cig
Enables AI agents to detect and operate Windows programs built with Electron by generating typed UI actions, such as reading element state, setting text, toggling options, invoking menus, and handling dialogs.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Control Interface Generator (CIG)
CIG lets an AI agent operate an ordinary Windows program without screenshots or synthetic mouse clicks.
It works in four steps:
It detects what the program is built with: Win32, WinForms, WPF, WinUI, Qt, Electron or a console program.
It looks that framework up in a capability library, which is data rather than code.
It applies rules that turn each UI element into a typed action, such as
set_text,set_checked,choose,menuoranswer_dialog.It serves those actions as an MCP server.
A program is handled through its framework's library entry, never through code written for that one program.
Safety
Every action passes the safety layer before it reaches a program:
Reads are always allowed.
Writes are refused while the person at the machine is using it, unless the call carries
confirmwith the person's own words.For third-party programs, a write is refused outright when that program's window is in front and has had recent real input.
confirmdoes not override this.Destructive actions (delete, remove, discard, "Don't Save"... in eleven languages) always need
confirm.Password fields, credential and security windows, and browsers are never acted on.
Every call is logged as JSON lines, refusals included, with secrets redacted. Files an action is known to change are backed up first, and
cig_undorestores them.dry_runchecks everything and returns a preview without acting.
Related MCP server: nexusos-semantic
Tools (MCP, stdio)
Tool | What it does |
| Version, loaded adapters, the presence reading and the policy thresholds |
| Programs with windows that CIG can see |
| Framework, version and ranked adapters for a program |
| Starts a program at normal integrity |
| Compact element tree with stable short ids |
| The generated typed action set, each with a JSON input schema |
| Performs one action ( |
| Reads one element's current state |
| Waits for an element or window |
| One screenshot of the program's window, on request only |
| The action log |
| Restores a backup |
To register it:
claude mcp add --scope user cig -- py -3 "<repo>\cig_server.py"Layout
Path | What it holds |
| The engine, safety layer, detector and adapters |
| Framework entries, rules, the destructive-word lexicon and schemas, all data |
| Thresholds, plus the allow and deny lists |
| Unit and safety tests on recorded fixtures ( |
Licence
GPL-3.0-or-later.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Connect ChatGPT, Claude, Cursor or VS Code to your Windows PC: files, terminal, browser, apps.
Automate 1,000+ services from any MCP-compatible AI agent: build Applets, run actions and queries.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to seamlessly integrate with the Windows operating system, performing tasks such as file navigation, application control, UI interaction, and QA testing via the MCP protocol.-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to access and act on web, desktop, and mobile interfaces via semantic accessibility trees, using MCP tools for querying, navigating, and executing deterministic UI actions without relying on screenshots or pixel coordinates.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables an MCP host to observe and control Windows desktop applications deterministically: reading UIA control trees, OCR text and pixel diffs, clicking, typing, scrolling and window management, plus verbatim text reading/appending via ValuePattern/TextPattern. Visual judgment is delegated back to the host model's own multimodal context through annotated screenshots, numbered element cards, grid maps and crosshair zoom-ins, so no separate vision model is needed.1AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to inspect and operate Windows applications through structured UI Automation maps, humanized mouse and keyboard input, and on-demand screenshots or OCR via MCP. It supports locating elements by role, name, or query; clicking, typing, scrolling, window management, event watching, and chained multi-step actions without relying on image analysis.MIT