_capabilities before run_bytecode, run_transaction, run_block, generate_artifact, or inspect_artifact
Live describeCapabilities() is authoritative — not stale markdown in the repo

After gateway changes

npm run build in mcp-gateway
npm run build in mcp-execution-engine if engine API changed
Restart MCP server in Cursor (Settings → MCP)
Update mcp-docs tool pages + llms.txt when behavior or tool list changes

Read the full file on GitHub · 44 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.

20d ago Changed · +3 lines · +178 tokens per session b4bf264e6f1e
27d ago Changed · +18 tokens per session a049c61366ef
1mo ago Changed · +5 tokens per session f7a3179b9584
1mo ago Changed · +3 lines · +93 tokens per session c7ce401765e2
1mo ago Changed · +15 tokens per session 378016c699e7
1mo ago Changed · +1 lines · +38 tokens per session 80281a3e688a
1mo ago Changed · +1 lines · +44 tokens per session 059bfc9abf72
1mo ago First seen · 36 lines · 309 tokens per session scan A e0dafc26808c

Subscribe to this mod's changes

mcp-surface is a cursor rule published in the GitHub repository feelyourprotocol/mcp-gateway (0 stars, last pushed 11d ago), licensed MIT. It adds 700 tokens to every session, about $0.0028 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.

Building agents

mcp-surface

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

MCP surface (gateway)

Few generic tools

Descriptions are the prompt

Probe-first for runtime agents

After gateway changes

What this file has done since we first saw it

Other cursor rules, from other repositories

ponytail

angular-20

dev-standard

prefer-assertions-over-defensive-checks

prefer-direct-imports-over-module-mocks

shared-plane-packages