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.
npx agentmods add rules/feelyourprotocol/mcp-gateway/mcp-surfacegit clone --depth 1 https://github.com/feelyourprotocol/mcp-gatewayWhat 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 | $0.00309 | $0.00309 |
| Opus 5 | $0.00154 | $0.00154 |
| Sonnet 5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
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 yesterday.
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.
What it actually says
MCP surface (gateway)
Few generic tools
- Tools are verbs (probe, simulate, later generate), not per-EIP endpoints
- Do not add
simulate_eip8024or similar — EIP modules live in the engine catalog - New query shape → one new generic tool + engine function
Descriptions are the prompt
- Tool
descriptionstrings must mention Amsterdam, runnable EIPs, and caller-supplied bytecode describe_capabilities: probe first — forks, runnable modules, opcodes/encodingrun_evm_bytecode: point at probe; no demo programs shipped
Probe-first for runtime agents
- Human and runtime agents should call
describe_capabilitiesbefore simulate - Live
describeCapabilities()is authoritative — not stale markdown in the repo
After gateway changes
npm run buildinmcp-gatewaynpm run buildinmcp-execution-engineif engine API changed- Restart MCP server in Cursor (Settings → MCP)
- Update mcp-docs tool pages +
llms.txtwhen behavior or tool list changes
Schemas
- Zod in
src/schemas/— source of truth for validation - Copy JSON schema to
website/mcp-docs/public/schemas/when inputs change
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.
- yesterday First seen · 36 lines · 309 tokens per session scan A e0dafc26808c
mcp-surface is a cursor rule published in the GitHub repository feelyourprotocol/mcp-gateway (0 stars, last pushed yesterday), licensed MIT. It adds 309 tokens to every session, about $0.0015 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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.