Remembra Relay

local MCP server

Installation

Terminal

claude mcp add remembra -e REMEMBRA_API_KEY=... -e REMEMBRA_URL=... -e REMEMBRA_AGENT_ID=... -- uvx remembra-mcp

Run in your project folder. Add --scope user to use it everywhere.

Claude Desktop, Cursor & other clients

Add to claude_desktop_config.json or .cursor/mcp.json.

{
  "mcpServers": {
    "remembra": {
      "command": "uvx",
      "args": [
        "remembra-mcp"
      ],
      "env": {
        "REMEMBRA_API_KEY": "...",
        "REMEMBRA_URL": "...",
        "REMEMBRA_AGENT_ID": "..."
      }
    }
  }
}

Fill in the environment variables with your own credentials.

Summary

Cross-agent handoff: the next coding agent starts from the last one's facts, not a blank page.

Questions

Remembra Relay is a local MCP server distributed as the pypi package remembra-mcp.

Run: claude mcp add remembra -e REMEMBRA_API_KEY=... -e REMEMBRA_URL=... -e REMEMBRA_AGENT_ID=... -- uvx remembra-mcp

Run: codex mcp add remembra --env REMEMBRA_API_KEY=... --env REMEMBRA_URL=... --env REMEMBRA_AGENT_ID=... -- uvx remembra-mcp

Similar MCP servers

NameStars

rag-ratio.github.cq27-dev/rag-rat20
Figma-Context-MCPio.github.GLips/Figma-Context-MCP16K
Agent-Native Designio.github.BuilderIO/agent-native-design6,874
Argentio.github.software-mansion/argent2,917
loki-modeio.github.asklokesh/loki-mode1,072
projectmemio.github.riponcm/projectmem844
Agent Swarmio.github.desplega-ai/agent-swarm835
clawdcursorio.github.AmrDab/clawdcursor402