agent memory mcp for VS Code
io.github.xultrax-web/agent-memory-mcp
Markdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database.
client:VS Code
transport:stdio
runtime:npm
Install agent memory mcp in VS Code
.vscode/mcp.json
{
"inputs": [
{
"type": "promptString",
"id": "agent-memory-dir",
"description": "AGENT_MEMORY_DIR",
"password": true
},
{
"type": "promptString",
"id": "agent-memory-scope",
"description": "AGENT_MEMORY_SCOPE",
"password": true
},
{
"type": "promptString",
"id": "agent-memory-log",
"description": "AGENT_MEMORY_LOG",
"password": true
}
],
"servers": {
"agent-memory-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@xultrax-web/agent-memory-mcp"
],
"env": {
"AGENT_MEMORY_DIR": "${input:agent-memory-dir}",
"AGENT_MEMORY_SCOPE": "${input:agent-memory-scope}",
"AGENT_MEMORY_LOG": "${input:agent-memory-log}"
}
}
}
}
VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs