2 1 2 MCP Server
The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches
context tax
queued
security
queued
cold start
queued
freshness
Active1d ago
Install 2 1 2 MCP server
Install in Claude Code
claude mcp add 2-1-2 -- npx -y @ohos-ports/agentic-flowInstall in Cursor
{
"mcpServers": {
"2-1-2": {
"command": "npx",
"args": [
"-y",
"@ohos-ports/agentic-flow"
]
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
Install in Claude Desktop
{
"mcpServers": {
"2-1-2": {
"command": "npx",
"args": [
"-y",
"@ohos-ports/agentic-flow"
]
}
}
}Settings → Developer → Edit Config (claude_desktop_config.json), then restart.
Install in VS Code
{
"servers": {
"2-1-2": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@ohos-ports/agentic-flow"
]
}
}
}Add to .vscode/mcp.json in your workspace.
Install in Windsurf
{
"mcpServers": {
"2-1-2": {
"command": "npx",
"args": [
"-y",
"@ohos-ports/agentic-flow"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
Freshness
Active — last maintenance signal 1d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-10-08 · 1d ago · GitHub
Latest release
no data · GitHub
Package published
no data · npm/PyPI
Registry entry updated
no data · official registry
FAQ
›How do I install the 2 1 2 MCP server in Claude Code?
Run: claude mcp add 2-1-2 -- npx -y @ohos-ports/agentic-flow. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does 2 1 2 require an API key?
No required environment variables are declared in its published metadata.
›Can I use 2 1 2 as a remote (hosted) MCP server?
No hosted endpoint is published; it runs locally over stdio.
›Is 2 1 2 in the official MCP registry?
No. It was indexed from npm.
Alternatives to 2 1 2
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.