Quell reads your docstrings, Pydantic models, and type annotations, extracts every testable requirement, finds which ones have no test, generates pytest tests via a rule engine, verifies each test through a 5-gate pipeline, and writes only proven tests to disk.

Does Quell require an LLM API key?

The rule engine runs entirely in-process — no source code is ever transmitted. ~75% of edge cases are handled with no network call and no API key. LLM fallback is opt-in and only sends the function signature, never the full body.

What is the 5-gate pipeline?

Every generated test must pass: Gate 1 (AST valid Python), Gate 2 (not already in a test file), Gate 3 (no shell calls or file writes), Gate 4 (passes against original code), Gate 5 (fails when the requirement is violated). Only gate-5-verified tests are written to disk.

What is the Production Readiness Score (PRS)?

PRS = (WRITTEN × 1.0 + SCAFFOLDED × 0.5) / total_requirements × 100. Tiers: 80-100 Production Ready, 60-79 Review Needed, 0-59 Needs Work.

How is Quell different from GitHub Copilot or Qodo for test generation?

Quell reads specifications that already exist in your code — it does not generate tests from scratch. It finds requirements already documented in your docstrings, Pydantic models, and type annotations that have no test. The 5-gate pipeline, especially Gate 5 (violation injection), verifies each test actually catches the bug it claims to catch. This verification step is not present in Copilot, Qodo, or Hypothesis.

Can Quell be used in CI pipelines?

Yes. Run quell ci src/ --threshold 80 to fail CI if PRS falls below 80. Set prs_threshold in pyproject.toml under [tool.quell]. Works with GitHub Actions, GitLab CI, and any system that checks exit codes.

Can Claude Code or Cursor use Quelltest directly?

Yes. Quelltest ships a local MCP server: install with pip install quelltest[mcp], then add {"mcpServers": {"quelltest": {"command": "quelltest-mcp"}}} to your project's .mcp.json. The agent can then call find_edge_cases, write_verified_tests, get_prs_score, prove_file, and reproduce_bug directly — no terminal needed. A Claude Code plugin is also available via /plugin marketplace add quelltest/quelltest-lib.

Does the Quelltest MCP server send my code anywhere?

No. The local MCP server (quelltest-mcp) runs entirely on your machine over stdio — no cloud, no network calls, no telemetry. The separate opt-in Claude.ai connector only ever transmits sanitized metrics (PRS score, bucket counts, test names, flag locations); a sanitizer blocks source code, function bodies, and docstrings structurally.

How do I add Quelltest as a Claude.ai connector?

In Claude.ai, go to Settings, then Connectors, then Add custom connector, and enter https://mcp.quelltest.com. Claude discovers the OAuth endpoints automatically and walks you through authorization.

MCP Server & Claude Code Plugin

Quelltest ships a local MCP server inside the pip package. Claude Code, Claude Desktop, Cursor, or any MCP client spawns it over stdio and operates Quelltest directly — no terminal, no cloud, no network. Nothing leaves your machine.

This is different from the Claude.ai connector: the connector serves synced readiness reports to Claude.ai; the MCP server lets an agent run Quelltest against the repo it is working in.

Setup in 2 steps

Step 1 — Install the MCP extra

pip install "quelltest[mcp]"

Step 2 — Register the server

Add to your project's .mcp.json (Claude Code reads this automatically):

{
  "mcpServers": {
    "quelltest": { "command": "quelltest-mcp" }
  }
}

That's it. Ask Claude to "find untested edge cases in this project" and it will call the tools directly.

The 5 tools

Tool	What it does
`find_edge_cases(path, sources?)`	Scan for documented requirements with no test. Read-only. Returns the gap list with file and line locations.
`write_verified_tests(path)`	Generate a pytest test per gap, verify each through all 5 gates, write only proven tests to disk.
`get_prs_score()`	Project Production Readiness Score (0–100) with tier and per-file breakdown.
`prove_file(file, function?)`	Coverage ratio for one file, optionally narrowed to one function.
`reproduce_bug(description, file?)`	Turn a natural-language bug description into a verified failing test.

Every tool returns structured JSON and never raises — errors come back as {"error": "..."} so the agent can react.

Claude Code plugin

The plugin bundles a skill that teaches Claude the daily workflows — when to scan, how to read the three buckets, what to do with FLAGGED items:

/plugin marketplace add quelltest/quelltest-lib
/plugin install quelltest@quelltest

Then use slash commands or just ask in plain English:

/quelltest find src/
/quelltest fix src/payments/
/quelltest score
/quelltest reproduce "payment accepts zero amount"

Workflows the skill runs proactively:

After editing a Python file — scan it for new gaps, offer to fix.
Before a commit or PR — check the PRS, fix the worst files first.
When you report a bug — reproduce it as a verified failing test.
When FLAGGED items block coverage — refactor for testability, re-run.

Privacy

The local MCP server makes zero network calls. It runs over stdio on your machine; source code, test bodies, and results stay in the repo. There is no telemetry. (The Claude.ai connector is separate, opt-in, and transmits sanitized metrics only.)

Other agents

Any MCP client works — Cursor, Claude Desktop, Devin, or your own agent via the MCP SDK:

quelltest-mcp              # stdio server, spawned by the client
python -m quell.mcp_server # equivalent
quell mcp                  # CLI alias

Troubleshooting

"mcp package is required" — install the extra: pip install "quelltest[mcp]".

Tools don't appear in Claude Code — check .mcp.json is at the project root and restart the session; claude mcp list should show quelltest.

Tests aren't written — that's the pipeline working: a test that fails any of the 5 gates (including Gate 5's violation injection) is discarded, never written. Check find_edge_cases output for SCAFFOLDED/FLAGGED reasons.