"Fig" matching MCP servers:

Pull a Figma frame once, then let Claude Code, Codex or any MCP agent read it offline with no rate limits. Six read-only tools serve the normalized node tree, design tokens and locally built SVG icons from a vault you can commit, so teammates need no Figma token.

Enables users to import scientific figures together with their code, review and publish them as immutable releases into one user-chosen local library, then search, preview and materialize an exact confirmed template into any project from Claude Science, Cursor, Codex or other stdio MCP hosts. It keeps the catalog on disk and never executes plotting code, so the host agent inspects files while the server hashes, versions, gates and publishes them.

Enables MCP clients to inspect and export OpenPencil .fig and .pen files directly from disk, supporting operations like info, tree traversal, XPath queries, linting, and conversion to various formats without the desktop app or CLI.

Enables an AI agent to inspect and operate a remote Windows machine over a private tailnet, listing and reading files, transferring and mutating them within a configured sandbox root, capturing screenshots, and — only when explicitly double-opted-in — executing commands and sending keystrokes. It runs self-hosted with no third-party client or vendor cloud in the session path, and reports its live policy rather than asserting its own safety.

mcp-node-zig is an MCP server for remote machines. Drop it on a build box, a homelab server, a Windows host or a VPS, and any MCP client can run commands, drive long-running processes and read and write files there over one authenticated HTTP endpoint.

Token-efficient Python stdio MCP server exposing safe text-file search, reading, and refactoring tools.

Enables AI assistants to securely operate on a local workstation through MCP by exposing file, shell, and workspace management tools.

Provides LLM-optimized tools for advanced code analysis, repository complexity evaluation, and call graph generation. It enables users to visualize directory structures, detect code patterns, and build semantic context with significant token savings.

Enables AI assistants to read and write a local, encrypted-by-default memory store, so they can share persistent notes and context across sessions and models on your machine.