Borrowing it
Nothing to install: this file belongs to luiox/openocd-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/luiox/openocd-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/luiox/openocd-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/luiox/openocd-mcp/agents-md)<a href="https://agentmods.dev/instructions/luiox/openocd-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/luiox/openocd-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/luiox/openocd-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/luiox/openocd-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01261 | $0.01261 |
| Opus 5.5 | $0.00504 | $0.00504 |
| Sonnet 5.5 | $0.00252 | $0.00252 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
openocd-mcp AGENTS.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 1mo ago.
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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
openocd-mcp — AI Agent Guide
What This Project Does
An MCP server (via fastmcp) that exposes OpenOCD flashing & debugging workflows through natural-language-callable tools. It reuses the project's .vscode/launch.json as the source of debug targets — no extra config needed.
Quick Start
# Install dependencies
uv sync
# Run with custom tool paths
uv run openocd-mcp --openocd-path openocd --gdb-path arm-none-eabi-gdb
# Run in SSE/HTTP mode (for local AI clients)
uv run openocd-mcp -sse --host 127.0.0.1 --port 9000
Parameter priority: CLI args > env vars > config.json > built-in defaults.
Key Architecture
| Module | Responsibility |
|---|---|
ProjectConfigManager |
Parses .vscode/launch.json, resolves ${workspaceFolder}, caches configs |
OpenOCDController |
Spawns OpenOCD for flash (program) or as GDB server (target remote :3333) |
GDBMISession |
GDB/MI 异步会话，协议解析、事件驱动、无需轮询提示符 |
DebugSessionManager |
Single active session; coordinates OpenOCD + GDB lifecycle |
- All tools return strings. Failures are prefixed with
"Error: ". launch.jsonsupports JSON with C-style comments and trailing commas (custom parser in_parse_launch_content).
MCP Tools
| Tool | Purpose |
|---|---|
set_project(project_dir) |
Load .vscode/launch.json from a project |
refresh_debug_targets() |
Reload launch.json configs |
flash_download(config_name, firmware_path?) |
One-shot flash via OpenOCD program |
debug_start(config_name, firmware_path?) |
Start OpenOCD + GDB, load firmware, optionally run to entry point |
debug_attach(config_name, firmware_path?) |
Attach to running target without reset/download (Attach mode) |
debug_stop() |
Kill OpenOCD & GDB |
debug_command(command) |
Send arbitrary GDB command to active session |
debug_continue() |
Continue target execution (async, returns immediately via MI ^running) |
debug_interrupt() |
Interrupt/pause running target (MI -exec-interrupt, Windows fallback to telnet halt) |
debug_state() |
Get target execution state (running/stopped) and last stop reason |
debug_status() |
JSON with session state, PIDs, available configs |
get_runtime_config() |
Show effective OpenOCD/GDB paths and their sources |
read_rtt(max_lines) |
Read RTT log from active debug session |
shutdown() |
Gracefully shut down MCP server |
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.
- 1mo ago First seen · 85 lines · 1,261 tokens per session scan A 8944fc496909
openocd-mcp AGENTS.md is an instructions file published in the GitHub repository luiox/openocd-mcp (10 stars, last pushed 4mo ago), licensed MIT. It adds 1,261 tokens to every session, about $0.0050 per session on Opus 5.5. 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.