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 skills add Sugra-Systems/sugra-api-mcp --skill hosted-vs-gatewaygit clone --depth 1 https://github.com/Sugra-Systems/sugra-api-mcpWrote 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.
[](https://agentmods.dev/skills/sugra-systems/sugra-api-mcp/hosted-vs-gateway)<a href="https://agentmods.dev/skills/sugra-systems/sugra-api-mcp/hosted-vs-gateway"><img src="https://agentmods.dev/badge/skills/sugra-systems/sugra-api-mcp/hosted-vs-gateway/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.
<a href="https://agentmods.dev/skills/sugra-systems/sugra-api-mcp/hosted-vs-gateway"><img src="https://agentmods.dev/badge/skills/sugra-systems/sugra-api-mcp/hosted-vs-gateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00057 | $0.00445 |
| Opus 5 | $0.00028 | $0.00222 |
| Sonnet 5 | $0.00011 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
hosted-vs-gateway 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 today.
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
Hosted agent tools vs gateway
Two transports, one catalog.
| Transport | Tools | How the client authenticates |
|---|---|---|
| Local package stdio | 8 | SUGRA_API_KEY in the server process |
| Self-hosted Streamable HTTP | 8 | Client Authorization: Bearer; server SUGRA_API_KEY is only a downstream fallback |
Hosted https://app.sugra.ai/mcp (canonical https://mcp.sugra.ai/mcp) |
11 | Client Bearer API key or OAuth |
The eight gateway tools on every transport: fetch_data, search_endpoints, describe_endpoint, call_endpoint, list_toolsets, list_sources, sugra_entity_screen, sugra_entity_lookup.
Hosted adds three composed tools that wrap an internal plane and register only on the hosted entry point:
resolve_entity- free text to a canonical market or macro entity; ambiguous matches return ranked candidates, never a silent pick.get_snapshot- entity plus a named recipe to one current view.get_timeseries- entity plus a metric to a bounded series.
Do not call those three on a stdio or self-hosted session. Do not document them in stdio-only examples. For LEI/VAT identity and sanctions screening, use sugra_entity_lookup and sugra_entity_screen on every transport.
MCP prompts shipped in the package name only the eight. Skills explore-catalog, envelope-attribution, auth-limits, and cross-domain-briefing are written for the eight so they work as a Claude/Codex drop-in next to the PyPI package.
app.sugra.ai/mcp remains a permanent alias of the hosted server.
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.
- today First seen · 29 lines · 57 tokens per session scan A 95488562a468
hosted-vs-gateway is a skill published in the GitHub repository Sugra-Systems/sugra-api-mcp (2 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 445 once invoked, about $0.0003 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 2026-09-11.
Other skills, from other repositories
terraform-skill
Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…
terraform-cli-setup
A setup guide for installing and initializing Terraform, a tool for managing infrastructure from configuration files. It also covers basic provider downloads and mirror settings, but not cloud-provider credentials.
api-workers
Cloudflare Workers deployment using createWorkerHandler from @cyanheads/mcp-ts-core/worker. Covers the full handler signature, binding types, CloudflareBindings extensibility, runtime compatibility guards, and wrangler.toml requirements.
coolify
Operate a Coolify self-hosted PaaS through the @masonator/coolify-mcp server. Use this skill whenever the user asks Claude to inspect, deploy, restart, debug, or manage anything on Coolify — including applications, databases, services, servers, projects, environments, deployments, environment variables, private keys…
discovery-patterns
Configure ServiceNow Discovery — schedules, IP ranges, credential affinities, MID Server assignment, custom probes/sensors, identification rules, and run-status monitoring on discovery tables.
webmcp-nexus
A coding guide for adding WebMCP tools to JavaScript or TypeScript projects. WebMCP lets AI agents call selected application functions through a standard interface.