agentmods.dev

QgisStreamMCP: Instructions file for Claude Code

CLAUDE.md

QgisStreamMCP CLAUDE.md is an instructions file for Claude Code from nic01asFr/QgisStreamMCP. It costs 2,355 tokens per session, scanned A, original, MIT.

Project instructions for an add-on that exposes a QGIS Desktop session to an AI agent. QGIS is desktop software for creating, analyzing, and displaying maps and geographic data.

In plain words
What is it for?
Use them when developing tools for QGIS, running geographic-data workflows, creating maps and print layouts, or working with the server and its remote desktop stream.
Why use it?
They explain the container's connected services, the bridge into QGIS, and the available actions. This gives an agent the context needed to change or use the mapping system correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is nic01asFr/QgisStreamMCP's own configuration. It tells Claude Code how to work on QgisStreamMCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything QgisStreamMCP configures →

not rated 10repo 6mo ago A scan 2,355 tokens original MIT
View source ↗ nic01asFr/QgisStreamMCP
Reuse

Borrowing it

Nothing to install: this file belongs to nic01asFr/QgisStreamMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nic01asFr/QgisStreamMCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/nic01asFr/QgisStreamMCP

Made for: Claude Code.

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 QgisStreamMCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nic01asfr/qgisstreammcp/claude-md/github.svg)](https://agentmods.dev/instructions/nic01asfr/qgisstreammcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nic01asfr/qgisstreammcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nic01asfr/qgisstreammcp/claude-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.

agentmods 80×15 button for QgisStreamMCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nic01asfr/qgisstreammcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nic01asfr/qgisstreammcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,355 This file is loaded in full into every session.
When invoked 2,355 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02355 $0.02355
Opus 5 $0.01177 $0.01177
Sonnet 5 $0.00471 $0.00471
Haiku 4.5 $0.00235 $0.00235

Measured 9d ago against content hash 33fa4a8a9853, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

QgisStreamMCP CLAUDE.md scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:8080/health
CLAUDE.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — QgisStreamMCP

Project

QgisStreamMCP exposes a full QGIS Desktop instance as an MCP Server. Single Docker container with QGIS GUI + Xvfb + noVNC + MCP Server.

Architecture

Container (single)
  supervisord
  ├── Xvfb :99 (virtual display)
  ├── fluxbox (window manager)
  ├── QGIS Desktop (GUI, PyQGIS bridge via startup script)
  ├── x11vnc → websockify/noVNC (:6080)
  ├── api_server.py (FastAPI REST :8080)
  ├── main_mcp.py (MCP Server :8100, 40 tools)
  └── stream_server.py (MJPEG :8081)

Communication: MCP Server → UNIX socket → QGIS Bridge (runs inside QGIS)

Key files

  • main_mcp.py — MCP Server with 40 tools, 10 resources, 3 prompts
  • src/qgis_bridge.py — Runs inside QGIS, UNIX socket listener, 45 actions
  • src/qgis_helpers.py — Python helpers injected into execute_python
  • src/api_server.py — FastAPI REST wrapper
  • src/stream_server.py — MJPEG stream
  • skills/*.md — MCP Resources (PyQGIS, Processing, cartography, smart loading, recipes, etc.)
  • templates/*.qpt — Print layout templates (A3 landscape, A4 portrait)
  • templates/web/ — Leaflet HTML templates (standard, flood, temporal)
  • recipes/*.json — Workflow recipes (5 pre-built analyses)
  • datasources.json — 30+ pre-configured French data sources (IGN, OSM, BD TOPO, Georisques)
  • Dockerfile — Single container build
  • supervisord.conf — Process orchestration
  • entrypoint.sh — Container startup

MCP Tools (40)

Core

  • execute_python — Run PyQGIS code with helpers module
  • get_screenshot — Capture QGIS canvas
  • get_project_info / new_project / open_project / save_project
  • qgis_desktop_ui — Open interactive QGIS view in conversation

Data loading

  • set_study_zone — Define study area (geocodes, stores bbox)
  • get_study_zone — Read stored zone
  • smart_load — Load from catalog (WFS → local GPKG, rasters stream)
  • list_datasources / add_from_catalog — Browse and add data sources
  • add_layer / remove_layer — Manual layer management

Read the full file on GitHub · 217 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. 9d ago First seen · 217 lines · 2,355 tokens per session scan A 33fa4a8a9853

Subscribe to this mod's changes

QgisStreamMCP CLAUDE.md is an instructions file published in the GitHub repository nic01asFr/QgisStreamMCP (10 stars, last pushed 6mo ago), licensed MIT. It adds 2,355 tokens to every session, about $0.0118 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens