"Memory" matching MCP servers:

This MCP server provides a deterministic index of the First Principles Framework (FPF) spec, enabling agents to query patterns, routes, and relations without vector databases.

A local MCP server that accumulates the business-domain knowledge of a software project — flows, integrations, decisions, nuances — and makes it available to any MCP-compatible agent (Claude Code, Cursor, Copilot, Gemini, OpenCode). The goal is to capture the why behind the code: the stuff a new developer would need six months from now to understand why a thing is built the way it is. The what is

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 semantic search over a software project's Markdown and text documentation by indexing document chunks in Qdrant and exposing retrieval through MCP tools.

Provides a structured documentation system for context preservation in AI assistant environments, helping users create and manage memory banks for their projects.

A deterministic, read-only MCP server that lets coding agents search Git-backed architecture decision records and retrieve decisions governing specific files. It includes rejected and superseded decisions, with no model, network, or write access.

A server for managing project documentation and context across Claude AI sessions through global and branch-specific memory banks, enabling consistent knowledge management with structured JSON document storage.

Enables MCP clients to work with a Memory Bank through routing, section-aware reading, governance validation, dependency graph traversal, full-text search, change tracking, and document creation or promotion.

A plain-files brain template and MCP server that lets models read owned, portable working memory via list, read, and grep-style search tools.

Enables AI coding agents to list, search, and read the official TypeSafe Jev documentation through MCP tools, with in-memory caching and no API key required.

Gives an LLM client BM25 keyword search over a local corpus of Markdown and text files, letting it find ranked passages, fetch exact chunks with source offsets, read whole documents, and list what was indexed. It runs entirely locally over stdio with an in-memory index, calling no model and requiring no API key.

An MCP server that turns the Game Boy Pan Docs into precise, citable lookups for registers, opcodes, memory, cartridges, and CPU behavior, enabling decompilation work.

Gives AI coding agents live, cached access to current Flutter, Dart SDK and pub.dev documentation returned as clean markdown, resolving class names, identifiers and packages on demand instead of relying on a model's memory. Also provides ranked name search over thousands of classes and a politeness layer with robots.txt compliance, throttling, conditional GETs and request budgets.

Memory-efficient MCP server for reading and splitting large PDF files page by page using PyMuPDF.

Enables searching documentation from GitHub repositories and web pages via MCP tools, with in-memory indexing and caching for fast retrieval.

Provides AI coding agents with durable architecture memory for repositories by generating structured project maps of responsibilities, relationships, and risks.

Provides professional C++ code style checking, best practices analysis, and modern C++ upgrade suggestions with tools for naming conventions, memory safety, const correctness, and access to comprehensive C++ style documentation.

Gives coding agents in-memory access to the language's specifications, diagnostic and fault catalogue, verified code recipes, and university curriculum, plus toolchain tools to check, evaluate, and test source when a local binary is installed.

Enables LLM agents to search and retrieve a hybrid knowledge base of manuals, videos, PDFs, DOCX files and images through tools for hybrid BM25-plus-vector search with facet and tag filters, full document retrieval, semantically similar document lookup, and timestamped video transcript segments. It ships with an in-memory backend for instant local use and an identical Elasticsearch backend for production deployment over stdio or authenticated HTTP.

Enables natural-language Q&A over multi-source documents (PDF/Markdown/web) with a self-reflective retrieval-augmented agent that cites sources, retries on poor retrieval or grounding, and supports multi-turn memory.

Provides comprehensive documentation about AWS AgentCore framework to GenAI tools, enabling users to build production-ready AI agents with enterprise-grade security, observability, and scalability. Offers guidance on identity management, API integration, monitoring, code execution, memory storage, and tool integration for AI agents.

Provides tools and resources for managing in-memory documents, allowing users to read, edit, and list document contents via the Model Context Protocol. It includes features for formatting documents to Markdown and accessing document-specific resources.

Enables AI IDEs and coding agents to navigate code at the AST symbol level, perform surgical, collision-free refactoring, and resolve live library documentation. It also supports project onboarding memory, giving agents semantic precision without regex guesswork or heavy dependencies.

Enables agents to read and write an in-memory notes store through reliable MCP tools, with configurable profiles, response budgets, capability gating, self-documentation resources, session recovery, and stdio/Streamable HTTP transports.

Provides a TypeScript MCP server scaffold that exposes tested, one-file tools to models with profile-scoped listings, honest annotations, response budgets, capability gating, and self-served guides and skills. Ships an in-memory notes backend as a working example and runs over stdio or Streamable HTTP.

An MCP server that enables AI agents to search, read, and contribute to a structured markdown knowledge base with citations, freshness tracking, and a safe write path, providing a shared, auditable company memory.

Gives Claude Code and other MCP clients cited answers from a local, code-aware hybrid index of a repository's documentation and source, returning path:line sections linked to the code symbols they name. It also stores session handoff notes and doc/code conflict decisions in a git-backed memory, all running offline with no API calls or data leaving the machine.

Enables Windows users to control WaveMetrics Igor Pro through COM, exposing MCP tools for executing commands, inspecting waves/variables/procedures, managing dialogs and compilation errors, querying local documentation, and using persistent local session memory.

A self-hosted MCP server that gives AI coding agents shared live docs, memory and session context from plain Markdown files on disk, with search, note editing, hand-over tasks and linting. It also provides a web UI with a graph of how notes connect, password-protected tokens, and offline sync.

Read-only MCP server that enables inspecting and auditing markdown agent steering files such as CLAUDE.md, AGENTS.md, GEMINI.md, SKILL.md, rules, commands and memory files. It reads files byte-exactly, outlines headings, lints frontmatter, invisible characters and broken links, estimates per-session token budgets, and locates steering files by when they load, all without ever writing, deleting or making network calls.