"Shell" matching MCP servers:

Compiles LaTeX resumes into PDFs via MCP tools, including validation, preview, template compilation, and LaTeX export, with security defaults like path isolation and no shell escapes.

Enables agents to discover Kujo projects, primitives, tooling, showcases, agent skills, workflows, and WebOps capabilities, retrieve exact source-backed records with install text and version notes, and get small deterministic stack recommendations. All seven tools are read-only, deterministic, and idempotent, with no write, fetch, filesystem, shell, install, or deployment capability.

Enables AI agents to search, browse, install, and manage a large library of skills via only 7 MCP tools, with skills stored locally and loaded on demand to minimize context overhead.

Enables agents to search a catalog of SKILL.md procedures, fetch individual skill instructions and supporting resources, and obtain advisory multi-step routes through read-only tools such as search_skills, route_request, get_skill, and get_skill_resource. It returns metadata and suggestions only, never executing skills, running shell commands, or granting authority.

Enables scraping and searching documentation websites using semantic or keyword search, with support for multiple deployment modes.

Enables execution of shell commands through a terminal tool with working directory support and timeout protection. Also provides access to MCP documentation as a resource.

Connects a Zotero research library to AI assistants so users can search items by title, author, tag, collection, full text, or meaning, read metadata and PDF content, add annotations, and add or organize papers by DOI, URL, ISBN, or BibTeX. It works in local or web mode and is available both as an MCP server for chat apps and as a CLI plus agent skill for shell-based agents.

Exposes a read-only virtual filesystem over MCP so agents can explore documentation with real shell commands (ls, cat, grep, head, sed) answered from a vector store rather than a disk or sandbox. It also provides a hybrid dense-vector plus BM25 search tool for finding where to look first, with page access governed by group rules.