"How to work with local files" matching MCP servers:

Enables AI assistants to programmatically read, modify, and query Tableau workbook files (.twb and .twbx) on the local filesystem via 80 tools.

Enables users to inspect local Hyper files by listing files, schemas, and tables, previewing up to 100 rows, and generating sample sales Hyper data.

Enables Claude to interact with local workspace files through MCP, including listing files, summarizing CSV datasets, generating plots, executing Python scripts, and running allowlisted shell commands from a chat interface.

Enables creating and editing PowerPoint .pptx files without corruption, with native editable SVG shapes, glued connectors, table surgery, threaded comments, live editing, and a comprehensive 138-tool MCP server surface.

Enables agents to turn structured data into production-ready static maps, returning rendered PNG and SVG URLs along with an editable map link.

Open-source mind maps and whiteboard your agent draws on live: 22 tools for mind maps, notes, shapes, tables, charts, connectors, comments and HTML/PDF export; boards are local files.

An MCP server that lets Claude or ChatGPT read, create, and edit mind maps stored in a GitHub repository, with support for local and HTTP transport.

Enables users to create, inspect, analyze, format, and chart Excel workbooks by having the client LLM write Python that runs in a fresh, network-restricted Docker container. Exposes a single execute_python tool with access to openpyxl, pandas, numpy, and matplotlib, persisting files between calls.

Enables any MCP client to evaluate Wolfram Language code in a persistent local Mathematica or Wolfram Engine kernel, export results to common file formats, and inspect or manage kernel status without cloud APIs, API keys, or runtime dependencies.

A Model Context Protocol server for interacting with Lightdash, enabling AI assistants to discover data, create charts, and manage dashboards programmatically.

Turns plain text or Markdown, web pages, and local PDFs into editable Markdown outlines that can be rendered as standalone, offline-capable interactive HTML mind maps. Works with any MCP client with no API key required, since the connected model writes the final outline from a draft and cleaned source text.

Generates beautiful Excalidraw diagrams from natural language descriptions using a local llama.cpp LLM, entirely offline.

MCP server for rendering 35+ diagram types — sequence, flowchart, ER, C4, gantt, mindmap, infra, and more — to SVG/PNG with browser preview. Local rendering with palette/theme support and shareable diagrammo.app URLs.

Enables MCP clients to teach on a view-only local browser chalkboard by drawing equations, plots, molecules, diagrams, and science illustrations step by step, with snapshots and saved lessons.

Enables assistants to read and analyze construction schedules like a scheduler: CPM, float, critical paths, DCMA 14-point, logic checks, update-to-update comparison, baseline variance, and S-curves from P6 XER and MS Project files.

Enables LLMs to author, validate, and render Blueprint Chart (.bpc) files with structured dataviz pedagogy and a tight parse + render feedback loop.

Turns an LLM into a Maltego CE investigation copilot, enabling AI-assisted OSINT investigations by building, analyzing, and exporting Maltego graph files.

Enables AI agents to create data visualizations like bar charts, line charts, pie charts, scatter plots, and histograms, returning inline SVG or PNG files.

Enables AI assistants and MCP clients to run Google Maps geo-grid rank tracking for local SEO, producing heatmaps, competitor insights, historical trends, and scheduled measurements.

Offline MCP server that queries CSV, Parquet, Excel, and JSON files and generates self-contained interactive HTML reports with reproducible provenance. Built and maintained by an AI agent.

IFC/BIM toolkit with a free browser 3D viewer: validate IFC with a 0–100 Health Score, check buildingSMART IDS 1.0, read DXF drawings, and open models, floor plans, 3D sketches and live digital twins in 3D. Validation runs locally and files are not uploaded.

An MCP server that connects AI assistants to a local Wolfram Engine, enabling symbolic math, numerical analysis, and data visualization through Wolfram Language. It provides secure expression filtering, client authentication, and supports both local stdio and HTTP transports.

Enables discovery of Fabric/Power BI workspaces and semantic models, execution of DAX queries, and generation of executive HTML reports with visualizations.

Enables creating executive presentation suites from a single prompt, generating PowerPoint, interactive web deck, KPI dashboard, whiteboard infographic, and vector PDF files through MCP.

A local MCP server that renders a database schema as an interactive, dbdiagram.io-style ER diagram in your browser.

Enables local creation and maintenance of editable draw.io XML diagram files, with tools for inspecting, validating, and updating diagrams.

Enables users to query enterprise sales data from a local SQLite database and investigate anomalies through an inline dashboard with human-in-the-loop review buttons.

Enables headless control of DHI MIKE Zero, including launching and batch-running simulations, monitoring job progress and logs, and reading/plotting simulation results from DFS and RES1D files.

Enables AI hosts to generate and open Mermaid diagram links in Markdown files, providing tools for syncing, listing, and injecting diagrams via the Mermaid.ai editor.

Enables read-only inspection of graph-shaped memories such as Obsidian vaults, Memory MCP files, or SQLite databases, allowing users to visualize, search, and trace the provenance and recall of an agent's knowledge.