All sources

OpenCode Documentation for AI Agents & MCP Integration

Explore OpenCode documentation to integrate AI coding agents with development environments using ACP, define reusable agent behaviors with SKILL.md, and extend functionality via MCP servers. Access guides for configuring AI models like OpenCode Zen and Go, and learn about secure enterprise deployment and data handling.

View Structure
Pages
36
Sections
518
Tokens
~108.7K
Refreshed
Sep 23, 2026
Monitoring
Active

Works with

  • ChatGPT
  • Claude
  • Cursor
  • MCP clients
Solutions

What AI Agents Can Do With This Source

Use OpenCode Documentation to complete source-specific tasks, make informed decisions, and follow evidence-backed workflows.

Integrating OpenCode with development environments

The documentation provides configuration steps and examples for using OpenCode via the Agent Client Protocol (ACP) in compatible editors like Zed and JetBrains.

Defining reusable agent behaviors for OpenCode

The documentation details how to create SKILL.md files with required frontmatter and placement rules for OpenCode to discover and load custom skills.

Extending OpenCode with external tools and plugins

The documentation explains how to add local or remote tools using the Model Context Protocol (MCP) by configuring them in the OpenCode Config.

Configuring AI models for OpenCode agents

The documentation outlines how to connect to LLM providers, including OpenCode Zen and Go, by running the /connect command and pasting an API key.

Deploying OpenCode securely in an enterprise

The documentation describes OpenCode Enterprise features like central config, SSO integration, and internal AI gateway use to ensure data stays within infrastructure.

Researching optimal AI models for coding tasks

OpenCode Zen and Go provide curated lists of tested and verified models, along with their respective access methods and performance characteristics, to guide model selection.

Advantages

Why Use Bulkgrid for AI-Ready Sources

Bulkgrid turns important websites into fresh, queryable, AI-ready sources without making teams maintain the infrastructure.

Spend Fewer Tokens

Retrieve the right source context instead of sending large pages, pasted docs, or noisy search results into every prompt.

Improve Answer Accuracy

Ground responses in current, source-backed evidence to reduce hallucinations and avoid relying on stale model memory.

Use Fresh Source Data

Keep important websites automatically recrawled and updated so AI is not working from old content.

Query Instantly

Search already-indexed source content immediately instead of crawling pages at question time.

No Infrastructure Maintenance

Bulkgrid handles crawling, rendering, retries, storage, indexing, recrawls, and change detection.

Change Detection

See when pages are added, removed, updated, or fail so teams can react without checking manually.

Give Your Agents Up-to-Date Knowledge from OpenCode

Search and use knowledge from OpenCode in ChatGPT, Claude, Cursor, and any MCP-compatible client.