Overview
This is an enterprise-grade feature available exclusively to Classiq’s enterprise customers.
- Modeling — write quantum algorithms in Python using Classiq.
- Synthesis — compile a model into a quantum program with
synthesize(), constraints, and hardware targets.
- Execution — run circuits:
sample, observe, calculate_state_vector, and variational loops.
- Post-processing — interpret results: histograms, energy curves, and most-probable states.
- Analyzer — inspect synthesized programs for gate counts, depth, and hardware fit.
- Qiskit migration — translate existing Qiskit code into Classiq models.
A built-in reference layer keeps the agent’s knowledge current as it works.
Installation
The marketplace is access-controlled: reach out to Classiq to get onboarded, and you’ll receive a personal GitHub invitation to the repository. Accept it first — the steps below assume you already have access.
Add the marketplace once per machine, using the repository from your invitation:/plugin marketplace add <owner>/<repo>
/plugin install classiq-quantum-engineer@classiq
classiq-mcp server on first use.Keeping it up to date:/plugin marketplace update classiq # pull the latest catalog
/plugin update classiq-quantum-engineer@classiq # update the plugin
/plugin list # see what you have installed
- Open Cursor Settings (Cmd+Shift+J) → Plugins.
- Choose Add/import plugin.
- Paste the GitHub URL from your Classiq invitation.
- Select classiq-quantum-engineer and install it.
- Confirm the plugin status shows Imported.
- Reload the window — open the Command Palette and run Developer: Reload Window.
- Enable the MCP server — go to Settings → Features → Model Context Protocol and turn on Classiq Docs.
- Confirm skills loaded — go to Settings → Rules → Agent Decides. You should see skills such as classiq, classiq-modeling, classiq-synthesis, and classiq-execution.
Keeping it up to date:To pick up the latest plugin version, remove and re-import the plugin from the GitHub URL in your invitation, then reload the window.After updating, verify that:
- Settings → Plugins shows classiq-quantum-engineer with status Imported.
- Settings → Features → Model Context Protocol shows Classiq Docs enabled.
- Settings → Rules → Agent Decides includes the Classiq skills.
The plugin requires the classiq Python package in your project’s environment. If you don’t have it yet, ask the agent to install it — see the Install Classiq example in the Examples section below, or Use Python and Classiq for manual SDK setup. Usage
Once installed, just describe what you want in natural language — no special syntax required. The agent picks the right skill for each phase of the work:
| You ask for | Skill that responds |
|---|
Writing, editing, or debugging a quantum algorithm in Python (@qfunc, QBit, QNum, QArray) | Modeling |
Writing or debugging native Qmod (.qmod files) | Native Qmod |
Compiling a model — synthesize(), constraints, hardware targets | Synthesis |
Running a circuit — sample, observe, calculate_state_vector, variational loops | Execution |
| Interpreting results — histograms, energy curves, most-probable states | Post-processing |
| Inspecting a synthesized program — gate counts, depth, hardware fit | Analyzer |
| Translating Qiskit code into Classiq models | Qiskit migration |
Examples
Hello World
Quantum Arithmetic
Grover's Search
Install Classiq
Prompt:Create a Bell state, synthesize it, run it on the simulator, and show the measurement counts.
from classiq import *
@qfunc
def main(res: Output[QArray[QBit, 2]]):
allocate(2, res)
H(res[0])
CX(res[0], res[1])
qprog = synthesize(main)
result = sample(qprog)
print(result)
res counts probability bitstring
0 [1, 1] 1036 0.505859 11
1 [0, 0] 1012 0.494141 00
Prompt:Write a quantum program that puts a 1-qubit integer in superposition, assigns 2 to a second integer, computes their sum, and runs it.
from classiq import *
@qfunc
def main(x: Output[QNum], y: Output[QNum], z: Output[QNum]):
allocate(1, x)
H(x)
y |= 2
z |= x + y
qprog = synthesize(main)
res = sample(qprog)
print(res)
| x | y | z | counts | probability |
|---|
| 0 | 2 | 2 | 1049 | 0.512 |
| 1 | 2 | 3 | 999 | 0.488 |
Prompt:Use Grover's algorithm to find all pairs (x, y) of 2-bit integers where x + y < 4 and (x * y) % 4 == 2. Run it and show which states get amplified.
from classiq import *
VAR_SIZE = 2
class GroverVars(QStruct):
x: QNum[VAR_SIZE]
y: QNum[VAR_SIZE]
@qperm
def my_predicate(vars: Const[GroverVars], res: QBit) -> None:
res ^= (vars.x + vars.y < 4) & ((vars.x * vars.y) % 4 == 2)
@qfunc
def main(vars: Output[GroverVars]):
allocate(vars)
hadamard_transform(vars)
power(
2,
lambda: grover_operator(
lambda vars: phase_oracle(predicate=my_predicate, target=vars),
hadamard_transform,
vars,
),
)
qprog = synthesize(main)
result = sample(qprog)
result
| vars.x | vars.y | probability |
|---|
| 1 | 2 | 0.481 |
| 2 | 1 | 0.463 |
| 2 | 2 | 0.006 |
Prompt:Install classiq and set it up for me.
classiq package via pip, opens a browser window for authentication, and confirms everything is ready with a final status summary.
Per-project best practices
A small amount of one-time setup per project pays off quickly: a project memory file gives the agent persistent context about your environment, sanity checks let you verify everything is wired up before you start, and a troubleshooting reference saves time when something unexpected happens.
Memory file
Both IDEs support a project-level file that the agent reads at the start of every conversation. Use it to record your Python environment and any project-specific conventions — so the agent never has to ask and never guesses wrong.
Create CLAUDE.md at the root of your project and fill in the bracketed fields:# [Project Name]
## Environment
- Python: [path/to/venv/bin/python] <!-- or just `python3` if using the system default -->
- Classiq SDK: installed in the environment above
## Backend
Default: Classiq cloud simulator.
[Optional: list hardware targets or execution preferences for this project.]
## Project overview
[One or two sentences describing the quantum algorithms or application this project implements.]
## Conventions
[Any project-specific patterns — naming, file layout, preferred synthesis constraints, etc.]
CLAUDE.md automatically — no additional configuration required. Create .cursor/rules/classiq.mdc at the root of your project. This file gives Cursor persistent Classiq-specific context for the project.---
description: Classiq project context
alwaysApply: true
---
# [Project Name]
## Environment
- Python: [path/to/venv/bin/python] <!-- or just `python3` if using the system default -->
- Classiq SDK: installed in the environment above
## Backend
Default: Classiq cloud simulator.
[Optional: list hardware targets or execution preferences for this project.]
## Project overview
[One or two sentences describing the quantum algorithms or application this project implements.]
## Conventions
[Any project-specific patterns — naming, file layout, preferred synthesis constraints, etc.]
alwaysApply: true frontmatter tells Cursor to load this rule for every conversation in the project.To verify the rule is active, open Settings → Rules and confirm the project rule appears. You can also ask the agent: “What Classiq project context do you see?” The response should reflect the environment and conventions from .cursor/rules/classiq.mdc. Sanity checks
Run these checks after installation to confirm the plugin is wired up correctly.
Verify the plugin is installed:Look for classiq-quantum-engineer@classiq in the output. If it is missing, reinstall:/plugin install classiq-quantum-engineer@classiq
/status or ask the agent directly: "Which Classiq skills do you have loaded?" The response should name skills such as classiq-modeling, classiq-synthesis, and classiq-execution.Confirm the MCP server is running:Ask the agent:"Can you look up the Classiq docs for synthesize?"
classiq-mcp server is up. A timeout or “no tools available” reply means the server did not start — see Troubleshooting below. Verify the plugin is installed:
- Open Cursor Settings → Plugins.
The classiq-quantum-engineer plugin should appear with status Imported. If it is missing, re-import it from the GitHub URL in your invitation.
If import fails, confirm that you accepted the GitHub invitation and are signed into Cursor with an account that can access the repository.Confirm skills are active:
- Go to Settings → Rules → Agent Decides.
You should see skills such as classiq, classiq-modeling, classiq-synthesis, and classiq-execution.You can also ask the agent:Which Classiq skills do you have loaded?
- Go to Settings → Features → Model Context Protocol and confirm Classiq Docs is enabled.
Then ask the agent:Can you look up the Classiq docs for synthesize?
Check whether the classiq Python package is installed in this project environment.
Troubleshooting
MCP server does not start
The classiq-mcp server starts automatically on launch, but requires a one-time approval prompt on first use.
- Run
/plugin list — confirm classiq-quantum-engineer@classiq appears.
- Go to Settings → MCP Servers. If
classiq-mcp shows as disabled, enable it.
- Restart Claude Code. The server starts fresh on each launch.
If the server still does not appear after a restart, try reinstalling:/plugin update classiq-quantum-engineer@classiq
- Go to Settings → Features → Model Context Protocol.
- Confirm Classiq Docs is toggled on.
- Reload the window — Command Palette → Developer: Reload Window.
If the server still does not appear, remove and re-import the plugin from the GitHub URL in your invitation, then reload.Skills do not load
Skills appear in Settings → Rules. If they are absent after installation:
- Quit and relaunch Claude Code.
- Confirm the plugin installed cleanly:
/plugin list should show classiq-quantum-engineer@classiq without an error flag.
Skills appear in Settings → Rules → Agent Decides. If they are absent after installation:
- Reload the window — Command Palette → Developer: Reload Window.
- Confirm the plugin status in Settings → Plugins shows Imported without an error.
Plugin is installed but not updating
If synthesize behavior or skill instructions seem outdated:/plugin marketplace update classiq # pull the latest catalog
/plugin update classiq-quantum-engineer@classiq
If skill instructions seem outdated, remove and re-import the plugin from the GitHub URL in your invitation to pick up the latest version, then reload the window.
See also
Use AI with Classiq
