"An explanation or exploration of reasoning" matching MCP servers:

Provides search and retrieval over a local database of Pathfinder 2e rules. Enables Claude Code to answer rules questions with cited, accurate answers from fetched entries.

Enables Claude to read and analyze PDF documents with automatic OCR processing for scanned files. Features intelligent text extraction, caching for performance, and secure file access with search capabilities.

Enables coding agents to list, search, and read a curated Shopware developer and merchant knowledge base offline as plain Markdown files, without network access or an API key.

An MCP server for local PDF inspection that classifies, searches, extracts text and tables without uploading documents or relying on OCR, surfacing reliability warnings for garbled or scanned content.

Enables progressive exploration of Swagger/OpenAPI API documentation. Supports loading multiple specs, browsing endpoints and schemas, and searching across documentation.

Enables a discovery subagent that performs docs research, logs triage, and codebase exploration, returning structured findings and specifying raw reads needed by the parent agent.

An MCP server that checks whether a vendor API or SDK is active, deprecated, or sunset, using a curated dataset. Enables agents to verify deprecation status before upgrade/maintenance work.

Enables LLMs to chat with long PDFs using a reasoning-based, tree-structured document index that navigates content like a human would, without requiring vector databases or hitting context limits.

An MCP server that guides AI assistants to navigate documentation using their built-in tools (grep, file reading) instead of traditional RAG.

An MCP server that gives AI assistants access to a curated database of Apple App Store rejection reasons, solutions, and real-world cases.

An MCP server that provides surgical read/write access to individual sections of Markdown files, allowing agents to fetch, edit, or delete specific slices without touching the entire file.

An MCP server that exposes a live Dwarf Fortress fort to an AI agent as a small set of curated, semantic tools — a fortress co-pilot and early-warning advisor, not an autopilot. It provides read-only sensors and reference tools to observe the game state and retrieve game data.

A static, read-only MCP server that exposes a database knowledge base (schema, relationships, workflows, and reasoning patterns) so Claude Code / Copilot can reason about a database without a live connection.

Lets AI agents search and read a folder of Markdown documentation at query time, exposing heading-level search, whole-page or section retrieval, and page listing as tools and resources over stdio or Streamable HTTP. Can run as a CLI, a hosted endpoint, or a library inside an existing Node or Next.js site.

Enables users to create frozen, auditable snapshots of selected Markdown or text-layer PDFs and perform read-only, verifiable local searches with SQLite FTS5/BM25, preserving source hashes, schemas, and page/line anchors.

Lets AI assistants classify an AI system under the EU AI Act, returning risk tier, obligations, and deadlines based on a plain-English description of the product.

Enables efficient exploration of OpenAPI specs via markdown, with progressive disclosure of endpoints, schemas, and batch operations to minimize AI context usage.

Enables MCP-speaking assistants to search an offline library of practical self-reliance knowledge and add new documents to it.

Enables AI assistants to access the complete documentation of the jangada library, ensuring they write code using the correct and current API without guessing function names or parameters.

Enables AI agents to access a markdown wiki or knowledge base through per-topic tools that expose available domains and retrieve tables of contents, matching lines, or full pages on demand.