Ross ROSS = Recommend OSS · open-source software intelligence for agents

ascending-llc/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. observed · 2026-08-28

github.com/ascending-llc/jarvis-registry · homepage · Python · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

84/100

  • Activity 99
  • Release rhythm 99
  • Longevity 23
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 9.5
  • age_days: 334
  • days_rel: 7
  • days_push: 7
  • n_releases_24m: 9

Full methodology

Adoption not part of the score

2757 stars · 404 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Jarvis Registry is an open-source, enterprise-grade MCP and A2A agent gateway and workflow orchestration platform that gives AI copilots and autonomous agents secure, governed access to enterprise tools through a single control plane. It provides identity federation (Keycloak, Entra ID, Cognito), fine-grained ACL enforcement down to the tool level, semantic skill discovery, protocol compliance validation, and full observability via OpenTelemetry and Prometheus.

Use cases

  • securely connect AI copilots like Cursor or Claude Desktop to internal enterprise tools
  • centralize MCP server registration, access control, and auditing in one gateway
  • orchestrate autonomous A2A agents with per-call permission enforcement
  • enforce OAuth 2.0/OIDC identity and role-based access on AI tool calls
  • discover MCP servers and agents by skill or semantic search at runtime
  • federate and govern agents from AWS AgentCore or Azure AI Foundry
  • add observability and audit logging to AI agent tool invocations

When to choose

  • you need a single governed entry point for multiple AI copilots and agents accessing enterprise tools
  • you require enterprise identity integration (Keycloak, Entra ID, Cognito) and fine-grained tool-level ACLs
  • you want both MCP servers and A2A agents managed under one control plane
  • you need audit trails, OpenTelemetry tracing, and compliance validation for AI tool access
  • you are deploying to Kubernetes and need a production-grade MCP gateway

When to avoid

  • you only need a simple local MCP server for personal use with no governance requirements
  • your stack is not Python/Docker/Kubernetes based and you need a lightweight proxy
  • you need a mature long-term-supported product — the project is young with rapid 0.x releases
  • you want a fully managed SaaS rather than a self-hosted platform to operate

Facets

service · maturity active

mcp api-gateway auth authorization agent-framework monitoring tracing rate-limiting search-engine workflow-automation security self-hosted large-language-models security apis developer-tools self-hosted infrastructure-as-code python self-hosted cloud mcp-gateway a2a-agents agent-orchestration tool-calling identity-governance rbac oauth2 oidc keycloak entra-id observability opentelemetry enterprise-ai skill-registry reverse-proxy ai-agents docker kubernetes web-server

10 sources

Member repositories

RepositoryRoleHealth v2
ascending-llc/jarvis-registrymain84

For agents

markdown · JSON · MCP: product_card(name="ascending-llc/jarvis-registry")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem