Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

Prism Logo

Prism

Prism lets AI see through IRIS.

MCP server and CLI for InterSystems IRIS development — SQL queries, document management, compilation, debugging, testing, and ObjectScript execution via the Atelier REST API.

Documentation Python 3.12+ License: AGPL v3


Features

  • SQL — Run queries, DDL, stored procedures against any IRIS namespace
  • Documents — Upload, fetch, compile, and delete .cls, .mac, .inc files
  • Terminal — Execute ObjectScript via native (SuperServer) or WebSocket backend
  • Debugging — Interactive step-through debugger with breakpoints, variable inspection, and stack traces
  • Testing — Run %UnitTest test classes, list test methods, view historical results
  • Code Indexing — Build a compact, token-efficient index of all classes using %Dictionary metadata
  • Monitoring — Live IRIS resource dashboard with CPU, memory, disk, process load scoring, and real-time sparkline graphs
  • MCP Server — Expose all tools to AI assistants (Claude Code, Claude Desktop, Cursor, GitHub Copilot)
  • Chatbot — AI agent that orchestrates Prism's MCP tools via natural language, connecting to any OpenAI-compatible LLM
  • GUI — tkinter SQL editor with database navigator, inline-editable results grid, and multi-tab editing (work in progress)
  • Cast Plugins — Extend Prism with custom commands from any Git repository
  • Cross-platform — Windows installer, Linux/macOS via pip/uv

Quick Start

# Install
uv sync

# Configure (or use environment variables)
uv run prism config -u _SYSTEM -p SYS -U http://localhost:52773 -n USER

# Run a SQL query
uv run prism sql "SELECT TOP 5 Name FROM %Dictionary.ClassDefinition"

# Start the MCP server
uv run prism serve

Need an IRIS instance? Start one with Docker:

docker run -d --name iris -p 52773:52773 -p 1972:1972 intersystemsdc/iris-community:latest

Installation

Windows (recommended)

Download the latest installer from GitHub Releases:

  • prism-X.Y.Z-setup.exe — Inno Setup installer. Installs prism.exe to C:\Program Files\prism\ and adds it to the system PATH.
  • prism.exe — Standalone PyInstaller binary. Drop it anywhere on your PATH.

After installing, open a new terminal and verify:

prism --help
prism info

Linux / macOS (development)

git clone https://github.com/AdriaERNI/Prism.git
cd Prism
uv sync
uv run prism --help

Or install via pip:

pip install iris-prism

See the installation guide for more details.

CLI Commands

Command Description
prism sql Run an SQL query
prism terminal Run ObjectScript via native SuperServer
prism ws Run ObjectScript via WebSocket
prism put-doc Upload a file to IRIS
prism get-doc Fetch a document from IRIS
prism list-docs List source documents
prism delete-doc Delete a document
prism compile Compile documents
prism info Server version and namespaces
prism monitor Live IRIS resource monitoring dashboard
prism test Run unit test classes
prism list-tests Discover test classes
prism index Build a compact class index
prism config View or edit settings
prism cast Run custom commands from Git repos
prism serve Start the MCP server
prism setup Register Prism MCP in external AI tools
prism chatbot Start an AI chatbot agent (OpenAI-compatible LLM)
prism gui Launch the tkinter SQL editor GUI (work in progress)

Global option: prism --format toon for TOON output.

Shell completion

Tab completion is available for bash, zsh, fish, and PowerShell:

prism --install-completion    # auto-detect shell

After running, restart your terminal. Then prism conf + Tab auto-completes to prism config, prism s + Tab cycles through sql and serve, etc.

See the commands overview for details.

MCP Tools

12 tools are always available (including monitor_system), 5 workspace-gated (put_document, put_and_compile, list_files, read_file, run_shell), and 9 debug-gated (debug_*) — up to 26 total.

See the full tool reference for details.

MCP Client Configuration

Tip: Run prism setup to automatically register Prism MCP in Claude Code, Codex CLI, OpenCode, and Hermes Agent. See setup docs for details.

The manual configurations below are for clients not yet supported by prism setup (Claude Desktop, Cursor, VS Code Copilot).

