"Serverless" matching MCP servers:

Provides read-only access to PostgreSQL databases via MCP, enforcing least-privilege roles, row-level security, masked views, and SQL AST guardrails to prevent data leakage and unauthorized operations, enabling AI agents to safely query sensitive production data.

Enables MCP servers to complete OAuth2 flows by accepting authorization codes from a serverless callback, storing them encrypted with a short TTL, and allowing one-time retrieval by the originating server. It also provides status tools for pending codes and service health.

Enables policy-style auditing of content through the audit_vibe MCP tool to enforce configurable guardrails. Supports both local stdio and serverless Streamable HTTP deployment via Vercel for flexible integration with MCP clients.

Simulates sensitive internal tools as a honeypot to detect unauthorized access and AI agent behaviors using Canarytokens, deployed as a serverless Cloudflare Worker with MCP protocol support.

Enables AI agents to diagnose and analyze AWS serverless infrastructure through Model Context Protocol, providing access to CloudWatch logs, Lambda functions, DynamoDB tables, IAM policies, and Bedrock-powered incident root-cause analysis.

A deployable serverless MCP OAuth gateway and proxy that adds OAuth 2.0 authentication to Excalidraw tools or any external MCP server, enabling secure connections from clients like Google Spark and Gemini.