init_projectLABSCO SUMMARY
Repo-owned context for coding agents, shared across whichever one you happen to open.
The documents live in the repository as Markdown and travel with it, so a decision recorded from one coding agent is waiting for the next, and edits to it get reviewed in a pull request like any other file. The tools stay deliberately plain — list, get, search, create, update, link — which leaves the structure of the directory up to how your team already thinks about the codebase.
What it is
A local stdio server shipped inside the Archcore CLI. It keeps typed Markdown documents — decision records, rules, specs, plans, incident write-ups — in a directory inside your repository, and lets any MCP-compatible coding agent read, write and link them while it works.
What you get
- Documents an agent can create, read, update and remove, each typed by what it is rather than filed as loose notes
- Search across them, so an agent loads the decisions covering the area it is about to touch and nothing else
- Directed links between documents: one implements another, extends it, depends on it, or is merely related
- Bootstrapping in a repository that has no context yet — the agent sets the directory up itself
- Prompts that chain a whole cascade in one call, an idea through a requirements document to a plan
- Everything on disk as Markdown, versioned in Git and reviewed in pull requests like the code beside it
Requirements
No account and no API key — the server reads and writes files inside your repository. It is a Go binary you install first, and the CLI then writes the MCP configuration for the coding agents it detects. Because it serves the directory it was started in, an agent launched from elsewhere has to be told which repository to serve.
Setup effort
One command — curl -fsSL https://archcore.ai/install.sh | bash
USE CASES
01
Getting an agent up to speed before it edits a module
Search for the decisions and rules covering that area and load only those, instead of pasting the whole handbook into the chat.
02
Recording a decision the moment it is made
Ask the agent to write it down as a decision record, with the context and the alternatives, in the repository.
03
Turning a convention you keep repeating into a rule
Write it once as a rule document, then link it back to the decision it came from.
04
Seeing what context an agent is actually working from
List the documents in the repository and follow the links between them to find what still applies.
05
Starting in a repository with no recorded context at all
Have the agent create the directory and write the first document in the same session.
10 tools
Listed in project docs. Your client may show a different list.
list_documentsget_documentsearch_documentscreate_documentupdate_documentremove_documentadd_relationremove_relationlist_relationsBEFORE YOU INSTALL
What to know first
Tools you get
10 tools named in the project's documentation.
INSTALLATION
Connect your client
Server setup
TERMINAL
curl -fsSL https://archcore.ai/install.sh | bashMCP Clients
Claude Code
CLAUDE CODE · TERMINAL
claude mcp add --transport stdio archcore -- archcore mcpCursor
CURSOR · TERMINAL
archcore mcp install --agent cursorGemini CLI, OpenCode, Codex, GitHub Copilot, Roo Code
TERMINAL
archcore mcp installCline
Cline is set up by hand: the project's agent table marks it "manual" instead of writing the configuration for you. In Cline's MCP settings, add a local server whose command is archcore with the single argument mcp. If Cline starts it from a directory other than your repository, add --project with your repository's path (or set ARCHCORE_PROJECT_ROOT) so it serves the right one.
