opencode-cli-mcp CLAUDE.md

A set of project instructions for working on opencode-cli-mcp, an MCP server that connects OpenCode’s HTTP service to agent tools and a web dashboard. It documents how to install, run, test, and inspect the project.

In plain words
What is it for?
Use it when developing, testing, or navigating the opencode-cli-mcp project, including its Python backend, web frontend, and MCP tools.
Why use it?
It gives coding agents the project’s commands, structure, ports, and conventions in one place. This reduces guesswork when changing or checking the repository.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/sandraschi/opencode-cli-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/sandraschi/opencode-cli-mcp
Per session 535 This file is loaded in full into every session.
When invoked 535 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00535 $0.00535
Opus 5 $0.00267 $0.00267
Sonnet 5 $0.00107 $0.00107
Haiku 4.5 $0.00053 $0.00053

Measured yesterday against content hash ba06d0a79b51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opencode-cli-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 52 lines

What it actually says

opencode-cli-mcp

MCP server that wraps opencode's opencode serve HTTP API into MCP tools, with a SOTA fleet webapp dashboard.

Build & Test

  • Install: uv sync
  • Run MCP server: uv run -m opencode_cli_mcp.server
  • Run webapp backend: uv run python -m api.main
  • Run webapp frontend: cd web_sota && npm run dev
  • Start all: .\start.ps1
  • Lint: uv run ruff check .
  • Test: uv run pytest
  • TypeScript check: cd web_sota && npx tsc --noEmit

Architecture

  • MCP server talks to opencode serve HTTP API (default http://127.0.0.1:4096)
  • Webapp backend (FastAPI, port 10951) bridges MCP tools to REST
  • Webapp frontend (Vite, port 10950) proxies /api to backend
  • Tools in src/opencode_cli_mcp/tools/: sessions, runs, agent, status
  • Shared tool registry in src/opencode_cli_mcp/registry.py
  • ensure_server() is wired into all session/status tools
  • OpenCode custom tools in .opencode/tools/ - TS definitions calling backend API
  • Docs served via GET /api/docs, tool source via GET /api/opencode-tools
  • Ports: 10950 frontend / 10951 backend / 4096 opencode

Key Patterns

  • opencode_run_agent(prompt, wait=false) launches background agent
  • opencode_get_run_status(job_id) polls for completion
  • opencode_session_diff(session_id) reviews changes
  • opencode_cancel_run(job_id) kills stuck agent

API Routes

Prefix Purpose
/api/capabilities Health + runtime introspection
/api/opencode/* Proxy to opencode serve
/api/runs/* Agent run tracking
/api/tools Tool definitions
/api/fleet Fleet app status
/api/system OS/GPU/memory info
/api/docs/* Documentation serving
/api/opencode-tools/* OpenCode custom tool definitions
/api/settings App settings CRUD

Webapp Pages (11)

Dashboard, Sessions, Projects, Tools Hub, OC Tools, Apps Hub, Chat, Help, Settings, Status Audit, API Docs

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 52 lines · 535 tokens per session scan A ba06d0a79b51

Subscribe to this mod's changes

opencode-cli-mcp CLAUDE.md is an instructions file published in the GitHub repository sandraschi/opencode-cli-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 535 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.