"Keeper" matching MCP servers:

Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions

Multi-agent shared brain MCP server enabling cross-session memory, self-improving skill loops, and inter-agent signaling across Claude, Codex, Gemini, Copilot, and VS Code CLI agents.

Local ledger for development ports: leases a block of ports per project slot (one per working copy), renders env files, and resolves service names to URLs. No daemon, no listener.

MCP server providing context usage estimation, conversation compaction, and durable semantic memory via local embeddings and SQLite.

An intelligent MCP server that serves as a guardian of development knowledge, providing AI assistants with curated access to latest documentation and best practices.

Enables an AI assistant on macOS to read and update data in supported desktop apps such as Due Again and Gift Keeper while those apps are open and assistant access is enabled.

Enables read-only analysis of FST waveform files, including signal value queries, timing measurements, event search, latency analysis, and PNG plot generation using human-readable time addressing.

Enables AI coding agents to fetch live MDN Web Docs pages, TypeScript handbook content, and npm package metadata as clean markdown, with local search, caching, and polite throttling.

Local-only MCP server that exposes Beeper Texts data (messages, chats, contacts) from the macOS Beeper Desktop SQLite database for AI assistants and automation tools, supporting search and media retrieval across multiple platforms.

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.

Enables AI coding agents to look up live JDK javadoc, Spring Boot reference sections, and Maven Central artifact metadata as clean markdown. It provides ranked search, caching, robots-aware throttling, and errors returned as suggestions instead of raising into the MCP layer.

An MCP server that gives AI assistants access to SEC-registered financial advisor data, enabling searches by name, firm, or state, full profile lookups, disclosure history checks, and risk assessments.

Enables autonomous AI agents to execute onchain transactions, settle HTTP 402 micro-payments, and verify cryptographic execution receipts through KeeperHub with built-in safety caps.