What MCP is in one page

WITHOUT MCP:
  Engineer asks Claude: "What's our biggest idle resource?"
  Claude: "I don't have access to your cloud data."
  Engineer: pastes data manually into the conversation
  (slow, error-prone, doesn't scale, no chain calls)

WITH MCP:
  Engineer asks Claude: "What's our biggest idle resource?"
  Claude (via MCP): calls list_idle_resources on ZopNight
  Claude: "i-0xyz123 has been stopped for 47 days, costs $69/month
  in attached EBS volumes alone."

On a default-configured organisation the agent has read access only, which is what makes this walkthrough safe to try on production data.
The engineer never leaves the conversation.

TOOL FAMILIES (about 119 tools: ~85 read, ~34 mutating)
─────────────────────────────────────────────────────
Resources        Costs / billing     Recommendations
Schedules        Overrides           Teams / showback
Budgets          Audit logs          Cloud accounts
Notifications    Organisation        Billing sync
─────────────────────────────────────────────────────
TOTAL: about 119 tools, roughly 85 read and 34 mutating.
Per-family counts move as tools are added; the MCP catalog is
the source of truth. What a given caller sees is narrower: the
advertised tool list is filtered at the gateway to exactly the
tools that caller is allowed to call, so discovery and
authorisation always agree.

WRITE TIER (per organisation, default none):
  none          reads only. The default.
  metadata-only descriptive changes
  reversible    actions that can be undone
  irreversible  destructive actions; additionally requires a
                token bound to the organisation

Enforced at the gateway, together with the caller's live role
and the token's own scope. A global kill switch sits above all
of it and is off by default.

1. NATURAL LANGUAGE INTERFACE
   Engineers ask questions in their IDE, chat, or CLI without
   switching contexts. The AI assistant becomes a query layer over
   ZopNight. "Show me the biggest cost growth this week" is faster
   than navigating to Reports → Cost Trend → filter.

2. AGENT COMPOSITION (chain calls)
   Agent chains MCP calls with other tools:
     "Find the top idle EC2 instance.
      Look up the owner from the tag.
      Draft a Slack message asking them about it."

   Three calls, three different systems, one conversation.
   The MCP server gives the agent the data; agent chains it
   with Slack, source-control, ticketing systems.

Claude Desktop / Cursor / Codex / Claude Code
    ↓ (MCP protocol: JSON-RPC over stdio or HTTP/SSE)
ZopNight MCP server (process running locally or hosted)
    ↓ (PAT-authenticated, gRPC)
ZopNight backend (Config, Discoverer, Aggregator, Recommender, Executor)

LOCAL (default):
  The MCP server runs as a process on the engineer's machine
  Started by their AI tool (Claude Desktop, Cursor, etc.)
  PAT is read from local environment variable
  Tool calls happen over local stdio

HOSTED (enterprise):
  ZopNight runs the MCP server on its infrastructure
  AI tool connects over HTTPS + SSE
  PAT authentication via OAuth handshake
  Customer's AI tool can call the hosted server from anywhere
  (still subject to the org's MCP toggle in M6.3)

RAW ZOPNIGHT API:                       MCP:
  Direct REST/gRPC calls                  Through AI assistant
  Engineer writes code                    Engineer asks in natural language
  Used by: integrations, custom tools     Used by: agent workflows
  Read + write                            Read by default; writes
                                          opt-in per organisation

Both are available. MCP is the agent-friendly path; API is the
programmer-friendly path. They share the same underlying data.

ENGINEER IN CURSOR (MCP connected to ZopNight):

  Engineer: "What's our biggest idle resource right now?"
  Cursor (via MCP):
    Calls list_idle_resources, sort by cost
    Returns: 12 idle EC2 instances
  Response: "i-0xyz123 (m5.2xlarge, stopped 47 days, $69/mo) is
            the biggest single idle resource. Combined idle: $810/mo."

  Engineer: "Get the top 10 recommendations by savings."
  Cursor (via MCP):
    Calls get_top_recommendations(limit=10, sort=savings)
    Returns: 10 recommendations
  Response: "Top 10 by potential savings:
            1. Right-size i-0abc → $1,200/mo
            2. Terminate i-0def (idle 60d) → $480/mo
            ... (full list)
            Total potential: $4,800/mo"

  Engineer: "Describe the business-hours-eu schedule."
  Cursor (via MCP):
    Calls describe_schedule("business-hours-eu")
    Returns: cron config, attached resources, recent firings
  Response: "business-hours-eu fires 8AM and 8PM Mon-Fri Europe/London.
            Attached to 14 resources in the eu-west-1 region.
            Last 5 firings all succeeded. No overrides active."

  Engineer: "Show me overrides created in the last week."
  Cursor (via MCP):
    Calls list_audit_logs(filter={action: "override_create",
                                  time: "7d ago"})
    Returns: 3 override creations
  Response: "3 overrides created in the past week:
            1. jane@platform on 2026-05-15 (24h override on dev-eks)
            2. bob@product on 2026-05-17 (override on staging-rds)
            3. alice@data on 2026-05-19 (until-cancel on ml-cluster)

            One of these (alice's) is still active: worth a check."

The engineer never opens the ZopNight UI. The AI assistant is
the working surface; ZopNight is the data layer.

YOUR AI TOOL:
  □ Claude Desktop
  □ Cursor
  □ Codex (GitHub Copilot, OpenAI Codex CLI)
  □ Claude Code
  □ None of the above
  □ Multiple

WHO USES IT:
  □ All engineers
  □ Some engineers (~__%)
  □ FinOps team specifically
  □ Pilot phase

MCP READINESS:
  Does your AI tool support MCP?    Yes / No / Unsure
  Is MCP enabled at the user level?  Yes / No / Unsure

PLAN to connect:
  □ Set up MCP for one engineer as pilot
  □ Enable org-wide (covered in M6.3)
  □ Defer until later (acceptable; not all teams need this yet)