Local-first MCP server for navigating and maintaining arbitrary hierarchical documentation with flexible node structure, raw content, and multiple parents, leaving navigation decisions to the connected LLM.
Enables AI agents to subscribe to a deterministic daily ethics feed drawn from a four-module curriculum and retrieve read-only tools, resources, and reflection prompts covering principles, case studies, and codes of conduct.
A tool that helps users conduct comprehensive research on complex topics by exploring questions in depth, finding relevant sources, and generating structured, well-cited research reports.
Lets AI agents browse and read a university's student resource center portal, retrieving the resource pages for a given admission year and department along with progression and graduation requirements, student handbook sections, academic calendars, bus timetables, class advisors, application forms and manuals, and contact information, each answer cited with its source document and page. It is an unofficial tool that runs locally and drives Chrome or Edge to access the portal on the user's behalf.
MCP server for token-efficient access to Open Finance Brasil rules, enabling coding agents to search and retrieve specific regulations, OpenAPI specs, and business rules through progressive disclosure.
Lets AI agents search and read a folder of Markdown documentation at query time, exposing heading-level search, whole-page or section retrieval, and page listing as tools and resources over stdio or Streamable HTTP. Can run as a CLI, a hosted endpoint, or a library inside an existing Node or Next.js site.
Code-mode MCP server (docs_search + execute_code two-tool surface) backed by a unified capability manifest across three sandbox kernels (in-process node:vm, WASM via QuickJS / Pyodide / Wasmtime, and remote microVM via E2B / Cloudflare Sandbox). At N=30 tools the bootstrap-context cost drops to 13.6% of direct tool-use. Apache-2.0.
docshelf-mcp manages AI-friendly document collections — converts PDFs and Markdown into chapter-split shelves with a single navigation INDEX, so AI agents can fetch only the relevant section by raw URL instead of choking on a 4 MB datasheet.
Repo: https://github.com/ignatenkofi/docshelf-mcp
Enables access to AWS documentation through natural language by fetching and converting documentation pages to markdown, searching AWS docs, and getting content recommendations for AWS service documentation.
Deterministic navigation maps over code AND markdown for AI agents: one MCP server, two lenses (tree-sitter TS/JS/Python + markdown). Map a whole project, read one function or one doc-section, ~99% less context. Merges codelens + docslens.
An MCP server that checks whether a vendor API or SDK is active, deprecated, or sunset, using a curated dataset. Enables agents to verify deprecation status before upgrade/maintenance work.
Enables AI agents to perform fast, offline full-text search and section-level retrieval over the HackTricks offensive-security wiki, including ranked snippets, page/section extraction, code-only payloads, and category navigation.
MCP server that exposes tools to route natural language queries to typed IDs, describe catalog entries, and list repository verification commands for the m-dev-tools organization.
Provides AI coding tools with queryable documentation for the AK (Active Kernel) event-driven MCU framework, including API signatures, guides, and guardrails.
