Bring operational intelligence into local OpenCode
Check deployments, investigate errors and inspect infrastructure from OpenCode. Opsphere brings live operational evidence and guided investigations into your session through MCP.
From a quick endpoint check to a cross-system investigation.
MORE THAN AN MCP TOOL CATALOG
More than an MCP tool catalog
Explaining an operational failure often means checking deployments, logs and infrastructure together. Individual queries are useful; connecting their findings takes context.
Opsphere gives OpenCode direct operational tools and guided workflows for investigations across systems. Sign in through your browser. Provider credentials stay on the Opsphere gateway; your client manages its own sign-in session.
Ops tools don't speak OpenCode: your observability, deployment and paging stack was never built to return structured operational context to a local OpenCode session over MCP. Opsphere sits between them and OpenCode.
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 OpenCode to reconstruct the whole investigation itself.
The intelligence layer belongs to Opsphere
Local OpenCode 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
Local OpenCode can call individual Opsphere tools to query specific systems: Kubernetes resources, AWS infrastructure, observability 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 OpenCode 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.
- Hypotheses
- Evidence
- Confidence
- Timeline
- Verification
OpenCode 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 OpenCode 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 local OpenCode. Source data in the systems that own it.
READ-ONLY BY DEFAULT
Investigate without changing production
Opsphere is read-only by default. Use OpenCode to inspect production, correlate evidence and review recommended next steps. These investigation workflows do not change production.
EXAMPLE
An operational question from OpenCode
Ask OpenCode: “What changed between the last healthy deployment and the current errors?” Opsphere queries the relevant configured systems and returns evidence, possible explanations and next checks. Coverage depends on your integrations and plan.
- Probable cause
- Supporting evidence
- Alternative hypotheses
- Timeline
- Verification
- Recommended next checks
ONE LAYER, MANY INTERFACES
One operational layer across AI workflows
Local OpenCode is one of several interfaces that connect to Opsphere. Whether your team works in OpenCode, Warp, Antigravity, GitHub 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.
IN THE SESSION
Investigations you can ask for in local OpenCode
Incident investigation
Investigate this incident
Multi-service outages and incidents → probable cause with evidence
Endpoint health
Check this endpoint
One hostname: DNS, HTTP, and certificate in one report
CI investigation
Diagnose this pipeline
Failed pipelines and workflows (Professional+)
Post-mortem writer
Write a post-mortem
Structured RCA; optional save to Investigation Memory
OpenCode supports MCP-only setup and an optional project package. The package adds operational skills and guidance; authenticate separately in this client. OpenCode also includes specialized agents and commands. Community includes incident triage, endpoint checks and post-mortems; deep CI diagnostics require Professional, Team or Enterprise.
KEEP EXPLORING
Related platform capabilities
GET STARTED
Connect local OpenCode to your operational stack
Connect OpenCode through MCP, or add the optional project package for reusable operational skills and guidance. Complete browser sign-in, then try “Check DNS for example.com”.