Claude Code

Add to ~/.claude.json:

{
  "mcpServers": {
    "prism": {
      "type": "http",
      "url": "http://localhost:3000/mcp"
    }
  }
}

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "prism": {
      "command": "prism",
      "args": ["serve"]
    }
  }
}

GitHub Copilot (VS Code)

Add to .vscode/mcp.json:

{
  "servers": {
    "prism": {
      "type": "http",
      "url": "http://localhost:3000/mcp"
    }
  }
}

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "prism": {
      "url": "http://localhost:3000/mcp"
    }
  }
}

Environment Variables

Variable Default Description
IRIS_BASE_URL http://localhost:52773 IRIS instance URL
IRIS_USERNAME _SYSTEM Authentication username
IRIS_PASSWORD SYS Authentication password
IRIS_NAMESPACE USER Default namespace
IRIS_WORKSPACE (empty) Local directory for MCP file I/O tools
IRIS_COMPILE_FLAGS cuk Compiler flags
IRIS_DEBUG_ENABLED false Enable debug tools (debug_*)
IRIS_TERMINAL_METHOD native Terminal backend: native or ws

See the configuration guide for all 28 settings.

Project Structure

src/prism/
├── settings.py        # Pydantic settings (env, .env, config.json)
├── iris/
│   ├── sdk/            # HTTP client, workspace, debug protocols, terminal
│   └── api/            # Thin IRIS REST API wrappers (sql, docs, compile, debug, monitor)
├── monitor/           # IRIS monitoring: Prometheus parser, scorer, dashboard
│   ├── parser.py       # Parse Prometheus exposition format
│   ├── scorer.py       # Compute 0-100 load score from metrics
│   ├── dashboard.py    # Rich terminal dashboard (sparklines, bars, history)
│   └── __init__.py     # collect_snapshot() — API → parse → score
├── mcp/               # MCP tools with @logged_tool decorator
│   ├── _decorator.py   # Logging + auto-discovery
│   ├── server.py       # FastMCP server
│   └── *.py            # One module per tool domain (12 always + 5 gated + 9 debug)
├── chatbot/           # AI chatbot agent (OpenAI-compatible LLM)
│   ├── agent.py        # Tool-calling agent with conversation memory
│   └── skills.py       # Built-in skills (code review, testing, etc.)
├── gui/               # tkinter SQL editor GUI
│   ├── app.py           # Main window, menu, layout, shortcuts
│   ├── theme.py         # Dark colour palette
│   ├── controllers/     # SQL execution controller (async)
│   └── widgets/         # DatabaseTree, SQLEditor, ResultsTable, StatusBar, Toolbar
├── cast/              # Cast plugin system (import-based Typer plugins)
│   └── manager.py      # Clone, import, cache, run commands
└── cli/               # Typer CLI commands (async wrappers)
    └── commands/       # One module per command (18 commands)

Testing

uv run pytest tests/unit/ -v                    # No IRIS needed (966 tests)
IRIS_BASE_URL=http://localhost:52773 \
  uv run pytest tests/integration/ -v            # Needs IRIS (87 tests)
uv run pytest tests/gui/ -v                      # GUI tests (29 tests, needs display)
uv run ruff check . && uv run ruff format --check .  # Lint

Full testing guide: docs/testing.md

Releases

Prism follows a Git Flow release workflow with two protected branches: development (active work) and main (stable releases).

Download the latest Windows installer or standalone exe from GitHub Releases.

Artifact Description
prism-X.Y.Z-setup.exe Windows installer (Inno Setup, adds to PATH)
prism.exe Standalone Windows binary (PyInstaller)
iris_prism-X.Y.Z-py3-none-any.whl Python wheel (pip install iris-prism)

See the release guide for the full release workflow, branch model, hotfix procedure, and CI pipeline details.

Documentation

Full documentation at adriaerni.github.io/Prism

License

Copyright © 2026 Adria Sanchez.

Licensed under the GNU Affero General Public License v3.0 (AGPL-3.0). You may use, modify, and distribute this software freely, including for commercial purposes, as long as you share your source code under the same license. SaaS/hosting providers must also share their source code (network clause).

See LICENSE for full terms.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

iris_prism-0.2.2b8-py3-none-any.whl (210.7 kB view details)

Uploaded Python 3

File details

Details for the file iris_prism-0.2.2b8-py3-none-any.whl.

File metadata

  • Download URL: iris_prism-0.2.2b8-py3-none-any.whl
  • Upload date:
  • Size: 210.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for iris_prism-0.2.2b8-py3-none-any.whl
Algorithm Hash digest
SHA256 42c52f995d3bcc568f57bef71ad256f10a0c7d080d9c7f48cc77e5ecb5f1cef6
MD5 ec6557a1e7453cd80932057b8f60e671
BLAKE2b-256 9e16dcd5a6ccfd84f00bf27f754519c0459bf729be3a2a485764f912bb38f0b6

See more details on using hashes here.

Release history Release notifications | RSS feed

This release

0.2.2b8 This release

1 file

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page