MCP Servers & Security Directory
Audit Model Context Protocol (MCP) servers for dangerous permissions, filesystem access, execution scopes, and tool risks. Profiles for GitHub, PostgreSQL, Filesystem, Slack, Playwright, and Notion.
Explore and audit enterprise Model Context Protocol (MCP) servers. Inspect tool schemas, required permission scopes, and known vulnerability CVEs before connecting AI agents to production systems.
Audited MCP Servers (10)
Connects AI agents to GitHub repositories for code reading, file creation, PR management, and issue tracking. Widely used but requires careful scope restriction.
Provides AI agents with direct access to PostgreSQL databases for querying, schema inspection, and data manipulation. High risk when connected to production databases.
Grants AI agents direct read and write access to the local filesystem. Extremely powerful — and extremely dangerous if misconfigured.
Connects AI agents to Slack workspaces for reading messages, posting updates, and managing channels. Requires careful scope management to prevent data exposure.
Gives AI agents full browser automation capabilities via Playwright. Extremely powerful for web tasks but carries the highest risk profile of any MCP server.
Connects AI agents to Notion workspaces for reading and writing pages, databases, and comments.
Provides AI agents access to Google Drive files and Google Docs for reading and writing content.
Provides AI agents with web search capabilities via the Brave Search API. One of the lowest-risk MCP servers as it only performs read operations against public web content.
Connects AI agents to the Stripe payment API for querying customers, subscriptions, and payment data. Requires extreme caution due to financial data sensitivity.
Connects AI agents to Linear for issue tracking, project management, and team workflow automation.