Opsphere

Bring operational intelligence into GitHub Copilot CLI through MCP

Opsphere connects local GitHub Copilot CLI to the systems you already run — infrastructure, observability, deployments, code and edge — through MCP, so a CLI session can ask a direct operational question or open a structured, evidence-backed investigation.

From atomic operational tools to structured investigations and reusable context.

Install Copilot PluginView Documentation (opens in new tab)

MORE THAN AN MCP TOOL CATALOG

More than an MCP tool catalog

A flat list of tool calls is useful, but it is where most MCP agent integrations stop. GitHub Copilot CLI then has to reconstruct every cross-system investigation from scratch.

Opsphere adds a structured operational intelligence layer behind those tools. In a local GitHub Copilot CLI session, engineers can run an atomic check when a precise query is enough, or delegate to specialized agents that correlate signals across systems into one evidence-backed investigation — with browser-based sign-in, zero provider secrets stored on your machine, and session tokens managed securely by Copilot CLI.

Ops tools don't speak GitHub Copilot CLI: your observability, deployment and paging stack was never built to return structured operational context to a GitHub Copilot CLI session over MCP. Opsphere sits between them and Copilot CLI.

  • Simple checks should stay simple

    For a direct question — one Kubernetes resource, one endpoint, one deployment list — an atomic tool is the right tool. Opsphere keeps those available.

  • Multi-system troubleshooting needs structure

    When a question spans deployments, errors, cluster state and edge checks, a flat list of tool calls forces GitHub Copilot CLI to reconstruct the whole investigation itself.

  • The intelligence layer belongs to Opsphere

    GitHub Copilot CLI is the interface where engineers ask and act. The operational capabilities, scoping and guardrails live in Opsphere.

TWO WAYS IN

Atomic tools and high-level investigations

Opsphere does not force every question into a long workflow. Simple checks stay simple; complex investigations use higher-level context and structure.

  • Atomic tools

    For direct operational questions: inspect a Kubernetes resource, check an HTTP endpoint, list deployments, query AWS inventory, search errors, inspect DNS and TLS state.

  • High-level investigations

    For cross-system questions: investigate an outage, diagnose environment degradation, correlate deployment and error signals, and return structured evidence and verification.

ATOMIC TOOLS

Query individual systems directly

GitHub Copilot CLI can call individual Opsphere tools to query specific systems: Kubernetes resources, AWS infrastructure, Datadog errors, deployments, DNS / HTTP / TLS, repositories, CDN and edge state. A direct query when a precise answer is all you need.

EVIDENCE-BACKED INVESTIGATIONS

Run structured operational investigations

High-level Opsphere workflows can return a structured investigation to GitHub Copilot CLI instead of an opaque answer. Depending on the workflow, the result can include hypotheses, evidence, confidence, timeline, verification, observed facts, inferences and recommended next steps.

  1. Hypotheses
  2. Evidence
  3. Confidence
  4. Timeline
  5. Verification

GitHub Copilot CLI can reason over structured operational evidence instead of reconstructing the entire investigation from raw tool calls.

OPERATIONAL CONTEXT

Give high-level workflows reusable operational context

Opsphere keeps Operational Context separate from the model and the client. That context can include relevant relationships between services, environments, repositories and previous investigations.

High-level Opsphere workflows can use shared operational context, while atomic tools remain focused on individual systems.

SOURCE SYSTEMS AUTHORITATIVE

Operational context without copying your entire stack into the session

Opsphere does not load all of your telemetry or infrastructure into the GitHub Copilot CLI session. The source systems keep the operational data; Opsphere queries what is needed and returns structured findings and context.

Operational intelligence in Opsphere. Model interaction in GitHub Copilot CLI. Source data in the systems that own it.

READ-ONLY BY DEFAULT

Investigate without changing production

GitHub Copilot CLI can use Opsphere to inspect and investigate operational systems while Opsphere stays read-only by default. Recommendations can be structured. Opsphere does not apply those changes in production.

EXAMPLE

Example: investigate a deployment regression from GitHub Copilot CLI

An engineer asks, in local GitHub Copilot CLI: "Why did checkout-api start failing after the last production deployment?" Opsphere works through deployment evidence, observability evidence, Kubernetes state, network and edge checks, and relevant operational context.

  1. Probable cause
  2. Supporting evidence
  3. Alternative hypotheses
  4. Timeline
  5. Verification
  6. Recommended next checks

ONE LAYER, MANY INTERFACES

One operational layer across AI workflows

GitHub Copilot CLI is one of several interfaces that connect to Opsphere. Whether your team works in Copilot CLI, Cursor, Codex, Claude Code, or the Web Client, they consume the same operational layer through supported surfaces, keeping capabilities, context and guardrails consistent.

Different AI interface. Same Opsphere operational layer.

SUBAGENTS & GUIDED SKILLS

Ready-made operational flows for GitHub Copilot CLI

  • Incident investigation

    outage-triage

    Multi-service outages and incidents → probable cause with evidence

  • Endpoint health

    endpoint-health

    One hostname: DNS, HTTP, and certificate in one report

  • CI investigation

    ci-investigator

    Failed pipelines and GitHub Actions (Professional+)

  • Post-mortem writer

    postmortem-writer

    Structured RCA; optional save to Investigation Memory

Copilot agents are invoked by name for focused investigations (such as "Use outage-triage"). Onboarding is guided by opsphere-onboarding. This package supports local GitHub Copilot CLI; Copilot cloud agent remains outside this package. Community covers triage, endpoints, and post-mortems; deep CI diagnostics require Professional, Team, or Enterprise plans.

KEEP EXPLORING

Related platform capabilities

GET STARTED

Connect GitHub Copilot CLI to your operational stack

Install the Opsphere plugin for GitHub Copilot CLI, complete browser sign-in once, and bring operational context and evidence-backed investigations into a local CLI session. The plugin is opsphere, package opsphere-copilot, from the public marketplace opsphere-io/opsphere-plugin.

Connect Copilot CLI