"Writing about MCP" matching MCP servers:

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.

An improved implementation of persistent memory using a local knowledge graph with a customizable --memory-path. This lets Claude remember information about the user across chats.

MCP server that connects AI coding tools to VibeCompass projects for reading context and writing decisions, conflicts, and session notes.

Exposes tools to ingest FigJam boards, retrieve context summaries, and answer free-form questions about the board content.

Provides long-term memory for agents with meaning-based recall, evidence-gated writing, and separate stores per agent mode.

Enables full Obsidian vault operations including reading, writing, searching, deleting notes, managing tags and links, with support for both local and remote access via stdio or HTTP transports.

Public, agent-searchable knowledge base about AI-native software development, served as an MCP server with tools to search, read, and list topics.

Exposes Obsidian-style Markdown vaults to MCP clients, enabling reading, writing, searching, and version-controlled editing of notes with automatic git snapshots and restore.

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 any MCP client query a Tableau Cloud knowledge graph in plain language — semantic search, node and edge lookup, lineage tracing, and impact analysis — plus reading and writing the business semantic contexts attached to it. Ships nine read tools and three guarded context-writing tools over stdio with PAT authentication.

Enables MCP-compatible agents to answer questions about you by exposing your CV through a tool, resource, and prompt.

MCP server for the Graphite Financial Knowledge Graph, enabling natural language queries about companies, supply chains, executives, regulations, and patents via MCP-compatible clients.

Gives AI coding agents persistent, evolving knowledge about a codebase, enabling them to store and retrieve observations about architecture, conventions, gotchas, and recent work context.

Provides a compressed knowledge graph of the NVIDIA AI developer stack for deterministic traversal, enabling agents to answer questions about dependencies and prerequisites with minimal tokens.

A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.

Enables Claude to query user-curated, dated memory entries stored locally, giving users direct control over what the AI remembers about them.

AI reads your codebase like a book - one page at a time. Pharaoh gives it the index and a map of how every chapter connects.

Enables AI agents to semantically search, ask questions about, and analyze videos, with persistent memory and social media import capabilities.

Connects AI assistants like Cursor and Claude to your local Daylens timeline so they can answer questions about your past work sessions, no cloud or API keys needed.

Local-first, code-aware engineering cognition for AI coding agents - persistent memory, contextual retrieval, and continuous cognition about your codebase.

Provides a read-only semantic layer over an Obsidian vault, enabling queries about projects, decisions, tasks, and related notes.

Analyses your published writing from a sitemap, extracts a corpus, and generates a Claude Skill so Claude writes in your voice.

MCP server for Rootr markdown knowledge collaboration. Provides 27 tools for reading, writing, searching, and managing documents, issues, logs, and webhooks via natural language.

A public MCP server about Boris Churzin's builds, decisions, and ops doctrine, allowing agents to interrogate his judgment instead of parsing a PDF.

MCP server that connects Cursor agents to a local Obsidian vault via the Local REST API, enabling note reading, writing, searching, patching, and organizing through natural language.

A Model Context Protocol server for combating disinformation about Venezuela, integrating real fake news patterns with optional web search.

A local MCP server for maintaining internal consistency in fiction writing, with constraint-based fact checking, branching, and author-oracle conflict resolution.

MCP server that exposes an Obsidian-style markdown vault as a shared memory for AI agents, with tools for searching, reading, writing, and querying notes and wiki-links.

Enables storing and querying structured information about software code entities (classes, functions, files) and their relationships (calls, imports) along with qualitative observations like design decisions and change rationale.

Persistent memory server for MCP clients that lets AI assistants remember facts about users across sessions via a single markdown file, with tools to read, save, search, update, delete, and organize memory.

A Model Context Protocol (MCP) server that provides AI assistants with secure access to Obsidian vaults. Enables reading, writing, searching, and managing notes without requiring Obsidian to be running.

A local knowledge graph MCP server that provides AI agents with permanent, structured memory about codebases, enabling semantic search, blast radius analysis, and convention enforcement.

Provides local MCP access to registered Obsidian vaults, enabling Markdown note operations like reading, writing, searching, and managing notes via tools for Codex and ChatGPT Desktop.

Enables AI agents to retrieve structured context about business processes, including ordered steps and responsible roles, so they can route tasks, explain procedures, and validate actions.

Make it easy for agents to build their context about your projects over time The server provides a set of tools to help agents accumulate knowledge about a project over time in a structured way.

Enables Claude to maintain persistent memory across conversations using a local knowledge graph with fuzzy search capabilities, allowing it to remember and recall information about users, relationships, and context.

About Your task manager is the best agent memory you're not using. An agent-native context layer over your existing task app.

Provides AI agents with Obsidian vault operations via the official CLI, including reading, writing, searching notes, and managing files, with security and concurrency protections.

Gives Claude persistent, local context about how you work, your weekly agenda, and shipped work, with automatic work logging and git integration—all stored privately on your machine.

An implementation of persistent memory for Claude using a local knowledge graph, allowing the AI to remember information about users across conversations with customizable storage location.