"Writing about MCP" matching MCP servers:

Provides local, deterministic scoring and detailed auditing of text for AI-writing patterns via two read-only tools, with no network calls or language models.

Exposes the Dalamud plugin API documentation to AI assistants, enabling them to answer questions about services, types, and methods for writing FFXIV Dalamud plugins.

Enables natural-language spatial analysis of transmission lines and wildlife/public access lands using Claude, MCP, and DuckDB. Users can ask questions about intersections, distances, buffers, and other GIS operations without writing SQL.

Enables authors to manage characters, chapters, world settings, and plot lines for novel writing, with creative inspiration tools.

Enables AI assistants to read a player's local save file and answer questions about inventory, technology, location, fleet, discoveries, scanned shops, and nanite planning without writing to the save or sending data off-device.

MCP server offering text analysis tools for writing improvement, including spellcheck, readability, keyword analysis, passive voice detection, and AI-generated content detection.

An MCP service for AI-assisted reasoning and editing on long-form fiction projects. It builds a structured index from scene files for targeted context retrieval.

Enables users to ask natural-language questions about a local folder's contents, including file names, sizes, and timestamps, with rollups by type and age and cleanup suggestions for stale or large files. It returns metadata only and cannot read, move, or delete files.

Enables querying any GitHub, GitLab, or Bitbucket repository and getting AI-generated answers about the codebase, powered by Gemini.

MCP server for system monitoring, enabling users to ask about CPU, memory, disk, network, and processes on their system.

Enables asking natural-language questions about any GitHub repository and receiving answers grounded in the actual code, with read-only enforcement and automatic repository fetching.

Enables AI agents to answer civic questions about Virginia state, county, and municipal public data, including zoning, parcel, boundary, and Code of Virginia lookups, with provenance on every answer.

Enables AI assistants to answer questions about French administrative procedures for individuals, professionals and the self-employed using only official service-public.gouv.fr guides. Every answer returns verbatim official text with a citable link and last update date, and flags low-confidence results when nothing relevant is found.

Enables reading, searching, editing, and writing files in legacy encodings such as GBK, Big5, Shift-JIS, and Windows codepages, with automatic detection and preservation of the original encoding.

Enables LLMs to discover, read, and edit tables in HTML/Markdown documents by converting messy collapsed HTML into clean pipe format and writing back with version-checked, surgical cell, row, and column operations.

An MCP server that gives models semantic context about a data warehouse, including table meaning, units, lineage, and health, to reduce guessing.

MCP server for reading and writing .docx files. Exposes four paginated tools so agents can batch-read document content and styles, write content, and union style definitions.

Enables AI agents to answer analytical questions about an online store's SQLite database through specialized read-only tools, without any risk of modifying the underlying data.

Provides Claude with read-only access to PC diagnostics including hardware specs, live performance metrics, disk usage, network checks, and more, enabling natural language queries about PC health and performance.

An MCP server that detects affiliate links and provides information about Tracklix, enabling AI assistants to answer affiliate-link-related questions without any network calls or API keys.

Scans code strings for hardcoded secrets (AWS keys, tokens, private keys, etc.) and returns redacted findings, helping AI coding agents catch secrets before writing or committing code.

Enables coding agents to turn explanations of code, pull requests, or concepts into narrated slide walkthroughs voiced locally with Kokoro, returning a link that starts playing in about a second while the remaining slides are still being written. Slides are grounded in real files and git history, checked for errors, and exportable as static folders with captions.

Enables MCP clients to look up Bible verses, perform semantic search, and access original-language word study through a local Concord instance, providing accurate citations and honesty about uncertainty.

An MCP-native research assistant — search backend, intent-routing, and writing pipeline that carries a question through search, verification, and writing, delivering whatever research you need: quick answers, verified sources, or a finished document.

Enables agents to interact with the Logflare API by writing JavaScript functions that run in a Vercel Sandbox, using three tools: search, execute_read, and execute_write.

An MCP server that uses Playwright to scrape Israeli weather forecasts from weather2day.co.il by automating a real browser, enabling an LLM to answer questions about current conditions and hourly forecasts for Israeli cities.

An MCP server that keeps raw tool output out of the context window by sandboxing and compressing results (about 98% reduction), persisting file edits, git operations, tasks and decisions in SQLite with BM25 retrieval so the agent resumes after compaction, and enforcing routing across 17 platforms via MCP and hooks. It also encourages the model to write scripts that compute answers and log only results instead of reading large data into context.

Enables reading, writing, and manipulation of Bike outlines on macOS through natural language, using AppleScript for local document management.

Lets an AI agent read a YNAB budget and ask plain-language questions about it — where money went, what still needs a category, whether an account matches the bank, and when money would run out. Changes such as categorising, splitting or budgeting are read-only by default, and every write is previewed, explicitly confirmed, and undoable.

MCP server that lets you ask questions about your Garmin training history in plain language. It ingests FIT files into DuckDB locally and exposes typed tools for analyzing activities, streams, and summaries.

MCP server that analyzes your writing style to generate personal voice rules, scores drafts for AI slop, and verifies authorship, enabling LLMs to write in your specific voice.

Reads and searches local email archives (.mbox or .eml) with full MIME parsing, enabling queries about senders, subjects, dates, and bodies while keeping all data on your machine.

Enables natural-language inquiries about personal listening history and playlist creation with enforced hard constraints and automated repair.

MCP server that exposes pre-extracted facts about code behavior, design decisions, and assumptions to AI agents, saving time and tokens by avoiding direct source file reading.

Two self-hosted MCP servers: manage a local model machine (Ollama pull/switch, LoRA training) and bridge to local Ollama/vLLM for pure language processing tasks (writing, summarizing, classifying, extraction) without giving the calling agent tools or file access.

Integrates CopyQ clipboard manager with LLM agents, enabling reading, writing, searching, and managing clipboard items organized in tabs with tags and notes through a unified interface.

Lets MCP clients ask typed questions — yes/no, choice, or score — about structured state, including images, and receive calibrated probabilities from System One decision models such as TypeSafe Jev and Cloudflare Clef. Supports TypeSafe, OpenRouter, and local providers selectable per request, with input validation and cost reporting.

Provides local academic literature search and writing support by querying OpenAlex, arXiv, and Crossref, downloading open-access PDFs, extracting IMRaD sections, and appending BibTeX references.

Bilingual (EN/ES) AI-writing detection that shows the evidence instead of a percentage: named tells with line and column, hidden-character inspection, and citation cross-checking against a document's own bibliography. Seven of its nine tools run entirely locally and never touch the network.

Enables coding agents to compile supplied files, run optional focused tests, and get static findings across ten programming languages, providing a deterministic feedback loop on the code they are about to return.