record_metrics
Log performance data
How to use it
record_metrics is exposed by the Evolve MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the record_metrics tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Evolve MCP
$
claude mcp add evolve-mcp -- python -m mcp_server.serverOther tools in Evolve MCP (20)
add_safety_pattern
Add custom pattern
analyze_prompt
Get complexity metrics
cancel_evolution
Stop a running cycle
check_evolution_trigger
Should evolve?
check_safety
Quick text check
crossover_variants
Combine two variants
detect_anomalies
Find anomalies
evaluate_variant
Calculate fitness score
explain_fitness
Detailed breakdown
generate_ab_pair
Create A/B test pair
generate_population
Create variant population
get_evolution_status
Check cycle progress
get_metrics_window
Aggregated metrics
list_fitness_functions
List available
mutate_prompt
Apply specific mutation
register_fitness_function
Add custom metric
resume_evolution
Resume from checkpoint
start_evolution
Begin an evolution cycle
update_fitness_weights
Adjust weights
validate_variant
Full safety check