"Writing about MCP" matching MCP servers:

An MCP (Model Context Protocol) server that gives AI agents live, structured ad intelligence across Facebook, Google, and Instagram — data that no base model can produce from training alone. Powered by Apify actors. Works with any MCP-compatible client: Cursor, Claude, etc.

Enables asking natural-language questions about three published data builds (housing, flights, and a fictional bank), with the agent finding tables, writing SQL, and re-verifying every number against the warehouse before returning an answer.

An MCP server that connects Claude to Teradata GCFR operational reporting, enabling natural-language queries about stream status, process history, loads, transforms, errors, SLA, and data lineage without writing SQL.

Content writing toolkit for headline generation, readability scoring, tone analysis, outline building, and plagiarism similarity checking.

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 an assistant to verify whether claims about AI systems hold against supplied evidence bytes, replay conformance vectors, and inspect related terms and artifact digests offline without fetching, writing, or sending data.

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 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.

MCP server that fetches ServiceNow Community events for a date range and returns them as structured data, optionally writing a CSV. No login or credentials required.

Enables natural language queries about Swiss mandatory health insurance coverage for medications and medical devices using official BAG lists.

An MCP server that lets an LLM answer a pharmacist's question about drug shortages by normalizing drug names, finding pharmacologic alternatives, and checking their shortage status using public FDA and NLM data.

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 assistants to answer questions about livestream advertising using GingerLive's up-to-date data on ad formats, network reach, campaign case studies, and the streamer program, as well as plan campaigns and evaluate streamer monetization.

An MCP server for Meertrack that enables users to ask their AI agent about competitors' recent activities, digests, and product changes via natural language.

Gives AI assistants direct access to Microsoft Dynamics 365 Business Central via the native WebSocket protocol, replacing OData, APIs, and browser automation. Enables page navigation, data reading/writing, actions, searches, and report execution.

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.

A small MCP server that gives agents rich context about a YouTube video — its transcript, jump-to-the-moment deep links, metadata, and most-replayed moments — so they can answer questions, summarize, pull quotes, or surface highlights.

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.

MCP server that provides statistically rigorous weather and climate context by exposing the Baseline API as agent tools, enabling queries about climate conditions and comparisons against historical data.

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.

Generate and edit images with GPT Image 2.5 for $0.029 each, inside Claude, Cursor or any MCP client. A free you.bot API key comes with 50 credits (about 17 images) and needs no card.

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.

Ask about the Saudi economy in plain English or Arabic. No API key or database required.

Answers questions about what businesses in a given industry sell for by returning median and interquartile-range EV/EBITDA and EV/Revenue multiples by industry and deal size, with industry comparisons and year-by-year trends from disclosed 2018-2026 transactions. Every figure carries its deal count, thin cells are withheld rather than estimated, and no API key is needed.

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

An MCP server that exposes a local notmuch email database to an LLM client such as Claude. It is read-first: searching, reading, and understanding mail is always available; writing anything (drafts, tags, exported files) requires an explicit opt-in flag and is confined to clearly bounded locations.

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.

Enables AI agents to run read-only AWS security audits and receive normalized, severity-ranked findings about account posture, such as stale access keys, missing MFA, public buckets, open security groups, and CloudTrail coverage.

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.

Enables LLM agents to query governed GA4 metrics over MCP, returning definitions, assumptions, and failure modes from a MetricFlow semantic layer without writing SQL.

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.