Jarvis Registry
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.
What is Jarvis Registry?
Jarvis Registry is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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.
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.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Connect any AI copilot or autonomous agent to your enterpris
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx jarvis-registryConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Jarvis Registry
Jarvis Registry is an enterprise MCP gateway and agent registry that provides a single, authenticated entry point for connecting AI copilots and autonomous agents to internal business tools. It enforces scope-based and role-based access control through a configurable ACL engine, supports OAuth 2.0/OIDC identity providers including Keycloak, Amazon Cognito, and Microsoft Entra ID, and emits full audit logs with OpenTelemetry tracing and Prometheus metrics. Platform and AI teams use it to govern which agents can call which tools, enable semantic skill discovery at runtime, and maintain compliance visibility across all AI-driven operations.
Prerequisites
- Docker and Docker Compose
- Python with the uv package manager (pip install uv)
- An identity provider account: Keycloak (self-hosted), Amazon Cognito, or Microsoft Entra ID
- An MCP client such as Claude Desktop, Cursor, GitHub Copilot, or VS Code
- Access to the enterprise tools you want to expose through the gateway
Clone the repository
Clone the Jarvis Registry repository to your server or local machine.
git clone https://github.com/ascending-llc/jarvis-registry.git
cd jarvis-registryConfigure your identity provider
Copy the example environment file and fill in your identity provider credentials. Jarvis Registry supports Keycloak, Amazon Cognito, and Microsoft Entra ID.
cp .env.example .env
# Edit .env and set your identity provider details:
# For Keycloak: KEYCLOAK_URL, KEYCLOAK_REALM, CLIENT_ID, CLIENT_SECRET
# For Cognito: AWS_COGNITO_USER_POOL_ID, AWS_COGNITO_CLIENT_ID
# For Entra: AZURE_TENANT_ID, AZURE_CLIENT_ID, AZURE_CLIENT_SECRETSet up the Python environment
Use uv to install all Python dependencies and activate the virtual environment.
uv sync --all-packages
source .venv/bin/activateStart all services
Launch the full Jarvis Registry stack including the gateway, registry database, and observability services using Docker Compose.
docker compose --profile full up -dAccess the management UI
Open the Jarvis Registry UI to register MCP servers, define ACL rules, and manage agent permissions.
# Open in browser:
http://localhost:80Register enterprise tools and configure MCP clients
In the UI, add the MCP servers for your enterprise tools. Then configure your AI copilots (Claude Desktop, Cursor, etc.) to point to the Jarvis gateway URL instead of individual MCP servers.
{
"mcpServers": {
"jarvis-gateway": {
"command": "npx",
"args": ["-y", "jarvis-registry"],
"env": {
"GATEWAY_URL": "http://localhost:80"
}
}
}
}Jarvis Registry Examples
Client configuration
MCP client configuration pointing to a local Jarvis Registry gateway.
{
"mcpServers": {
"jarvis-gateway": {
"command": "npx",
"args": ["-y", "jarvis-registry"],
"env": {
"GATEWAY_URL": "http://localhost:80"
}
}
}
}Prompts to try
Example prompts once the gateway is running and enterprise tools are registered.
- "List all the tools available to me through the Jarvis gateway."
- "Search for skills related to Jira issue management and show what actions are available."
- "Query our internal inventory database for all open purchase orders this month."
- "Check my permission scope — which enterprise tools am I authorized to call?"
- "Trigger the onboarding workflow for a new employee joining the engineering team."Troubleshooting Jarvis Registry
Services fail to start with identity provider connection errors
Verify that all identity provider credentials in the .env file are correct and that the identity provider is reachable from the Docker network. For Keycloak, ensure the realm and client are created and the client secret matches what is in .env.
AI copilot receives 403 Forbidden when calling a tool
The ACL engine is blocking the request. Log in to the Jarvis Registry UI and review the scope and role assignments for the agent's identity. Add the required scope to the agent's permission set and confirm the target MCP server is registered.
No traces appearing in observability dashboard
Ensure the full Docker Compose profile is running ('docker compose --profile full up -d'). The observability stack (OpenTelemetry collector, Prometheus) is included in the 'full' profile. Check that the OTEL_EXPORTER_OTLP_ENDPOINT env var points to the collector container.
Frequently Asked Questions about Jarvis Registry
What is Jarvis Registry?
Jarvis Registry is a Model Context Protocol (MCP) server that 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. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Jarvis Registry?
Follow the installation instructions on the Jarvis Registry GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Jarvis Registry?
Jarvis Registry works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Jarvis Registry free to use?
Yes, Jarvis Registry is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Jarvis Registry Alternatives — Similar Cloud Services Servers
Looking for alternatives to Jarvis Registry? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Jarvis Registry in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Jarvis Registry?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.