ContextLattice — Claude Code MCP server: setup
A local-first memory and context layer for AI agents that preserves project state, retrieves relevant evidence, and resumes work across sessions.
claude mcp add --transport http contextlattice https://contextlattice.io/mcpWhat ContextLattice does
ContextLattice keeps a durable project context that an agent can reopen when a session, model, or tool changes. It gathers relevant evidence with provenance, moves bounded signed context between agents, and records outcomes that can support later work.
The project is primarily operated through its CLI. MCP and HTTP provide integration surfaces, while commands cover readiness checks, context retrieval, progress notes, and resuming a task without replaying the whole conversation. Repository integration adds managed instruction blocks and preserves existing text.
A local run needs a Compose v2-compatible container runtime plus gmake, jq, rg, python3, and curl; macOS, Linux, and Windows via WSL2 are listed. Without that setup, the local quickstart will not complete. Claude Code connects through the MCP endpoint.
What it helps with
- reopen project goals after a session change
- retrieve evidence with source coverage
- save verified progress for the next agent run
- carry bounded context between agents
- add ContextLattice blocks without replacing repository instructions
Example prompts for the agent
- Use ContextLattice to reopen the project goal, recent decisions, and next action before changing the code.
- Retrieve context for the current release regression, show the supporting sources, and list any gaps in the evidence.
- Save the verified root cause and regression test as project progress so the next session can resume.
How to install ContextLattice
Platform CLI: remote server
claude mcp add --transport http contextlattice https://contextlattice.io/mcpPlatform CLI: remote server
codex mcp add contextlattice --url https://contextlattice.io/mcpConfig file
{
"mcpServers": {
"contextlattice": {
"url": "https://contextlattice.io/mcp"
}
}
}Config file
{
"servers": {
"contextlattice": {
"type": "http",
"url": "https://contextlattice.io/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http contextlattice https://contextlattice.io/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about ContextLattice
How do I install ContextLattice in Claude Code?
Run claude mcp add --transport http contextlattice https://contextlattice.io/mcp.
What does ContextLattice do?
It gives MCP-connected agents durable project context, source-aware retrieval, and a way to save progress for later sessions. It can also carry bounded context between agents.
Which platforms does ContextLattice support?
The listed platforms are Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, and Zed.
