AiAgentKarl/agent-context-optimizer-mcp
MCP Server that solves context window overload — smart tool pruning, relevance scoring, budget tracking for AI agents
Platform-specific configuration:
{
"mcpServers": {
"agent-context-optimizer-mcp": {
"command": "npx",
"args": [
"-y",
"agent-context-optimizer-mcp"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
Solves the #1 problem with MCP servers: context window overload.
When you have 10+ MCP servers installed, their tool schemas can consume 40-50% of your context window — leaving less room for actual conversation. This server fixes that.
pip install agent-context-optimizer-mcp{
"mcpServers": {
"optimizer": {
"command": "uvx",
"args": ["agent-context-optimizer-mcp"]
}
}
}| Tool | Description | |------|-------------| | analyze_task | Analyze a task and recommend optimal server combination | | estimate_context_usage | Estimate context window consumption for servers | | get_server_catalog | Full catalog of known MCP servers with categories | | optimize_server_set | Optimize currently loaded servers for a task | | suggest_minimal_set | Recommend the absolute minimum servers needed |
"I need to check the safety of a Solana token"
→ Recommends: solana (required)
→ Saves: 85% context tokens vs loading all servers---
| Category | Servers | |----------|---------| | 🔗 Blockchain | Solana | | 🌍 Data | Weather · Germany · [Agriculture](https://github.com/AiAgentKarl/agricu
Loading reviews...