"How to interact with Excel files" matching MCP servers:

Read, write, analyze and test the VBA inside Excel, Word, PowerPoint and Access files, and edit the document around it. The file layer needs no Office installation and runs anywhere; running macros and tests needs Windows with Office.

Generates test files locally (images, PDFs, CSVs, corrupted files, etc.) from natural language prompts, with configurable sizes and safety limits.

Provides a read-only MCP bridge that lets Claude Web inspect workspace files, git state, and recorded test results while Codex remains the sole executor of changes.

Twelve tools combine per-function complexity and branch coverage to rank work and check edited functions against their ceiling. Packets include source, uncovered lines, change-coupled files and near-duplicates. MCP calls can write local caches and metadata; they do not run test suites, edit source or claim work.

Feedback ingestion for AI agents. Record your screen and talk; your agent does the rest — files the bugs, writes the spec, builds the backlog.

Enables read-only analysis of FST waveform files, including signal value queries, timing measurements, event search, latency analysis, and PNG plot generation using human-readable time addressing.

Screen-reader navigation cost analyzer. Measures how hard it is for assistive-technology users to discover, reach, and operate interactive targets on the web.

Enables AI assistants to inspect generated .docx and .pdf files before delivery, extracting structural, typographic, spacing, and language facts so formatting errors can be caught automatically.

MCP server for autonomous end-to-end testing with Wopee.io. Analyzes web applications, generates and executes Playwright-based functional tests, and validates results — all driven by natural language commands.

An MCP server that enables AI assistants to visually inspect and interact with rendered web pages via a persistent headless Chromium browser, supporting navigation, screenshots, clicks, viewport resizing, and console log retrieval.

Creates, validates, audits, and repairs PowerPoint .pptx files against the OOXML spec, allowing users to generate spec-compliant slides from templates.

A local-first MCP server that scores your codebase's Build Readiness by reading code and running tests on your machine, outputting a diligence-grade score and risk register without uploading your source.

MCP server for semi-manual QA test execution on real Smart TVs (Tizen/webOS) and local Chrome via Chrome DevTools Protocol, enabling remote control, state inspection, and profiling.

Enables passive security scanning of HAR files from QA test automation to detect missing security headers, insecure cookies, CORS misconfigurations, and leaked secrets, without making any live requests.

Exposes Semgrep as deterministic, rule-matching analysis tools over MCP so a code-review agent can scan only the lines changed in a diff, scan whole files on demand, and check analyzer availability, version, ruleset, and limits. Results are returned as compact per-finding lines with source snippets suitable as comment anchors, along with counts of suppressed out-of-diff matches.

MCP server that validates dashboardbase setup files and widget endpoint responses against the dashboardbase JSON contract, reporting errors and warnings before deployment.

Enables agents to inspect print artwork and check it against product presets, identifying issues like low resolution, missing bleed, unsafe margins, wrong colour mode, and unwanted transparency, then suggesting fixes without modifying the files.

Audits Excel workbooks by tracing cell dependencies and detecting circular references, volatile functions, and other formula risks, enabling natural-language audit queries on local files.

A ruthless, read-only code review MCP server that analyzes code produced by AI coding assistants, catching missing requirements, security vulnerabilities, edge cases, and performance issues without ever modifying files.

A stdio MCP server that audits other MCP servers over the live protocol. It connects to any MCP target (stdio or HTTP), lints every tool's schema for agent-usability, then actually calls the tools with deliberately broken inputs to see how the server handles them, and returns a 0–100 conformance score with a per-dimension breakdown rendered as Markdown.