Every server below was scanned with the same deterministic engine that powers the MCP Trust Checker CLI and free API — an auditable A–F Trust Score, the server's capability blast radius, and every finding with its evidence. No pay-to-list, no self-reported ratings: the score is computed from the package's actually published code and tool surface.
Microsoft’s official Playwright MCP server: drive a real browser through accessibility-tree snapshots.
Security scan results for the Transport Http MCP server.
Security scan results for the Session Manager MCP server.
Security scan results for the Storybook MCP server.
Security scan results for the Tmcp MCP server.
Security scan results for the Orval MCP server.
Security scan results for the Addon MCP server.
Up-to-date, version-specific library documentation injected straight into prompts.
Security scan results for the Handler MCP server.
Security scan results for the Fastmcp MCP server.
Security scan results for the Remote MCP server.
The official MCP filesystem server: read, write, search and manage local files with configurable access roots.
Security scan results for the Mcporter MCP server.
Security scan results for the Hono MCP server.
Security scan results for the Adapters MCP server.
Security scan results for the Nest MCP server.
Supabase’s official MCP server: manage projects, run SQL and inspect your database.
The official structured-reasoning server: break problems into revisable thought sequences.
Security scan results for the Tools MCP server.
Security scan results for the Gitlab MCP server.
MongoDB’s official MCP server: query collections, inspect schemas and run aggregations.
The official knowledge-graph memory server: persistent entities, relations and observations.
Security scan results for the Figma Developer MCP server.
Security scan results for the Nx MCP server.
The MCP Trust Registry catalogs Model Context Protocol servers — the connectors that let AI assistants such as Claude, Cursor and other LLM clients reach real systems: databases, browsers, cloud and DevOps tooling, memory stores and web search. Most MCP directories only aggregate links and download counts. Here, every listed server has first been analyzed by the open-source mcptrustchecker engine: the published npm or PyPI package is scanned deterministically, the same input always yields the same result, and nobody can pay to be listed or ranked higher.
Each entry exposes three signals worth reading together before you install anything:
Prefer the narrowest capability set that still does the job: an assistant that only needs read-only analytics has no reason to run a server with shell access. Anything not yet listed can be checked on demand through the free scan API.
An MCP server sits inside the trust boundary of your AI assistant, so its risks differ from ordinary dependencies. Tool poisoning hides instructions in tool descriptions that the model reads and obeys. Prompt injection arrives through fetched pages, tickets or emails and can redirect the assistant mid-task. And an over-permissioned server turns either attack into data exfiltration: a connector that can both read your files and make outbound requests can quietly ship secrets to an attacker. Scores here are automated opinions derived from published package code — evidence to weigh, not certifications.
No. A strong grade means the deterministic scan found no dangerous patterns in the published package at the scanned version, with the stated coverage. New releases change code, so re-check after updates, review the capability profile against your own threat model, and grant each server the least access it needs.