mcp-server

jarvis-registry

Name: jarvis-registry
Author: ascending-llc

Connect any AI copilot or autonomous agent to your enterprise tools — through a single, secure MCP/Agent gateway with built-in identity, access control, and full observability.

3,703 stars+85★ this week557 forksPythonUpdated 10/23/2026100% free · open source

What it does

Jarvis-registry connects any AI copilot or autonomous agent to your enterprise tools through a single, secure MCP/Agent gateway with built-in identity, access control, and full observability.

When to use it

•When you need to integrate multiple AI agents with your enterprise tools
•When you require a single gateway for managing access control and identity across different AI copilots
•When full observability of AI agent interactions with your tools is necessary

Ready-to-paste prompt

python -m jarvis_registry.main --config config.yaml --agent my_agent

Heads up: Ensure you have Python installed and properly configured on your system, as jarvis-registry is built using Python and may require specific versions or dependencies to function correctly

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/jarvis-registry && curl -fsSL https://workflowstacks.com/api/skills/jarvis-registry/claude-skill -o ~/.claude/skills/jarvis-registry/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How jarvis-registry works

Codeflow

Free to inspect

Jarvis-registry is a very large Python project (~115k lines across 573 code files, plus 240 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size

Very large codebase

~115k lines · 573 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Python · Docker

Needs API keys (.env)

Python 85%TypeScript 14%Shell 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
pyproject.toml
Dependencies and the commands it exposes
4
.env.example
The API keys and settings you must provide

What's in each folder

frontend/Frontend / UI211 files

docs/Documentation146 files

registry/Folder292 files

registry-pkgs/Folder226 files

auth-server/Folder70 files

scripts/Helper scripts43 files

config/Configuration13 files

workflow-worker/Folder13 files

READMEHas testsDocumentedCI checksDocker readyApache-2.0 licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/jarvis-registry && curl -fsSL https://workflowstacks.com/api/skills/jarvis-registry/claude-skill -o ~/.claude/skills/jarvis-registry/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

ascending-llc

Language

Python