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.
npx skills add luiox/openocd-mcp --skill openocd-mcp-debuggit 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/skills/luiox/openocd-mcp/openocd-mcp-debug)<a href="https://agentmods.dev/skills/luiox/openocd-mcp/openocd-mcp-debug"><img src="https://agentmods.dev/badge/skills/luiox/openocd-mcp/openocd-mcp-debug/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/skills/luiox/openocd-mcp/openocd-mcp-debug"><img src="https://agentmods.dev/badge/skills/luiox/openocd-mcp/openocd-mcp-debug.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 | $0.00101 | $0.04149 |
| Opus 5.5 | $0.00040 | $0.01660 |
| Sonnet 5.5 | $0.00020 | $0.00830 |
| Haiku 4.5 | $0.00010 | $0.00415 |
Grade A, and why
openocd-mcp-debug 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 — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
openocd-mcp Embedded Debug Skill
Project Overview
openocd-mcp is a fastmcp-based MCP server that wraps OpenOCD flashing and GDB debugging workflows into AI-callable tools. It reuses the project's existing .vscode/launch.json as the debug target source, requiring no extra configuration.
| Property | Description |
|---|---|
| Repository | D:\GitHub_Repository\openocd-mcp |
| Installation | uv tool install . or uv tool install git+https://github.com/luiox/openocd-mcp.git |
| Run mode | stdio (default, VS Code MCP) / SSE (--sse --host 127.0.0.1 --port 9000) |
| Protocol | GDB/MI2 async protocol (--interpreter=mi2), event-driven, no polling |
| Dependencies | OpenOCD + arm-none-eabi-gdb |
| Platforms | Windows / Linux / macOS |
Core Architecture
AI Client → MCP Protocol → openocd-mcp
├── ProjectConfigManager (parses launch.json)
├── OpenOCDController (start/stop OpenOCD process)
├── GDBMISession (MI2 async protocol communication)
├── RTTClient (real-time log reading)
└── DebugSessionManager (coordinates lifecycle)
MCP Tool Complete Reference
All tools return strings by default. On failure, the response starts with "Error: ".
Project & Configuration
| Tool | Description | Typical Usage |
|---|---|---|
set_project(project_dir) |
Load project .vscode/launch.json |
set_project(project_dir="d:/path/to/project") |
refresh_debug_targets() |
Reload launch.json configurations | Use after modifying launch.json |
get_runtime_config() |
View current OpenOCD/GDB paths and their sources | Use when troubleshooting path issues |
Flash & Debug Lifecycle
| Tool | Description | Typical Usage |
|---|---|---|
flash_download(config_name, firmware_path?) |
One-time firmware flash (no debug session) | flash_download(config_name="Launch (DAP)") |
debug_start(config_name, firmware_path?) |
Start a debug session | debug_start(config_name="Launch (DAP)") |
debug_stop() |
Stop the debug session | debug_stop() |
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 · 409 lines · 101 tokens per session scan A 71045864abbe
openocd-mcp-debug is a skill published in the GitHub repository luiox/openocd-mcp (10 stars, last pushed 4mo ago), licensed MIT. It adds 101 tokens to every session and 4,149 once invoked, about $0.0004 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 skills, from other repositories
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
doca-flow
DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, counters. Trigger on packet steering, classifier, rule-matching, representor, hairpin or 5-tuple-to-queue questions even when "DOCA Flow" is not named. Also covers pipe validation…
competition-firmware-layout
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for firmware images, partition tables, boot chains, update packages, extracted filesystems, embedded configs, and device-facing trust boundaries. Use when the user asks to unpack firmware, map partition layout, inspect bootloader or init…
diagnose-driver-install
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
catc-troubleshoot
Catalyst Center troubleshooting workflows - device unreachable investigation, client connectivity issues, interface down analysis, site-wide outage triage, wireless roaming problems, integration with pyATS for CLI-level diagnostics. Use when the device is managed by Catalyst Center and you want its…