Give your agents the tools to act.
A toolkit connects an agent to an app or service, with every action it offers labelled read, write or destructive, so you decide what an agent may touch.
GitHub
Manage repositories, issues, pull requests, and Actions.
GitLab
Browse projects, triage issues, review merge requests, and check pipelines.
Bash
Run shell commands in the project's own sandbox, or read files, list directories and search the filesystem under a narrower read-only grant.
Browserbase
Run headless browsers in the cloud, and fetch or search the web through Browserbase.
Buildkite
Read failed builds, job logs and artifacts, and trigger, rebuild, retry or unblock Buildkite builds.
CircleCI
Read failed pipelines, workflows, jobs, test results and artifacts, and trigger, rerun or cancel CircleCI workflows.
ConfigCat
Read and change feature flags, their per-environment values, configs and the audit log in ConfigCat.
Context7
Pull current, version-specific library documentation and code examples into an agent's context, and add your own repositories and sites to the index.
Docker Engine
Inspect and restart containers, images, and Compose services on a Docker host.
GrowthBook
Read and toggle feature flags, and read experiments and their results, in GrowthBook.
Postman
Read Postman workspaces, collections and environments, and run the monitors that test an API on a schedule.
SonarQube
Read code-quality issues, quality gates, measures and security hotspots from SonarQube Cloud or SonarQube Server, and triage them.
Unleash
Find, create and toggle feature flags, manage rollout strategies, and read the event log in Unleash.
incident.io
Read and run incidents, status updates, follow-ups, alerts, on-call schedules and escalations in incident.io.
Want to compare connection types, or see each toolkit’s transport? The full integrations directory has those filters.
Need a tool that isn’t listed?
Build a toolkit for your own API and give any agent access to it.