Executor MCP gateway — one catalog for OpenAPI/GraphQL/MCP integrations shared across agents. Use for external APIs, multi-agent tool routing, policies.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add nuroctane/nur-cli --skill executor-gateway --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Executor Gateway?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/nuroctane-executor-gateway)More formats (shields.io, HTML) on the badges page.
---
name: executor-gateway
description: "Executor MCP gateway — one catalog for OpenAPI/GraphQL/MCP integrations shared across agents. Use for external APIs, multi-agent tool routing, policies."
---
# Executor (executor.sh)
Docs: https://executor.sh/docs
CLI: `npm i -g executor` (Meta auto-installs)
## What it is
Local (or cloud) MCP gateway: configure integrations once, every agent gets the same tools with shared auth + policies.
## Meta integration
- Tool: `executor` (status / tools search / call / sources)
- Service: `executor install` starts durable local daemon
- MCP HTTP: `http://127.0.0.1:4788/mcp` (stdio: `executor mcp`)
- Prefer Meta's native tools for repo work; use Executor for **external SaaS/APIs**
## Common commands
```
executor tools sources
executor tools search "send email"
executor call <namespace> <tool> '<json>'
executor web # UI at :4788
```
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
