Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Agent-Hellboy/mcp-runtimenpx agentmods add skills/agent-hellboy/mcp-runtime/mcp-runtime-platform-publicWrote 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/agent-hellboy/mcp-runtime/mcp-runtime-platform-public)<a href="https://agentmods.dev/skills/agent-hellboy/mcp-runtime/mcp-runtime-platform-public"><img src="https://agentmods.dev/badge/skills/agent-hellboy/mcp-runtime/mcp-runtime-platform-public/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/agent-hellboy/mcp-runtime/mcp-runtime-platform-public"><img src="https://agentmods.dev/badge/skills/agent-hellboy/mcp-runtime/mcp-runtime-platform-public.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 | $0.00077 | $0.00956 |
| Opus 5.5 | $0.00031 | $0.00382 |
| Sonnet 5.5 | $0.00015 | $0.00191 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
mcp-runtime-platform-public 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Runtime — public platform (domain, TLS, DNS)
Hostname model
With export MCP_PLATFORM_DOMAIN=example.com (apex only, no https://):
| Role | Host |
|---|---|
| Registry (push/pull ingress) | registry.example.com |
| MCP servers (default host-based) | mcp.example.com |
| Dashboard / API / Grafana path | platform.example.com |
Override individual hosts with MCP_REGISTRY_INGRESS_HOST, MCP_MCP_INGRESS_HOST, MCP_PLATFORM_INGRESS_HOST.
Operator may set MCP_DEFAULT_INGRESS_HOST=mcp.<domain> from platform domain env.
Expected URLs (after DNS + TLS)
- Dashboard:
https://platform.<domain>/(API at/api/v1/*via Traefik). Grafana at/grafanaviamcp-sentinel-platform-observability+sentinel-admin-auth@file(admin cookie or adminx-api-key). Prometheus stays internal — port-forward only for backend debug. - Registry:
https://registry.<domain>/v2/(admin auth viaregistry-admin-auth@file→/api/v1/registry/authz) - MCP server:
https://mcp.<domain>/<server-name>/mcp(path-based; setspec.publicPathPrefixandMCP_PATH)
Default MCPServer ingress class: traefik.
TLS setup
./bin/mcp-runtime setup --with-tls --acme-email <addr>
# staging: --acme-staging or MCP_ACME_STAGING=1
# enterprise CA (no ACME): --with-tls --tls-cluster-issuer <name> # mutually exclusive with --acme-email
DNS requirements
- A/AAAA (or CNAME) for
registry.,mcp., andplatform.→ same ingress IP/LB - Port 80 → Traefik for HTTP-01 before certs issue
- Typos (
regsitry,platfrom) break matching certificates
Certificates
registry/registry-cert→registry/registry-tls(only supported owner for that Secret; registry Ingress must not usecert-manager.io/cluster-issueron the Ingress itself)- Platform UI:
mcp-sentinel-platform-tlsinmcp-sentinelviamcp-sentinel-platform-uiIngress - Bundled HTTPS may create
cert-manager/mcp-runtime-ca; nodes must trusttls.crtfor image pulls - Private CA without ACME:
config/cert-manager/and omit--acme-email
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 First seen · 69 lines · 77 tokens per session scan A 0e419eade801
mcp-runtime-platform-public is a skill published in the GitHub repository Agent-Hellboy/mcp-runtime (6 stars, last pushed 26d ago), licensed Apache-2.0. It adds 77 tokens to every session and 956 once invoked, about $0.0003 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.
Other skills, from other repositories
terraform-setup
Install (deploy) MCP Gateway & Registry on AWS using the Terraform aws-ecs stack (ECS Fargate, Aurora, DocumentDB, Keycloak). Asks whether you are running from an EC2 instance or a local laptop, confirms the required AWS IAM permissions are in place, clones the repository, bootstraps the toolchain (uv, AWS CLI…
infra-sync
Keep Terraform and CDK infrastructure in sync. Compares terraform/aws-ecs/ and infra/ to identify discrepancies in ECS services, networking, storage, secrets, IAM, and configuration. Reports parity gaps and generates fixes for the target IaC tool. Use when changes are made to either Terraform or CDK infrastructure.
cluster-run
Use when resolving Spack software, configuring a JARVIS pipeline and following its execution. Triggers on "run this on the cluster", "JARVIS pipeline", "install and run". Not for handwritten batch scripts; use slurm-script.
tencent-pg-inspection
Run routine health inspection for Tencent Cloud PostgreSQL by calling Tencent Cloud OpenAPI directly. This skill can use the full aligned PostgreSQL OpenAPI action set documented in @references/apireference.md. Start with evidence collection first, and require explicit confirmation before any write, fee-impacting, or…
tencent-pg-ops-troubleshooter
Troubleshoot operational issues for Tencent Cloud PostgreSQL by calling Tencent Cloud OpenAPI directly. This skill can use the full aligned PostgreSQL OpenAPI action set documented in @references/apireference.md. Start with evidence collection first, and require explicit confirmation before any write, fee-impacting…
nixos-remote-cache-expert
Expert system administrator for NixOS remote cache servers on modest hardware. Use when setting up, optimizing, troubleshooting, or planning NixOS cache servers, especially on low-spec machines with limited RAM or CPU. Provides realistic assessments, creative workarounds, hardware upgrade planning, direct network…