Key insight: Static context files are great but go stale. Connecting OpenCode directly to live systems — Confluence, Jira, Webex, Airtable — means it always has current information. And with write access, it stops being an assistant and becomes an agent: publishing pages, creating tickets, deploying sites.

What is an MCP?

MCP stands for Model Context Protocol. It's a standard that lets OpenCode connect to external tools and data sources — think of it as a plugin system, or a USB cable between OpenCode and another system. Each MCP gives the agent a new set of capabilities: the ability to read from, or write to, a specific tool.

Without MCPs, OpenCode only knows what you paste into the conversation or upload as files. With MCPs, it can reach out to live systems directly — pulling current data, or pushing completed work.

Two types of access

MCPs can give OpenCode two different relationships with a tool. Most setups use both.

Reading data

Passive use — OpenCode pulls context, changes nothing.

  • Pull the latest version of a Confluence playbook as context
  • Read open Jira tickets before drafting a status update
  • Fetch recent Webex messages to summarise a discussion
  • Read Airtable records for data-driven analysis
  • Search your email or calendar via Outlook for relevant context

Low risk. A good place to start when first configuring an MCP — get comfortable reading before granting write access.

Taking action

Agentic use — OpenCode acts directly, no copy-paste.

  • Publish a new Confluence page from a prompt
  • Create or update Jira tickets and dashboards
  • Add records to Airtable — e.g. logging a use case
  • Build and deploy a GitHub Pages site
  • Send a Webex message or create a meeting invite
  • Send an email or create a calendar event via Outlook

Real consequences. The output is the deliverable — not a draft to copy into something else.

The read → act pattern

The two modes naturally work together. A typical agentic workflow might be:

  1. Read open Jira tickets to understand what's in flight
  2. Read the relevant Confluence playbook for context
  3. Draft a status update or analysis
  4. Publish the output back to Confluence, or create a Jira ticket with the findings

That entire loop — read context, reason, act — runs inside a single OpenCode session with no manual steps.

A note on safety

Write access means real consequences. A few practices that help: