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 commands/vishnu2kmohan/mcp-server-langgraph/deploygit clone --depth 1 https://github.com/vishnu2kmohan/mcp-server-langgraphWhat 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 | $0.00018 | $0.03751 |
| Opus 5 | $0.00009 | $0.01876 |
| Sonnet 5 | $0.00004 | $0.00750 |
| Haiku 4.5 | $0.00002 | $0.00375 |
Grade A, and why
deploy 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.
curl -X POST https://api.langgraph.com/v1/deployments \ How it starts
The opening of the file, as written. The whole thing — 542 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unified Deployment Command
You are tasked with deploying the mcp-server-langgraph application to various targets. This command provides a unified interface for deploying to Kubernetes, GKE, Cloud Run, Helm, and Kustomize.
Deployment Context
Available Targets:
- Kubernetes (kubectl + Kustomize): GCP, Azure, AWS overlays
- GKE Staging: Google Kubernetes Engine (preview-gke overlay)
- Cloud Run: Google Cloud Run serverless
- Helm: Kubernetes package manager with dependencies
- Kustomize Overlays: dev, staging, production
- LangGraph Platform: LangGraph Cloud deployment
Deployment Structure:
deployments/
├── base/ # Base Kubernetes manifests
├── cloudrun/ # Cloud Run deployment
├── helm/ # Helm charts
├── kubernetes/ # K8s overlays (GCP, Azure, AWS)
├── overlays/ # Kustomize overlays (dev, staging, prod)
├── langgraph-platform/ # LangGraph Cloud
└── kong/ # Kong API Gateway
Your Task
Step 1: Gather Deployment Information
Ask the user using the AskUserQuestion tool:
Question 1: What is your deployment target?
- Header: "Target"
- Options:
- Kubernetes (GCP): Deploy to GKE or GCP Kubernetes
- Kubernetes (Azure): Deploy to AKS
- Kubernetes (AWS): Deploy to EKS
- GKE Staging: Staging environment on GKE
- Cloud Run: Google Cloud Run serverless
- Helm: Package manager deployment
- Kustomize Overlay: Dev/Staging/Production overlay
Question 2: What environment?
- Header: "Environment"
- Options:
- dev: Development environment
- staging: Staging environment
- production: Production environment
Question 3: Deployment mode?
- Header: "Mode"
- Options:
- Full Deploy: Complete deployment with all dependencies
- App Only: Deploy only the application (skip dependencies)
- Dry Run: Show what would be deployed (no actual deployment)
- Validate Only: Validate manifests without deploying
Step 2: Pre-Deployment Validation
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 · 542 lines · 18 tokens per session scan A 95e22d053559
deploy is a command published in the GitHub repository vishnu2kmohan/mcp-server-langgraph (4 stars, last pushed 9d ago), licensed MIT. It adds 18 tokens to every session and 3,751 once invoked, about $0.0001 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 commands, from other repositories
karpenter
Design, install, debug, review, plan capacity, audit scaling history, migrate from Cluster Autoscaler, and upgrade Karpenter v1.x on EKS. Covers NodePool, EC2NodeClass, NodeClaim, Spot diversity, disruption strategy, Pod Identity/IRSA, interruption queue, private clusters, AMI rotation, and GitOps integration. Use…
kubernetes
Cluster baseline scaffolding, RBAC diagnosis and generation, workload hardening, and structured pod/scheduling debug for plain Kubernetes across all distributions.
keda
Design, debug, and review KEDA ScaledObject/ScaledJob autoscaling. Covers all major scalers (Prometheus, SQS, Kafka, Redis, Cron, HTTP Add-on, Azure Service Bus), TriggerAuthentication, scaling lifecycle tuning, GitOps integration, and troubleshooting. Use when asked to "add KEDA autoscaling", "debug why my…
k8s-manifest
You are a senior DevOps & Cloud Infrastructure specialist. The user needs help with k8s manifest in the context of ci/cd pipelines, container orchestration, iac, monitoring and incident response.
migrate-k8s
Migrate Kubernetes manifests, Docker Compose projects, or Helm charts to Control Plane.
aci-run
Run a container in Azure Container Instances for quick one-off tasks or scheduled jobs.