"Microsoft 365 MCP Server by Softeria AS" matching MCP servers:

Provides a SQLite-backed MCP server that records agent memory as history, enabling explicit consolidation, source checks, revisions, narrative versions, and accountable forgetting.

Local-first shared memory that several AI apps can use at once, with every change recording which app, model and machine made it.

Agent memory for facts that change. When a user corrects something, Recall replaces the old fact, tells the agent what it replaced, and keeps the old value in a history. Ask what was believed on any date, see every change to a fact, or diff two dates. Runs locally on polign_db, Postgres with pgvector, MongoDB, or Qdrant. Apache 2.0.

Continuity by Ouroboros Apps (https://ouroborosapps.com). Story continuity for fiction writers: a series bible and novel memory that keeps characters, places, timelines, and plot facts consistent across chats. Connect by pasting https://continuitywriter.com/mcp into Claude, Cursor, Grok, or ChatGPT (OAuth). Docs: https://ouroborosapps.com/docs/continuity

Milestone by Ouroboros Apps (https://ouroborosapps.com). Freelance project milestones: approved milestones, deliverables, and acceptance criteria; a milestone is only done when the saved criteria are met. Connect by pasting https://milestone-continuity2.vercel.app/mcp into Claude, Cursor, Grok, or ChatGPT developer mode (OAuth). Docs: https://ouroborosapps.com/docs/milestone

Enables searching imported AI conversations locally across different providers from an MCP client, with read-only access to the archive.

Scope by Ouroboros Apps (https://ouroborosapps.com). Freelance scope of work: approved scope, rates, deadlines, and change orders, so an assistant cannot promise work or discounts that were not approved. Connect by pasting https://scope-continuity2.vercel.app/mcp into Claude, Cursor, Grok, or ChatGPT developer mode (OAuth). Docs: https://ouroborosapps.com/docs/scope

Claim by Ouroboros Apps (https://ouroborosapps.com). Brand claims and marketing copy compliance: approved claims, offers, proof, brand voice, and banned phrases, with a check that rejects copy inventing a guarantee or discount. Connect by pasting https://claim-continuity2.vercel.app/mcp into Claude, Cursor, Grok, or ChatGPT developer mode (OAuth). Docs: https://ouroborosapps.com/docs/claim

Design contract layer for AI agents. Scans Figma, code, Storybook, and token files, reconciles conflicts, and serves a single machine-readable source of truth so every agent gets the same authoritative design rules before it builds. Local-first.

Refines development prompts and stores semantic memory to save tokens in complex Antigravity tasks, enabling token savings and enriched context.

A modular MCP server suite that provides core tools, long-term memory, knowledge RAG, skills registry, and external integrations for AI agents.

Integrates with Get Notes API to search and retrieve knowledge from configured knowledge bases with AI-powered synthesis and raw recall capabilities.

A privacy-first, local-first MCP server that provides 15 ADHD/second-brain tools for capturing, prioritizing, and resurfacing tasks with context from calendar, mail, and messages.

An MCP server that gives AI agents persistent, narrative memory: concepts as nodes, relationships as typed "because" edges, so anything filed can be pulled back by association rather than by address.

An MCP server that makes your AI agent learn and evolve by capturing feedback as reusable, persistent skills that improve over time.

Enables users to visualize the impact of edits in internal documents and emails by structuring content as a graph and tracing dependency chains.

Enables AI assistants to read, write, and manage Microsoft OneNote notebooks, sections, and pages through OAuth-authenticated MCP tools, resources, and prompts.

Exposes Microsoft BCQuality repository (Business Central development best practices) as structured tools for AI agents, enabling rule discovery, search, and application via MCP protocol.

Enables listing and continuing conversations from Claude Code, Codex, Cursor, and GLM, allowing context handoff between tools by providing historical transcripts as context.

Enables an LLM to keep a persistent scratchpad by adding and reading notes, retrieving the latest note as context, and generating summaries through MCP.

Enables AI tutors to maintain durable, local-first learning state by modeling goals as prerequisite-aware knowledge trees, reusable concepts, and evidence-gated mastery.

MCP server for Locus, a local semantic dataspace manager powered by Ollama. It exposes all Locus HTTP endpoints as MCP tools to manage dataspaces, ingest documents, and perform semantic search.

A custom Memory MCP Server that acts as a cache for Infrastructure-as-Code information, allowing users to store, summarize, and manage notes with a custom URI scheme and simple resource handling.

Provides project memory management for Claude Desktop, storing memories as Markdown files with intelligent keyword-based retrieval and automatic creation/update decisions by LLM.

Enables AI agents to manage a markdown vault wiki by creating, reading, updating, deleting, moving, and searching notes, as well as giving feedback and asking questions with missed information logged for later retrieval.

A local-first Python MCP server that turns Gmail, Outlook/Microsoft 365, iCloud Mail, and generic IMAP/SMTP mailboxes into a synchronized, searchable OKF knowledge layer, exposing 38 tools and four resources for mailbox actions, synchronization, retrieval, attachments, and optional semantic search while keeping the provider mailbox authoritative.

iwec gives AI agents structured access to your Markdown notes as a knowledge graph instead of a pile of files. Agents search, retrieve, traverse, and refactor your notes by structure and links — not blind text similarity — working from the same plain .md files you edit by hand. No database, no cloud, no lock-in.

A native macOS app with a read-only stdio MCP server for searching a local work timeline by app, document, optional Chrome page context and time. Requires Apple silicon and macOS 15+; it runs on the user’s Mac, rather than in Docker or as a hosted endpoint.

Demonstrates Agent 365's bring-your-own-MCP flow by enabling natural-language search of a Zava IT support knowledge base, retrieval of support ticket statuses, and creation of new support tickets.

Enables AI agents to read, search, write, and update Microsoft OneNote pages through the Model Context Protocol.