tabnas is a Model Context Protocol (MCP) server: Seven tools over the tabnas parsing engine: parse, validate, diagnose, fixtures, compare. In practice that means any MCP-compatible AI assistant can call tabnas's tools directly — the model decides when to use them in a conversation or agent run.
You can run tabnas two ways: connect to the hosted endpoint at https://mcp.tabnas.dev/mcp with no local install, or run it on your own machine via the npm package @tabnas/mcp. The current release is v0.1.15, published under the MIT license, with source at tabnas/mcp on GitHub.
tabnas is listed under Development on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain tabnas for tabnas.dev, claim this listing to verify ownership, earn the Verified badge, and keep the details current.