"Exposing a markdown folder as an MCP server for Claude" matching MCP servers:

Publishes a spending-summary tool alongside an interactive HTML view, letting people click a category in the answer to fetch the individual expense records behind that total. Keeps calculations and their supporting evidence together in a single inspectable flow.

Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.

A read-only MCP server that lets you search current and historical facts from a time-indexed knowledge graph derived from a folder of Markdown/text documents, with verification against original sources. It exposes tools for status, fact search, history search, and revision lookup while keeping document insertion and modification to the CLI.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Enables an MCP client to list, read, search, stat, write, edit and move files inside one or more named root folders, with access strictly confined beneath those roots. Paths, parent-directory segments and symlinks cannot reach anything outside, and write operations are offered only when explicitly enabled.

Syncs Jira Cloud issues into local Markdown files with source metadata, kept current including deletions. Includes a local read-only MCP server so Claude Code or Codex can search, read and list recent changes. Linux.

Enables AI agents to search any local folder through a private SQLite FTS5 index that extracts text from PDFs, Office documents, plain text, code and zip listings, returning ranked matches instead of slow ls/grep scans. It also supports metadata and glob listing, paged retrieval of already-extracted text, duplicate detection, and incremental background re-indexing with secrets and caches excluded by default.

Enables users to ask natural-language questions about a local folder's contents, including file names, sizes, and timestamps, with rollups by type and age and cleanup suggestions for stale or large files. It returns metadata only and cannot read, move, or delete files.

Enables Codex to consult Claude Code for a second opinion through a local stdio MCP server, exposing the ask_claude tool for text-only reviews and recommendations using existing Claude Code authentication. Codex can request findings and tradeoff analysis without allowing Claude to edit files or run commands.

Gives Claude control of a real, headed Chromium browser via Playwright, enabling web navigation, clicking, typing, screenshots, and JavaScript evaluation.

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — not just a single LLM call. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) inside a sandboxed workspace.

Use Codex as a subagent inside Claude Code: async dispatch into a long-lived codex app-server, results pushed back into the Claude session automatically, steer/interrupt mid-task, and Codex's built-in code review.

Exposes the local Claude Code CLI as a subagent for Codex, enabling background review and implementation jobs with two fixed permission tiers.

Delegates work from MCP clients (like Claude Code) to the Codex CLI, allowing spawning of autonomous Codex subagents for tasks.

Provides a SQLite-backed MCP server that records agent memory as history, enabling explicit consolidation, source checks, revisions, narrative versions, and accountable forgetting.

Bridges a remote, cloud-hosted agent to your local machine, exposing Pi's coding tools (read, write, edit, ls, grep, find, bash, powershell) rooted at a directory you choose. It also adds a human channel so the agent can message, question, and wait on you through tool calls instead of a platform chat UI, with OAuth 2.1 or bearer-token authorization and no persistence between runs.

Lets Claude Desktop and Claude Code inspect and drive Windows desktop applications in the background, including clicking, typing, launching, and verifying results, while the user keeps their mouse, keyboard, and foreground window.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Enables reading and optionally editing existing Markdown files under a configured root folder, including section-level queries, overwrites, appends, deletions, and front matter management, over stdio with no network dependencies.

Write your resume in Markdown and export to PDF with AI assistance, using a built-in stylesheet and tools for conversion.

Fetches a URL and returns the main content as clean Markdown, using plain HTTP when possible and headless Chromium for JavaScript-rendered or bot-protected pages.

Enables agents to convert Markdown into WhatsApp-compatible formatting, including styled text, lists, and tables that fit a phone's monospace width.

Deterministic SNAP eligibility logic, exposed as auditable Model Context Protocol tools. An AI agent can read, reason, and orchestrate, but the eligibility determination itself is made by versioned, tested, cited code that a caseworker, an auditor, or a court can inspect.

Converts any URL to clean, LLM-ready Markdown by removing ads, navigation, and other clutter, using Mozilla Readability and Turndown.

Integrates Google's Gemini AI models into Claude Code and other MCP clients to provide second opinions, code comparisons, and token counting. It supports streaming responses and multi-turn conversations directly within your existing AI development workflow.

Enables AI assistants to read local documents by converting PDFs, Office files, images, and audio to Markdown on-device, without uploading them.

Enables Codex to delegate review and implementation tasks to the local Qoder CN CLI as background jobs, with two permission tiers and polling-based status updates.

A Model Context Protocol (MCP) server that provides a local-first RAG engine for your markdown documents. It uses a file-based Milvus vector database to index your notes, enabling LLMs to perform semantic search and retrieve relevant content from your local files.

Exposes product-style completion tools (OpenAI chat-completions-shaped and Anthropic messages-shaped) that are fulfilled by sampling the host agent's own LLM over MCP, so no model API keys are ever needed. Also offers a model listing endpoint aliasing the host's model.

MCP server for markdown files — search, extract sections, list headings, find code blocks across docs.