pulsemcp scanned Safe content atomic mcp-remote

Plexus

This MCP server provides a multi-tenant OAuth-enabled framework for building secure MCP applications with user authentication, external service integration, and API key management. Built using Python with FastAPI, FastMCP, and SQLite/Redis storage backends, it features tenant isolation, Plexus user authentication tokens, OAuth 2.1 provider capabilities with PKCE support, encrypted API key storage for external services, and a comprehensive CLI for administrative operations. The implementation includes decorators for tool authentication (@requires_auth, @requires_api_key), session management with Redis, tenant-scoped tool access controls, and both stdio and HTTP transport modes, making it valuable for enterprise MCP deployments requiring user authentication, multi-tenant SaaS applications, secure integration with external APIs like Google services, and any use case needing robust authentication and authorization layers for MCP tool access.

Cognium trust score
0%
Tier
Scanned

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.

Scan details: Circle-IR · 2026-09-19 · Appeal

View full trust & usage report →

Metadata

Version
1.0.0
Skill type
atomic
Execution layer
mcp-remote
Category
database
Source
PulseMCP
Author type
human
Last scanned
2026-09-19
Updated
2026-09-19
View source Find related skills

Use via MCP

MCP

Resolve Plexus from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
Swap --scope user for --scope project to commit it to .mcp.json.

Search SkillsRegistry