Skip to main content
Pre-release

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

DevNarrate

GitHub Repo Release

MCP server for developer workflow automation — smart commits, secret scanning, PR descriptions, and more.

Features

  • Change Review — understand AI-generated code changes before committing with narrative summaries, goal alignment, and attention guides
  • Smart Commit Messages with user approval
  • Secret Scanning — detect API keys, tokens, passwords, and private keys before they reach your repo (25+ detectors via detect-secrets)
  • PR Descriptions driven by customizable templates
  • GitHub & GitLab support for PR flows
  • Token-aware diff handling with automatic pagination
  • Safety-first workflow by requiring staged changes

Installation (PyPI)

pip install devnarrate

# Install pre-release builds
pip install --pre devnarrate

Register the MCP server

Use the Python interpreter from the environment where you ran pip install (e.g. /path/to/venv/bin/python). Capture it once and reuse:

PYTHON_BIN=$(python -c 'import sys; print(sys.executable)')

# Claude Code (global scope)
claude mcp add --scope user DevNarrate -- "$PYTHON_BIN" -m devnarrate.server

# Claude Code (project scope)
claude mcp add DevNarrate -- "$PYTHON_BIN" -m devnarrate.server
  • Cursor (~/.cursor/mcp.json):
{
  "mcpServers": {
    "DevNarrate": {
      "command": "/path/to/venv/bin/python",
      "args": ["-m", "devnarrate.server"]
    }
  }
}

Restart Cursor after editing the config.

Usage

Commit Messages

DevNarrate works entirely off staged changes:

git add <file1> <file2>
# stage everything tracked:
git add -u

Then ask your AI assistant:

Generate a commit message for my changes

DevNarrate summarizes the diff, proposes a conventional commit, and waits for approval before committing.

Change Review

After an AI assistant makes changes, ask it to review them before committing. DevNarrate presents a layered summary: narrative overview, goal grouping (known, inferred, unrecognized), and an attention guide highlighting what needs human review.

Secret Scanning

Secret scanning runs automatically when you ask for a commit message. DevNarrate scans staged diffs for API keys, tokens, passwords, and private keys. If secrets are found, you're warned before committing. Suppress false positives with an inline # pragma: allowlist secret comment.

PR Descriptions

  1. Ask your AI assistant: "Create a PR to main from my current branch"
  2. Choose a template if you have custom ones in .devnarrate/pr-templates/
  3. Review the generated PR description and approve to let DevNarrate call gh or glab

Configuration

DevNarrate ships a fully commented .devnarrate/config.toml with all available settings and their defaults. Copy it into your repo and edit the values you care about — every option is documented inline.

Platform Requirements

  • Commits: only needs git
  • GitHub PRs: install gh and run gh auth login
  • GitLab PRs: install glab and run glab auth login

Links

Metadata

Release files for devnarrate 0.1.0a7

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for devnarrate 0.1.0a7
File Size Uploaded Provenance
devnarrate-0.1.0a7.tar.gz 97.5 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for devnarrate 0.1.0a7
File Interpreter ABI Platform
devnarrate-0.1.0a7-py3-none-any.whl Python 3 none any Details

Total release size: 123.0 kB

Release files / devnarrate-0.1.0a7.tar.gz

Download URL devnarrate-0.1.0a7.tar.gz
Size 97.5 kB
Tags Source
SHA-256 checksum
How to use checksums
385068b097dc27015a99ac99ff870a936c535469da3d26b9c5492a6894f71772
BLAKE2b-256 checksum
How to use checksums
47a27090d7e9515d0e11dd9540beb497b6c0b8c756d922c65f39cd1932bdd719
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Mar 2, 2026.

Transparency log

Release files / devnarrate-0.1.0a7-py3-none-any.whl

Download URL devnarrate-0.1.0a7-py3-none-any.whl
Size 25.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
ba189582405d25220fa635c82b613bf172b35e50c841dcf565ff3920cfb42dbb
BLAKE2b-256 checksum
How to use checksums
2d384bbc75b214083c8cb3364abb2ff08eb9b1db352d047bd31ca5230c4b09d9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Mar 2, 2026.

Transparency log

Security for devnarrate 0.1.0a7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for devnarrate-0.1.0a7.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Mar 2, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page