Back to search
30
MCP

cctx-optimizer

npm/cctx-optimizer

Reduce Claude Code token usage by 70-90% with cross-session memory and four-layer optimization: semantic codebase indexing, PostToolUse tool compression, turn summarization, and session consolidation. MCP server powered by Ollama — zero API calls, runs en

Uptime
0.0%
12 probes
Response
0ms
last probe
Tools
0
callable
Primary URL
—

Similar MCP servers embedding-nearest

token-optimizer-mcp
Intelligent token optimization for Claude Code - achieving 95%+ token reduction through caching, compression, and smart tool intelligence
0 tools
@cocaxcode/token-optimizer-mcp
Orchestration + observability + coach layer for Claude Code token optimization. Measures tool usage, enforces budgets, advises on complement
0 tools
io.github.ooples/token-optimizer-mcp
Intelligent token optimization achieving 95%+ reduction through caching, compression, and 80+ tools
0 tools
cctx-mcp
MCP server for AI agents — structured code analysis that cuts token usage by 87%
0 tools
Claude Token Saver
Offloads routine coding tasks to a local LLM to reduce Claude API token usage.
0 tools
io.github.blackfoil/claude-token-saver-mcp
MCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens
0 tools

How to use

Add to your Claude Desktop / Cursor / Cline MCP config:

{
  "mcpServers": {
    "cctx-optimizer": {
      "url": "None",
      "transport": "http"
    }
  }
}