Persistent, branch-aware workflow state memory MCP server for AI coding assistants. Tracks tasks, accepted decisions, and active blockers to prevent session context bloat and speed up development.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add state-memory -- npx -y @putervision/state-memory-mcp~/.codex/config.toml
[mcp_servers.state-memory]
command = "npx"
args = ["-y", "@putervision/state-memory-mcp"]
# codex mcp add state-memory -- npx -y @putervision/state-memory-mcp~/.cursor/mcp.json
{
"mcpServers": {
"state-memory": {
"command": "npx",
"args": [
"-y",
"@putervision/state-memory-mcp"
]
}
}
}.vscode/mcp.json
{
"servers": {
"state-memory": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@putervision/state-memory-mcp"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"state-memory": {
"command": "npx",
"args": [
"-y",
"@putervision/state-memory-mcp"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"state-memory": {
"command": "npx",
"args": [
"-y",
"@putervision/state-memory-mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"state-memory": {
"command": "npx",
"args": [
"-y",
"@putervision/state-memory-mcp"
]
}
}
}