ros2_medkit_mcp copilot-instructions.md

Project instructions for a Python MCP server that connects AI coding agents to ROS 2 diagnostics through a SOVD HTTP API. ROS 2 is a framework for robot software, and SOVD is an API for vehicle or device diagnostics.

In plain words
What is it for?
Guiding work on the HTTP client, server entry points, tool definitions, configuration, models, tests, and project verification steps.
Why use it?
They explain the project structure and required development workflow so an agent can work consistently in the repository.

Instructions file for GitHub Copilot

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/selfpatch/ros2_medkit_mcp/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/selfpatch/ros2_medkit_mcp

Made for: GitHub Copilot.

Per session 1,582 This file is loaded in full into every session.
When invoked 1,582 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 $0.01582 $0.01582
Opus 5 $0.00791 $0.00791
Sonnet 5 $0.00316 $0.00316
Haiku 4.5 $0.00158 $0.00158

Measured 2d ago against content hash 137152bcd634, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ros2_medkit_mcp copilot-instructions.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 2d 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.

.github/copilot-instructions.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions

Project Overview

Python MCP (Model Context Protocol) server that wraps the ros2_medkit SOVD HTTP API, enabling LLM tools to interact with ROS 2 diagnostics. Provides 40+ tools for entity discovery, fault management, operations, configurations, and data access.

Architecture

src/ros2_medkit_mcp/
├── __init__.py
├── config.py           # Pydantic settings (base_url, timeout, auth)
├── models.py           # Pydantic models for tool arguments
├── client.py           # Async HTTP client (SovdClient) wrapping gateway API
├── mcp_app.py          # MCP server with tool definitions and dispatcher
├── server_stdio.py     # stdio transport entrypoint
└── server_http.py      # HTTP/SSE transport entrypoint

Key Components

SovdClient (client.py)

Async HTTP client using httpx for all gateway API calls:

class SovdClient:
    async def get_version(self) -> dict[str, Any]
    async def list_entities(self) -> list[dict[str, Any]]
    async def list_areas(self) -> list[dict[str, Any]]
    async def list_components(self) -> list[dict[str, Any]]
    async def list_faults(self, component_id: str) -> list[dict[str, Any]]
    async def create_execution(self, entity_id, operation_name, request_data, entity_type) -> dict
    async def get_execution_status(self, entity_id, operation_name, execution_id, entity_type) -> dict
    # ... 30+ more methods

MCP Tools (mcp_app.py)

Tools are registered via @mcp.tool() decorator and dispatched by name:

@mcp.tool()
async def sovd_version() -> str:
    """Get SOVD API version information."""
    ...

@mcp.tool()
async def sovd_entities_list(filter: str | None = None) -> str:
    """List all SOVD entities with optional filtering."""
    ...

@mcp.tool()
async def sovd_call_operation(
    entity_id: str,
    operation_name: str,
    request_data: dict | None = None,
    entity_type: str = "components"
) -> str:
    """Execute a SOVD operation (ROS 2 service call)."""
    ...

Read the full file on GitHub · 167 lines

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. 2d ago First seen · 167 lines · 1,582 tokens per session scan A 137152bcd634

Subscribe to this mod's changes

ros2_medkit_mcp copilot-instructions.md is an instructions file published in the GitHub repository selfpatch/ros2_medkit_mcp (6 stars, last pushed 10d ago), licensed Apache-2.0. It adds 1,582 tokens to every session, about $0.0079 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.