Goldentrii MCP Server
by goldentriiio.github.Goldentrii/agent-recallv3.4.31
Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
context tax
queued
security
queued
cold start
queued
freshness
Active19d ago
Install Goldentrii MCP server
Install in Claude Code
claude mcp add goldentrii -- npx -y agent-recall-mcpInstall in Cursor
{
"mcpServers": {
"goldentrii": {
"command": "npx",
"args": [
"-y",
"agent-recall-mcp"
]
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
Install in Claude Desktop
{
"mcpServers": {
"goldentrii": {
"command": "npx",
"args": [
"-y",
"agent-recall-mcp"
]
}
}
}Settings → Developer → Edit Config (claude_desktop_config.json), then restart.
Install in VS Code
{
"servers": {
"goldentrii": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agent-recall-mcp"
]
}
}
}Add to .vscode/mcp.json in your workspace.
Install in Windsurf
{
"mcpServers": {
"goldentrii": {
"command": "npx",
"args": [
"-y",
"agent-recall-mcp"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
Freshness
Active — last maintenance signal 19d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-09-21 · 19d ago · GitHub
Latest release
2026-09-12 · 27d ago · GitHub · v3.4.50
Package published
no data · npm/PyPI
Registry entry updated
2026-06-20 · 4mo ago · official registry · v3.4.31
FAQ
›How do I install the Goldentrii MCP server in Claude Code?
Run: claude mcp add goldentrii -- npx -y agent-recall-mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does Goldentrii require an API key?
No required environment variables are declared in its published metadata.
›Can I use Goldentrii as a remote (hosted) MCP server?
No hosted endpoint is published; it runs locally over stdio.
›Is Goldentrii in the official MCP registry?
Yes, as io.github.Goldentrii/agent-recall.
Alternatives to Goldentrii
Other memory MCP servers.
MemoryActiveKnowledge graph-based persistent memory for maintaining context.
HindsightActiveHindsight: long-term memory for AI agents modeled on human memory.
Codebase MemoryActiveIndexes a repo into a persistent local knowledge graph of functions, classes, call chains, HTTP routes and cross-service links, using tree-sitter and LSP.
CogneeActiveMemory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources.
HonchoActiveMemory that reasons: continual learning for stateful agents. Better context, fewer tokens.
Basic MemoryActiveLocal-first AI memory: a semantic knowledge graph of Markdown files that humans and LLMs both read and write, with optional cloud sync and team workspaces.