AI Marketplaces Leaderboard

Steadybit

Claude connectorPartner — verified

Find reliability risks in your systems: design, run, and analyze chaos experiments.

View in Claude directory
Tools
31

exposed by this connector

Movement

From our daily snapshots over the last 30 days.

Rank by popularity

#2061of 5,1835places up24h86places down7d
#1,834#1,898#1,962#2,026Sep 13Sep 19Sep 25Oct 1Oct 7Oct 12

Rank by trending score

—not ranked—24h—7d
#433#711#989#1,267Sep 13Sep 19Sep 25Oct 1Oct 7Oct 12

Popularity score

7,170+3024h+2757d
5,4925,9506,4086,866Sep 13Sep 19Sep 25Oct 1Oct 7Oct 12

Trending score

——24h—7d
17,86623,32928,79234,25539,718Sep 13Sep 19Sep 25Oct 1Oct 7Oct 12

In its category

How this connector compares with others in the same category. Positions are counted within the category, not across the whole directory.

Developer tools334th of 934 by popularity · not ranked by trending score
Order by

All 943 Developer tools connectors

Steadybit is a reliability and chaos engineering platform. This connector lets Claude work with your own Steadybit tenant: explore what you run, design and execute chaos experiments against it, and interpret the results.

Discover your systems Browse environments, teams, and services. Search targets — hosts, containers, Kubernetes workloads, cloud resources — with Steadybit's query language, inspect their attributes, and see which chaos actions your teams are allowed to use.

Design and run experiments Search and read existing experiment designs, draft new ones from a plain-language description, create them from your own templates, and start or cancel runs. Steadybit's AI can suggest experiments tailored to a service and its weak points.

Understand what happened Review past executions step by step, read execution logs, query the metrics recorded during a run, and pull reliability advice and service risk reports. Ask why an experiment failed and get an analysis grounded in the actual run data, not guesswork.

Everything Claude sees is scoped to your own permissions: the connector acts as you, limited to your teams, their environments, and the actions they may run. Read-only tools are annotated as such, and starting an experiment is marked destructive, so Claude asks before injecting a fault.

Tools

  • analyze_execution
  • cancel_execution
  • create_experiment
  • create_experiment_from_template
  • draft_experiment
  • get_action
  • get_execution
  • get_execution_artifact
  • get_execution_log
  • get_execution_metric
  • get_execution_report
  • get_experiment
  • get_reliability_advice
  • get_service
  • get_service_risk_report
  • get_target
  • get_target_stats
  • get_template
Show all 31
  • list_environments
  • list_execution_metrics
  • list_metric_label_values
  • list_teams
  • list_templates
  • run_experiment
  • search_actions
  • search_executions
  • search_experiments
  • search_services
  • search_targets
  • suggest_experiments
  • update_experiment
Categories
Made by
Steadybit · Website
Sign-in
Required
Connector URL
https://platform.steadybit.com/mcp/demo
Transport
Streamable HTTP
Works with
Claude, Claude API, Claude Code, Claude Desktop
Acts on
Servers & cloud, Logs & errors
Department
Engineering
Added
July 28, 2026
More info