Skip to main content

Observal MCP Server Registry & Agent Registry CLI

Project description

 ██████╗ ██████╗ ███████╗███████╗██████╗ ██╗   ██╗ █████╗ ██╗
██╔═══██╗██╔══██╗██╔════╝██╔════╝██╔══██╗██║   ██║██╔══██╗██║
██║   ██║██████╔╝███████╗█████╗  ██████╔╝██║   ██║███████║██║
██║   ██║██╔══██╗╚════██║██╔══╝  ██╔══██╗╚██╗ ██╔╝██╔══██║██║
╚██████╔╝██████╔╝███████║███████╗██║  ██║ ╚████╔╝ ██║  ██║███████╗
 ╚═════╝ ╚═════╝ ╚══════╝╚══════╝╚═╝  ╚═╝  ╚═══╝  ╚═╝  ╚═╝╚══════╝

Discover, share, and monitor AI coding agents with full observability built in.

License Python Status Stars Coverage

If you find Observal useful, please consider giving it a star. It helps others discover the project and keeps development going.


Observal is a self-hosted AI agent registry with built-in observability. Think Docker Hub, but for AI coding agents.

Browse agents created by others, publish your own, and pull complete agent configurations — all defined in a portable YAML format that templates out to Claude Code, Kiro CLI, Cursor, Gemini CLI, and more. Every agent bundles its MCP servers, skills, hooks, prompts, and sandboxes into a single installable package. One command to install, zero manual config.

Every interaction generates traces, spans, and sessions that flow into a telemetry pipeline. The built-in eval engine scores agent sessions so you can measure performance and make your agents better over time.

Agent Registry

Agent Registry

Browse, search, and install published agents

Dashboard

Dashboard

Agent scores, recent sessions, top downloads

Trace Detail

Trace Detail

Every tool call: models, token counts, 16 turns

Insight Report

Insights

AI-generated analysis of agent usage patterns

Error Log

Errors

Classified errors with drill-through to sessions

Review Queue

Review

Admin approve/reject workflow for submissions

Documentation

Full docs live at docs.observal.io

Start here Go to
5-minute install and first trace Quickstart
Understand the data model Core Concepts
Instrument your existing MCP servers Observe MCP traffic
Run Observal on your infrastructure Self-Hosting
Look up a CLI command CLI Reference
Report a bug with diagnostics Reporting Issues

See CHANGELOG.md for recent updates.

Quick start

See SETUP.md for the full setup guide.

git clone https://github.com/BlazeUp-AI/Observal.git && cd Observal
cp .env.example .env
make up
uv tool install --editable .
observal auth login

Supported IDEs

IDE Support
Claude Code Full — skills, hooks, MCP, rules, OTLP telemetry
Kiro CLI Full — superpowers, hooks, MCP, steering files, OTLP telemetry
Gemini CLI Tested — hooks, MCP, rules, OTLP telemetry
Cursor Tested — MCP + shim telemetry, rules
VS Code Limited — MCP + shim telemetry, rules
Copilot CLI Limited — hooks, MCP + shim telemetry, rules
Codex CLI Limited — rules
OpenCode Limited — JS plugin hooks, MCP + shim telemetry, rules

Compatibility matrix and per-IDE setup: Integrations.

Tech stack

Component Technology
Frontend Next.js 16, React 19, Tailwind CSS 4, shadcn/ui, Recharts
Backend Python 3.11+, FastAPI, Strawberry GraphQL, Uvicorn
Databases PostgreSQL 16 (registry), ClickHouse (telemetry)
Queue Redis + arq
CLI Python, Typer, Rich
Eval engine AWS Bedrock / OpenAI-compatible LLMs
Telemetry OpenTelemetry Collector
Deployment Docker Compose (10 services)

Contributing

See CONTRIBUTING.md. The short version:

  1. Fork and clone
  2. make hooks to install pre-commit hooks
  3. Create a feature branch
  4. Run make lint and make test
  5. Open a PR

See AGENTS.md for internal codebase context.

Running tests

make test      # quick
make test-v    # verbose

All tests mock external services. No Docker needed.

Community

Have a question, idea, or want to share what you've built? Head to GitHub Discussions. Please use Discussions for questions; open Issues for confirmed bugs and concrete feature requests.

Join the Observal Discord to chat directly with the maintainers and other community members.

Reporting issues

When filing a bug report, please attach a support bundle so maintainers can diagnose the problem quickly:

observal support bundle

This produces a .tar.gz archive containing version info, sanitized configuration, health probes, aggregate table counts, and optional system metrics. All values pass through a redaction layer — no customer data, row contents, or credentials are included. Review the bundle before sharing:

observal support inspect observal-support-*.tar.gz

Security

To report a vulnerability, please use GitHub Private Vulnerability Reporting or email contact@blazeup.app. Do not open a public issue. See SECURITY.md.

License

GNU Affero General Public License v3.0 (AGPL-3.0). See LICENSE.

Star history

Star History Chart

Project details


Download files

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

Source Distribution

observal_cli-0.5.0.tar.gz (4.8 MB view details)

Uploaded Source

Built Distribution

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

observal_cli-0.5.0-py3-none-any.whl (187.7 kB view details)

Uploaded Python 3

File details

Details for the file observal_cli-0.5.0.tar.gz.

File metadata

  • Download URL: observal_cli-0.5.0.tar.gz
  • Upload date:
  • Size: 4.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for observal_cli-0.5.0.tar.gz
Algorithm Hash digest
SHA256 0e01155f39cb611bf5a9d40b2d93c8c084efb182b22c33abd5dfa879c4dca999
MD5 44fec7a257ca9410c89096c6039ccb12
BLAKE2b-256 34066d69941afa182aff59c6dcfee982cc6da59ee4740dd0401c6909046a5fdd

See more details on using hashes here.

Provenance

The following attestation bundles were made for observal_cli-0.5.0.tar.gz:

Publisher: release.yml on BlazeUp-AI/Observal

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file observal_cli-0.5.0-py3-none-any.whl.

File metadata

  • Download URL: observal_cli-0.5.0-py3-none-any.whl
  • Upload date:
  • Size: 187.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for observal_cli-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6bebd697cf500c8488da96442fdf14f68f1786b8ea2cf8e4607e31a265cef63b
MD5 17739c9053a604ca0bd64eae2d55228c
BLAKE2b-256 34025955b204361cf3e1ee605a5ef1b8695bfdcef0e4a6293d4c46ea17b38f79

See more details on using hashes here.

Provenance

The following attestation bundles were made for observal_cli-0.5.0-py3-none-any.whl:

Publisher: release.yml on BlazeUp-AI/Observal

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

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