mcp-server-servicenow: Agent for Claude Code

.github/agents/deploy-mcp-container.chatmode.md

deploy-mcp-container is an agent for Claude Code from pavecer/mcp-server-servicenow. It costs 25 tokens per session (1,892 once invoked), scanned A, original, MIT.

An agent mode for deploying a Docker-based ServiceNow MCP server to Azure Container Apps. MCP is a way for software tools to expose functions that an AI assistant can call.

In plain words
What is it for?
Use it to store the container image in Azure Container Registry, run it in Azure Container Apps, enable external access, and expose its MCP endpoint.
Why use it?
It guides the deployment setup and gathers the Azure, ServiceNow, and Microsoft Entra settings needed to make the server available over the web.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is pavecer/mcp-server-servicenow's own configuration. It tells Claude Code how to work on mcp-server-servicenow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-server-servicenow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pavecer/mcp-server-servicenow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pavecer/mcp-server-servicenow/main/.github/agents/deploy-mcp-container.chatmode.md
Clone the repo
git clone --depth 1 https://github.com/pavecer/mcp-server-servicenow

Made for: Claude Code.

Wrote 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.

agentmods badge for deploy-mcp-container

README.md
[![agentmods](https://agentmods.dev/badge/agents/pavecer/mcp-server-servicenow/deploy-mcp-container/github.svg)](https://agentmods.dev/agents/pavecer/mcp-server-servicenow/deploy-mcp-container)
Your own site
<a href="https://agentmods.dev/agents/pavecer/mcp-server-servicenow/deploy-mcp-container"><img src="https://agentmods.dev/badge/agents/pavecer/mcp-server-servicenow/deploy-mcp-container/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.

agentmods 80×15 button for deploy-mcp-container

Your own site · 80×15
<a href="https://agentmods.dev/agents/pavecer/mcp-server-servicenow/deploy-mcp-container"><img src="https://agentmods.dev/badge/agents/pavecer/mcp-server-servicenow/deploy-mcp-container.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,892 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.01892
Opus 5 $0.00013 $0.00946
Sonnet 5 $0.00005 $0.00378
Haiku 4.5 $0.00003 $0.00189

Measured 8d ago against content hash 85d0b69651d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

deploy-mcp-container 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 8d 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 -i http://localhost:8080/health
.github/agents/deploy-mcp-container.chatmode.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ServiceNow MCP Server — Deploy Container to Azure

This chat mode deploys the Dockerized ServiceNow MCP Server to Azure Container Apps.

It is designed for the optional container deployment path already present in this repository:

  • Dockerfile
  • src/server.ts
  • docs/DEPLOY_CONTAINER_AZURE.md

Use this mode when you want GitHub Copilot to perform or guide the deployment of the single-container MCP server into Azure with all required configuration.

Deployment Target

  • Azure Container Registry for image storage
  • Azure Container Apps for runtime hosting
  • External ingress enabled
  • MCP endpoint exposed at https://<container-app-fqdn>/mcp

Required Inputs

Before deploying, collect or confirm these values with the user.

Azure

  • Subscription ID or subscription name
  • Azure location
  • Resource group name
  • Azure Container Registry name
  • Container Apps environment name
  • Container App name
  • Docker image tag

ServiceNow

  • SERVICENOW_INSTANCE_URL
  • SERVICENOW_CLIENT_ID
  • SERVICENOW_CLIENT_SECRET
  • SERVICENOW_USERNAME
  • SERVICENOW_PASSWORD

Entra ID

  • ENTRA_TENANT_ID
  • ENTRA_CLIENT_ID
  • ENTRA_CLIENT_SECRET
  • Optional: ENTRA_AUDIENCE
  • Optional: ENTRA_TRUSTED_TENANT_IDS
  • Optional: ENTRA_ALLOW_ANY_TENANT

Rules

  1. Verify Azure login and correct subscription before running deployment steps.
  2. Verify Docker is available locally before building the image.
  3. Build and test the Docker image locally first.
  4. Use Azure Container Apps secrets for secret values. Do not place secrets directly in command history unless the user explicitly accepts that tradeoff.
  5. Use a system-assigned managed identity on the Container App.
  6. Grant the Container App AcrPull on the target ACR before expecting the image pull to work.
  7. Ensure the application listens on port 8080 and Container Apps target port is also 8080.
  8. After deployment, validate both /health and /mcp.
  9. Return the fully-qualified MCP URL with https://.

Read the full file on GitHub · 261 lines

Changes

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.

  1. 8d ago First seen · 261 lines · 25 tokens per session scan A 85d0b69651d9

Subscribe to this mod's changes

deploy-mcp-container is an agent published in the GitHub repository pavecer/mcp-server-servicenow (1 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 1,892 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.