metorial/metorial

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

3350 stars · 366 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Metorial is an open-source identity and access control plane for AI agents, providing 1200+ verified MCP integrations with centralized auth, RBAC, SSO, and audit logging. It exposes a single Magic MCP URL (plus CLI and API) so agents and MCP clients can access approved tools under existing security policies.

Use cases

• connect ai agents to saas tools like slack, github, and notion
• manage oauth and api key credentials for mcp servers
• control which tools an ai agent can access with rbac
• audit what actions ai agents took and with whose credentials
• give employees one mcp url for all approved integrations
• self-host an mcp gateway for internal tools
• build customer-facing agents with per-user tool access

When to choose

• you need production-grade auth, permissions, and audit trails for agent tool calls
• you want one managed MCP connection URL across many integrations and clients
• your team requires SSO, RBAC, or compliance for AI agent access
• you want an open-source, self-hostable alternative to Composio

When to avoid

• you just need a single simple MCP server for one tool with no governance
• you want a fully free self-hosted stack without considering the hosted platform's paid tiers
• your project is a hobby prototype that doesn't need access control or observability

Facets

service · maturity active

mcp auth authorization agent-framework monitoring secrets-management api-gateway self-hosted large-language-models security apis developer-tools self-hosted self-hosted cloud mcp-gateway agent-infrastructure oauth rbac audit-logs integrations yc-startup control-plane ai-agents web-server docker typescript nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="metorial/metorial")