"Kingsoft Document Connector" matching MCP servers:

Keyless, local MCP server bringing ISTQB / OWASP / IEEE / ISO / EU AI Act QA standards into your AI client. Standards-grounded retrieval, deterministic QA effort estimation, automated QA document quality review (0-100 rubric), and JUnit/CSV test-results flakiness analysis.

Deployment-readiness harness for AI document-QA and extraction systems. Scaffolds grounding checks, privacy redaction and cost tracking into a project, composing OpenGATE, Redacta and PubCrawl.

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.

Enables agents and users to validate Kubernetes manifests (YAML/JSON, multi-document) against the API of a chosen Kubernetes version without needing a cluster. It reports removed or deprecated APIs with replacements, unknown or misspelt fields, misconfigurations the API server would reject, Pod Security Standard violations, and common risks, each with file, line, and fix.

Automates generation of QA artifacts such as API tests, E2E tests, and documentation exports. It supports REST Assured, Cypress, and Excel/Word document generation.

Serves offline document validation and evaluation operations of the Judgment Pack Specification to MCP clients over stdio, enabling agents to validate and evaluate JPS documents as tool calls. Supports conformance validation, experimental evaluation with disposition and error classes, and corpus testing.

Local Markdown-to-PDF MCP server with four tools to list themes, render a document, validate an existing PDF, and create a document from a template. Requires Python, Pango/GLib, and fonts; its 0–100 report is heuristic, not print or accessibility certification.

Enables coding agents to capture, measure and explore any user interface in Chromium, producing a provenance-tagged UI DNA document and a verifiable React project rebuilt from it. Provides a deterministic DiffReport so each reconstruction can be checked pixel-by-pixel, style-by-style and transition-by-transition against the original.

Enables language models to query, inspect, check, and validate XML documents through XPath 1.0 expressions and XSD schemas without loading the full document into a context window. Documents stay on disk while models retrieve exact counts, values, and structural summaries via tool calls.

Enables LLM agents to drive a selector-free browser through natural language, so they can debug styling and console errors, map and document web apps, and generate or run end-to-end and exploratory tests without screenshots.

Enables users to validate a remote MCP server against Claude connector directory rules — sign-in discovery, tool metadata, and listing requirements — and walk through publishing it to npm, the official MCP Registry, a Claude Code plugin repo, and the Claude connector directory one step at a time.

Enables local image analysis and document processing through MCP workers (Vision and Document) using Ollama models, with cloud orchestration for mixed hierarchical tasks. Supports tools for image understanding, requirement extraction, test case generation, and GPU memory lifecycle management.

An MCP server that exposes a document store for evaluating agent tool-use accuracy and measuring resistance to indirect prompt injection, with built-in conformance to the 2026-07-28 MCP protocol.

Enables AI-powered document analysis and querying for project documentation using vector embeddings stored in Redis. Supports document upload, context-aware Q\&A, automatic test case generation, and requirements traceability through OpenAI integration.

Exposes read-only and write probes over a remote Streamable-HTTP /mcp endpoint so users can verify that ChatGPT Web discovers and calls remote tools, and test whether write actions actually execute on their plan. Real HWPX document editing is not yet supported; this P0 release only measures connectivity and read/write action boundaries.

Checks that every computed number in a Markdown document still matches the formula that produced it, and repairs it under an explicit write gate — so an agent's correct formula can't ship with a wrong total. Exposes every VisiMark command as a tool (check, explain, eval, infer, format), the authoring discipline as resources, and the orderings an agent gets wrong unsupplied as prompts. Read-only by