"SAP" matching MCP servers:

An agent-neutral MCP server providing SQLite key/value storage, Postgres knowledge base, and Kart task queue functionality. Features SAP/1.0 authorization on every tool call for secure multi-application access.

Converts family notices (hospital, government, insurance, delivery) into action cards with confirmed facts and pending verifications, enabling collaborative family confirmation and completion.

Enables a small local LLM to build and maintain a project map by offloading event ID/date generation, batching, synchronization, recovery, and finalization to the server, so the model only decides what to read and how to classify.

MCP server that provides a navigable map of an Obsidian vault for coding agents, with tools to outline notes, fetch sections, query frontmatter, and grep content, reducing token usage compared to reading whole notes.

Generates structured project memory and exposes MCP tools for AI coding agents to query topology, read relevant files, and log changes in a repository.

An MCP server that reduces AI coding agent token usage by 80-99% through a queryable knowledge graph of code, change tracking, and persistent memory across sessions.

Enables full read/write management of SAG knowledge bases, including source and document CRUD, semantic search, knowledge graph queries, and model configuration through 18 MCP tools.

Enables MCP-compatible AI agents to connect to SoluCortex projects, recall relevant technical decisions, conventions, risks, and architecture before working, and record new memories afterward.

Enables local semantic search and management of OKF knowledge bundles via MCP tools, with hybrid BM25 and vector search.

Enables creating and querying semantic knowledge graphs to model business logic, code relationships, and project structure across multiple projects.

Enables AI agents to safely interact with golf course operations by providing real-time inventory, booking rules, pricing policies, and a self-learning memory system.

An experimental MCP server that explores neuroscience-inspired approaches to software development analysis, featuring associative memory, context-aware caching, and cross-language API detection.

Enables AI assistants to read, search, and write Markdown notes kept in Postgres, alongside a web app with a file tree, wikilinks, full-text search, and a graph. Supports OAuth or API-key connections, per-account vaults, and folders shared with other people read-only or read-write.

Enables managing personal vehicle history including mileage, maintenance, expenses, reminders, and document references through MCP tools and resources, all stored locally in SQLite.

Enables users to visualize and interact with Claude's chain-of-thought reasoning from extended thinking traces, turning them into interactive reasoning maps with typed moves, dependency graphs, timelines, and replay mode.

Intelligent AI memory management system with ML auto-triggers that automatically saves and retrieves information across AI platforms without manual intervention.

Enables any MCP-capable coding agent to share one persistent, token-frugal local SQLite memory across tools, so decisions and project facts saved in one agent are known to the others. It exposes a tiny four-tool surface for searching and retrieving gists, injecting only budgeted, relevance-gated context per session instead of dumping whole memory files.

Enables an AI agent to recall past approvals, edits and rejections that are similar to the task at hand before drafting, and to record each new decision along with the human's reason. Memory lives in a local Postgres (PGlite + pgvector) store, so corrections carry across sessions without hosting anything.

Enables AI agents to compress and selectively retrieve context, with measured recall rather than claimed performance. It provides tools to assess potential traffic and token savings, list compression dictionaries, and assemble relevant memory entries within a token budget.

Enables AI agents to add decision drafts, evidence, and counterarguments to a shared local decision state, while users confirm or reopen decisions in a web console. Prevents unverified agent answers from being silently turned into code.