MCP.so
Sign In

GroundworkVerifiedFeatured

@Rarefied-Earth

RepositoryHomepageDocumentation

About Groundwork

Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "groundwork": {
      "url": "https://connector.rarefied.earth/public/mcp"
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Groundwork?

Company memory for your AI tools. It serves your brand, voice rules, charter, priorities, module catalog, and entitled skill how-tos into Cursor, Claude, and other MCP clients. Public proof needs no account. Docs public. Source closed.

How to use

  1. Open https://rarefied.earth/groundwork/install/
  2. One-click Add to Cursor, or paste the public MCP URL into your client: https://connector.rarefied.earth/public/mcp
  3. Call company_status (or the public proof tools) to see live company state.

Install page: https://rarefied.earth/groundwork/install/ GitHub: https://github.com/Rarefied-Earth/groundwork

Key features

  • Read-only company-state MCP (zero model calls on Rarefied Earth's account)
  • Brand, voice, charter, priorities, modules, skill discovery
  • Public no-account taste path for first value in under a second
  • Tenant-scoped entitlements for real deployments

Comments

Basic information

Category

Memory & Knowledge

License

NOASSERTION

Author

Rarefied-Earth

Submitted by

Joseph Scott

More Memory & Knowledge MCP servers

Orcha

westonhancock

Orcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age

Memory

modelcontextprotocol

Model Context Protocol Servers

88.1K

Agimem

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.

Tempreon

Tempreon

Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

ctxfile

ctxfile

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

2