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 skills/agent-hellboy/mcp-runtime/mcp-runtime-local-devnpx skills add Agent-Hellboy/mcp-runtime --skill mcp-runtime-local-devgit clone --depth 1 https://github.com/Agent-Hellboy/mcp-runtimeWhat 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 | $0.00075 | $0.00718 |
| Opus 5 | $0.00037 | $0.00359 |
| Sonnet 5 | $0.00015 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
mcp-runtime-local-dev scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `UI_API_KEY` must appear in both `API_KEYS` and `ADMIN_API_KEYS` for admin curl + browser login How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Runtime — local dev endpoints and auth
Prerequisites
Cluster running per .codex/skills/qa-cluster-bringup/SKILL.md or docs/contributor/README.md.
kubectl port-forward -n traefik svc/traefik 18080:8000
URLs (test-mode)
| Service | URL |
|---|---|
| UI | http://localhost:18080/ |
| API | http://localhost:18080/api/v1 |
| Grafana | http://localhost:18080/grafana |
| MCP samples | http://localhost:18080/workspace-assistant-mcp/mcp, …/data-utility-mcp/mcp, …/text-analysis-mcp/mcp |
| Prometheus (debug) | kubectl port-forward -n mcp-sentinel svc/prometheus 9090:9090 |
PII redaction: config/ingress/overlays/http + pii-redactor@file — keep off /api/v1 routes (keys and grant subjects must stay exact).
API keys
kubectl get secret mcp-sentinel-secrets -n mcp-sentinel -o jsonpath='{.data.UI_API_KEY}' | base64 -d
kubectl get secret mcp-sentinel-secrets -n mcp-sentinel -o jsonpath='{.data.INGEST_API_KEYS}' | base64 -d
UI_API_KEYmust appear in bothAPI_KEYSandADMIN_API_KEYSfor admin curl + browser loginINGEST_API_KEYSfor analytics ingest only- After secret changes: roll platform-api, runtime-api, analytics-api, UI, ingest, and gateway workloads
/api/v1401 →./bin/mcp-runtime cluster doctor
Test-mode logins
setup --test-mode seeds (local only):
[email protected]/test@123[email protected]/admin@123
Override via PLATFORM_DEV_* in mcp-sentinel-secrets; roll the split API Deployments after changes.
Platform admin bootstrap (one-shot)
kubectl apply -f k8s/21-platform-admin-bootstrap-job.yaml
kubectl wait --for=condition=complete job/mcp-sentinel-platform-admin-bootstrap -n mcp-sentinel --timeout=120s
kubectl patch secret mcp-sentinel-secrets -n mcp-sentinel --type merge -p '{"stringData":{"PLATFORM_ADMIN_PASSWORD":""}}'
Clear PLATFORM_ADMIN_PASSWORD from steady-state API env after bootstrap.
Quick commands
./bin/mcp-runtime status
./bin/mcp-runtime bootstrap # preflight only
./bin/mcp-runtime cluster doctor
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.
- 2d ago First seen · 68 lines · 75 tokens per session scan A b1cf74949c68
mcp-runtime-local-dev is a skill published in the GitHub repository Agent-Hellboy/mcp-runtime (5 stars, last pushed 8d ago), licensed Apache-2.0. It adds 75 tokens to every session and 718 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
triage-image-cves
Scan an Activepieces Docker image with grype for OS/base-image (deb) and application (npm) CVEs of High/Critical severity. Lists the 3 most-recent published tags and lets the user pick which to scan, validates each finding is real and reachable, and proves candidate fixes in an isolated git worktree (rebuild image +…
cloud-k8s
Use for authorized cloud, container, and Kubernetes security assessment including metadata SSRF, IAM misconfig, container escape paths, and cluster RBAC review.
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…
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
reproduce-issue
The single skill for reproducing an nx issue. Given a GitHub issue number (human entry) OR explicit repro parameters (agent entry), it runs the reproduction ENTIRELY inside an isolated Docker sandbox — gVisor on Linux, the Docker VM on macOS — so the untrusted repro's install scripts and commands never execute on the…
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.