INDIVIDUAL MCP TOOL
lab_get_graph
How everything connects: nodes are projects, agents, MCP servers, systems and notes keyed 'kind:slug', edges say which uses, documents, hosts or owns which.
LIVE ENDPOINT
https://zckr.dev/mcp
Connect to this endpoint to inspect the live schema for lab_get_graph and invoke it with your own arguments.
Indexed input schema
{}Risk classification
Inferred read-only · medium confidence · heuristic, not a guarantee.
- No write-capable action terms were found; this is not proof that invocation has no side effects.
Parent server
CONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.zckr-lab]
url = "https://zckr.dev/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"zckr-lab": {
"type": "http",
"url": "https://zckr.dev/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: zckr-lab
Remote MCP URL: https://zckr.dev/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"zckr-lab": {
"url": "https://zckr.dev/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"zckr-lab": {
"type": "http",
"url": "https://zckr.dev/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "zckr-lab",
"transport": "streamable-http",
"url": "https://zckr.dev/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
Related tools
lab_list_projects— List every project on zckr.dev with slug, status (building/experiment/shipped/paused/dead), type, and one-line description.lab_get_project— Full detail for one project as markdown: problem, hypothesis, architecture, measured results, learnings, and — for dead projects — the cause of death.lab_list_notes— List engineering notes (essay tier) and TILs (two-minute findings) with slugs, dates, and summaries.lab_get_note— Full markdown body of one note or TIL by slug.lab_list_agents— Every coding agent this lab runs, with its model tier, tool-grant count and one-line job.lab_get_agent— One agent in full: its tool grants verbatim, the context it receives, what it remembers between runs, how it is evaluated, and the failure modes it is known for.lab_list_mcp_servers— The MCP registry, split by origin.lab_list_systems— What the lab runs on: hypervisor, managed platforms, and the services on each, with what depends on what.