mcp-server-ascom CLAUDE.md

mcp-server-ascom CLAUDE.md is an instructions file for coding agents from stellarpunk/mcp-server-ascom. It costs 2,226 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for an MCP server that connects Claude to ASCOM astronomy devices, such as telescopes. It covers setup, running the server, and testing.

In plain words
What is it for?
Use it when developing or testing this ASCOM MCP server, including starting its Python environment, running the server, and running unit, integration, or protocol tests.
Why use it?
It gives a coding agent the project’s setup steps, architecture, and expected error-handling patterns in one place.

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/stellarpunk/mcp-server-ascom/claude-md
Clone the repo
git clone --depth 1 https://github.com/stellarpunk/mcp-server-ascom

Wrote 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.

agentmods badge for mcp-server-ascom CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/stellarpunk/mcp-server-ascom/claude-md.svg)](https://agentmods.dev/instructions/stellarpunk/mcp-server-ascom/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/stellarpunk/mcp-server-ascom/claude-md"><img src="https://agentmods.dev/badge/instructions/stellarpunk/mcp-server-ascom/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,226 This file is loaded in full into every session.
When invoked 2,226 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 $0.02226 $0.02226
Opus 5 $0.01113 $0.01113
Sonnet 5 $0.00445 $0.00445
Haiku 4.5 $0.00223 $0.00223

Measured 4d ago against content hash 8174d4e8d247, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-server-ascom 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 4d 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.

CLAUDE.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - ASCOM MCP Server (v0.4.0)

Bridge ASCOM devices to Claude via MCP. Now with instant connections!

Quick Start

# Activate venv
source .venv/bin/activate

# Run server
python -m ascom_mcp

# Run tests
pytest tests/unit/ -v         # Unit tests (40+ passing ✅)
pytest tests/integration/ -v  # Integration tests (NEW!)
pytest tests/mcp/ -v          # MCP protocol tests

Architecture

Our server is a "USB cable" between MCP and ASCOM:

Claude → MCP Protocol → Our Server → HTTP/Alpaca → seestar_alp → Telescope
         (FastMCP 2.0)    (Translation)   (ASCOM)     (Community)   (Hardware)
             ↑                ↓
             └── Event Stream ←── Real-time events from devices (v0.4.0)

FastMCP 2.0 Patterns

1. Context Parameter (Required)

@mcp.tool()
async def telescope_goto(ctx: Context, device_id: str, ra: float, dec: float):
    await ctx.info(f"Slewing to RA={ra}, Dec={dec}")  # Direct logging
    # NOT ctx.logger.info() - that's wrong!

2. ToolError for User-Friendly Errors

raise ToolError(
    "Device not found. Run discovery first.",
    code="device_not_found",
    recoverable=True,
    details={"suggestions": ["Try: discover_ascom_devices"]}
)

3. Structured Logging

await ctx.debug("tool_called: telescope_goto")
await ctx.info(f"connected: device_id={device_id}")
await ctx.error(f"failed: {str(e)}")

Key Commands (v0.4.0 IoT Patterns)

Direct Connection (No Discovery Required!)

# Connect instantly with connection string
telescope_connect(device_id="[email protected]:5555")

# Or use pre-configured device
telescope_connect(device_id="telescope_1")

# Discovery only when adding new devices
discover_ascom_devices(timeout=5.0)  # Optional!

# Initialize telescope (CRITICAL for Seestar!)
telescope_custom_action(
    device_id="Telescope_0",
    action="action_start_up_sequence",
    parameters={"lat": 40.745, "lon": -74.0256, "move_arm": True}
)

Read the full file on GitHub · 317 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. 4d ago First seen · 317 lines · 2,226 tokens per session scan A 8174d4e8d247

Subscribe to this mod's changes

mcp-server-ascom CLAUDE.md is an instructions file published in the GitHub repository stellarpunk/mcp-server-ascom (0 stars, last pushed 1y ago), licensed MIT. It adds 2,226 tokens to every session, about $0.0111 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.