MCP server for persistent context management in AI coding assistants
MCP server for persistent context management in AI coding assistants
A Model Context Protocol (MCP) server that provides persistent context management for Claude AI coding assistants. Never lose context during compaction again! This MCP server helps Claude Code maintain context across sessions, preserving your work history, decisions, and progress.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| minimal | 8 |
| standard | 22 |
| full | 38 |
{
"mcpServers": {
"memory-keeper": {
"command": "npx",
"args": [
"mcp-memory-keeper"
],
"env": {
"TOOL_PROFILE": "minimal"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| TOOL_PROFILE | Declared in the maintainer’s client configuration. | Check documentation |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Russian-language news archive since 1999: semantic search, daily digests, trending topics.
Local-first persistent memory MCP: shared SQLite key/value store, searchable, TTL-aware, secret-safe
Persistent memory for AI agents. Search and store durable facts, preferences and decisions.
Live context MCP server: resolves git, services, and tests into agent context. Local-first, MIT.