$ loading_
Let AI assistants use OpenCode CLI and multiple models through one interface.
The materials indicate a local MCP server that interacts with the OpenCode CLI, with no declared secrets or remote endpoints; the main security surface is the inherent local code-execution capability of this tool class. Because the repository is open source and auditable, but comes from a third-party registry with low adoption and unknown maintenance, it is better classified as caution rather than high risk.
The materials explicitly state that no keys or environment variables are required, and there is no request for API tokens, account credentials, or other long-lived secrets; based on the provided facts, credential exposure and abuse risk appears low.
No remote endpoints are declared, and the README does not list any external APIs or upload destinations; from the provided materials, there is no evidence of user data being sent to unknown external services.
The system checks explicitly flag executes-code, and the description says the MCP server interacts with the OpenCode CLI, which typically implies invoking a local CLI and spawning local processes. This is a normal capability for this tool class and warrants caution, but the materials do not show unusually broad privileges beyond the stated purpose.
The materials do not explicitly define the read/write scope, but as an MCP tool that interacts with a local CLI, it would typically have access at least to local session context or relevant working-directory data. There is no stated need for full-system access or other clearly excessive permissions unrelated to its purpose, so caution is appropriate.
A positive factor is that there is an open-source repository, making source review possible; however, it comes from a third-party registry, has no declared license, only 0 stars, and unknown maintenance status, so trust is limited. There is no evidence of closed-source data exfiltration or other strong red flags, so this does not rise to high risk.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "opencode-mcp-tool" yet — see the docs or source repo.
Using opencode-mcp-tool via OpenCode CLI, enable plan mode to create a step-by-step implementation plan for adding a caching layer to an existing Node.js API, then compare recommendations from two models.
A structured implementation plan plus a comparison of strengths, weaknesses, and differences between model suggestions.
Use opencode-mcp-tool to call two different models through a unified interface, analyze performance bottlenecks in this Python code, and provide a merged optimization recommendation.
Analysis from each model and a consolidated performance optimization plan.
Interact with OpenCode CLI through opencode-mcp-tool, review the current project's build scripts, identify potential issues, and provide actionable fixes.
A list of build script issues, risk explanations, and actionable remediation steps.
Build, debug, and manage software tasks with natural language across LLMs.
Provide AI agents with coding standards, testing, planning, and requirements guidance.
Enable Claude Code to perform coding tasks through the OpenAI Codex CLI.
Connect to the mcp API via MCP to extend AI tool capabilities.
Get technical advice, code reviews, and explanations via Codex CLI.
Safely run Python code with AI and MCP tool integration.