"Guidance on orchestrating new software projects" matching MCP servers:

A Model Context Protocol server that saves prompts with timestamps and allows users to list previously saved prompts for Claude Desktop.

On Board is a local MCP server that gives multiple AI agents and IDEs a shared project memory, ticket queue, and handoff history, so agents can seamlessly continue each other's work. It supports agent-to-agent wake events, enabling autonomous workflows like reject-fix-resubmit cycles without human relay.

Project Memory stores decisions, evidence, outcomes and reviewed lessons in local SQLite. Assistants retrieve bounded context through three MCP tools. People follow and plan work in a live workspace with an overview, sprint board, decision history, readable documents, skills and project maps. Offline exports remain available.

Shelfmark is an MCP server that builds a local metadata catalogue of your documents, enabling AI agents to discover, search, and select relevant files without opening or indexing their contents. It provides governed access with ownership and confidentiality controls, ensuring agents only see what they are permitted to.

A deterministic, local-first memory engine for AI assistants that provides versioned context management via MCP, enabling token-budgeted context patches with provenance and explainability.

MCP bridge for PDF Content Search — full-text PDF search with Apple Vision OCR across thousands of documents in under a second from Claude, Cursor, or any MCP client. Advanced filters (date, category, sender, amount), wildcards, boolean operators. Bridge open-source (MIT), PDF Content Search app is commercial with free iOS+Android companion scanner apps.

A git-backed MCP server that centrally manages AI agent skills, tools, and knowledge with role-based access, change requests, and a remote OAuth 2.1 endpoint.

The coordination layer for AI agent networks, providing persistent memory, task management, inter-agent messaging, and human oversight through native MCP tools.

Enables saving project facts as they occur and retrieving only task-relevant entries when starting new work, using Jev evaluation to rank them while preserving all stored context.

Enables Claude Code to search, browse, and read its own past conversation history across all projects using BM25 keyword search.

Provides tools for managing quantitative research knowledge graphs, enabling structured representation of research projects, datasets, variables, hypotheses, statistical tests, models, and results.

Provides tools for managing project knowledge graphs, enabling structured representation of projects, tasks, milestones, resources, and team members.

Universal MCP knowledge server for LLM agents, powered by local RAG, providing domain-specific best practices and playbooks across software engineering, marketing, video editing, and other knowledge areas.

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 producing verifiable FORRT nanopublication chains with grounded quote verification and compact Science Live constellation projections, supporting reproduction, replication, and new research workflows.

A local-first MCP server that gives AI coding assistants persistent, structured, human-readable memory for a software project by storing project knowledge as Markdown files in the project's .dev-context-memory/ folder.

Knowledge-lifecycle MCP: turn agent work into memory, recall it across projects

Search past OpenCode conversation history before starting new work on a module or file, via a local read-only FTS5 index built from OpenCode's own SQLite database. No network calls, fully local. 7 tools for keyword search, file lookup, and session browsing.

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

Marrow is an MCP server that solves agent amnesia. It gives coding agents persistent task tracking, versioned docs, and semantic search over your actual source code (via a tree-sitter powered background indexer) — so a new session, or a different model entirely, can pick up exactly where the last one left off. Built for multi-agent, multi-session software delivery.