"Understanding Unstructured Data or Concepts" matching MCP servers:

MCP server for querying work checkpoints and storing finalized timesheet reports in SQLite.

Enables MCP clients such as Claude, ChatGPT and Cursor to answer business questions about sales, customers, orders and spreadsheets in natural language by reading live Postgres/SQLite databases and Google Sheets without exporting files or gaining write access. Guardrails include AST-based read-only SQL validation, read-only database roles, row/byte caps with pagination, PII masking, bearer-token auth for remote HTTP use, and a full JSONL audit log of every tool call.

Connects AI assistants to Confluence Server/Data Center, enabling search, content management, attachments, and natural-language interaction with your Confluence instance.

A Model Context Protocol (MCP) server that connects AI assistants to Jira Server/Data Center, enabling issue management, JQL search, sprint tracking, and natural language interaction with Jira.

An MCP server that automates HR onboarding tasks including employee management, email, ticketing, meeting scheduling, and leave management, enabling AI agents to handle new-hire workflows from a single prompt.

Exposes enterprise WeChat approval, report, and check-in data reading capabilities through the MCP protocol, enabling WorkBuddy and CodeBuddy to read historical business data.

Generate professional AI-powered presentations from a topic, raw text, or document file. Export to PPTX, PDF, image, or shareable link.

Render PDFs and images from HTML templates (Jinja2, Liquid, Handlebars) or Word and PowerPoint files through the Formfeed API, check data against a template's schema before rendering, and convert Office documents to PDF.

Enables creating meeting minutes from unstructured meeting memos with validation, grounding checks, and user-approved saving.

Gives an AI assistant read- and draft-only access to a single personal Microsoft mailbox, letting it search, list and read mail, browse folders, save attachments to a jailed directory, and create new or reply drafts. It requests no send scope, so mail can never be sent, deleted, moved or marked, and calendar, contacts and files are untouched.

Renders PDFs from HTML templates or saved templates and spreadsheet data, with batch job support and document retrieval.

Render branded PDF documents (invoices, reports, certificates) and PNG social images directly from any MCP client using DocJet templates or raw HTML with JSON data.

Enables reading unstructured meeting notes, generating meeting minutes drafts, validating them against source text, and saving approved versions through a local MCP server.

LeadFuze MCP Server for contact/company enrichment from email or LinkedIn URL plus email validation. Hosted MCP endpoint: https://mcp.leadfuze.com/mcp (API key required).

Enables generation of PDF documents from JSON specs or Markdown, supporting themes, tables, images, and other rich blocks.

Generate production-ready PDFs from Markdown, HTML, or built-in templates (invoices, resumes, reports) directly from Claude or any MCP-compatible AI agent via the DocRenders API.

Enables creating PDFs from text, Markdown, or tabular data and editing existing ones through metadata and page operations, with support for CJK font embedding, tagged PDF/PDF-UA, and PDF/A archival output.

The official Model Context Protocol (MCP) server for SeaTable, built and maintained by SeaTable GmbH. It lets AI agents interact with data in your bases — reading, writing, searching, linking, and querying rows through a focused set of tools. The server intentionally focuses on data operations, not schema management (creating/deleting tables or columns), keeping the tool set lean and safe for auto

Enables Claude or Cursor to read Google Keep notes and checklists, add items, and check or uncheck them via MCP over HTTP with OAuth.

Connects Claude Code, Codex or any MCP agent to a live Galley Typst project. The agent reads the document, the file tree and real Typst compiler diagnostics, then proposes edits that a person accepts or rejects in Galley; it never writes directly. No model or API key inside: it bridges the agent you already run.