kage / setup / langgraph
Setup guide

Set up Kage in LangGraph

communitystdiowrite capableno verified config · noindex

Persistent, verified memory for coding agents — so they stop re-explaining your codebase and never act on stale knowledge. Every memory is checked against your actual code; lives in your repo as plain files, shared via git. No account, no DB. Install: npx -y @kage-core/kage-graph-mcp install


01Configuration
# Kage via LangGraph # transport: stdio # launch: npx -y @kage-core/kage-graph-mcp

LangGraph connects to MCP servers in code. Use its MCP client with the command/URL below; exact API varies by version.


02Steps
  1. Make sure LangGraph is installed and up to date.
  2. Wire the server into LangGraph using its MCP client API.
  3. Provide any required API keys/credentials as environment variables.
  4. Restart LangGraph and confirm Kage’s tools appear.

03Other runtimes

04Provenance
config_sourcegenerated from captured install method
last_checked2026-07-06 11:26Z
sourcesGitHub repo search [p4]

Next step

Want agents that act within guardrails? Apex is the live governed-agent product — paced, capped, and fully-logged actions with approvals before anything runs.

Explore Apex →

See also: server page · is it safe? · alternatives

Set up Kage MCP in LangGraph — MCPExplorer