Bitrise MCP integration for AI agents.
Connect AI agents to Bitrise through 4 structured actions, including get build, trigger build, and list apps. Review authentication, inputs, workflows, and s…
- ACTION CONTRACTS
- 4
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Bitrise integration exposes
The Bitrise Agent App exposes 4 provider-backed actions for developer tools work. Its current contract lets an authorized agent retrieve one bitrise build by app slug and build slug, trigger a bitrise build or pipeline for an app, and list bitrise apps available to the authenticated account. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Bitrise account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Bitrise capabilities.
Showing 4 of 4 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_buildREADRetrieve one Bitrise build by app slug and build slug.
INPUTS: appSlug / buildSlug
trigger_buildWRITETrigger a Bitrise build or pipeline for an app.
INPUTS: appSlug / branch / workflowId / pipelineId / commitHash
list_appsREADList Bitrise apps available to the authenticated account.
INPUTS: sortBy / next / limit / title / projectType
list_buildsREADList builds for a Bitrise app with optional filters and pagination.
INPUTS: appSlug / sortBy / branch / workflow / commitMessage
INPUT CONTRACTS
Know what the action needs before it runs.
get_build
appSlugOPTIONAL- Bitrise app slug.
buildSlugOPTIONAL- Bitrise build slug.
trigger_build
appSlugREQUIRED- Bitrise app slug.
branchOPTIONAL- Git branch to build.
workflowIdOPTIONAL- Bitrise workflow ID to trigger.
pipelineIdOPTIONAL- Bitrise pipeline ID to trigger.
commitHashOPTIONAL- Git commit hash to build.
list_apps
sortByOPTIONAL- Application sort order.
nextOPTIONAL- Pagination cursor returned by Bitrise in paging.next.
limitOPTIONAL- Maximum number of items to return. Bitrise allows up to 50.
titleOPTIONAL- Filter apps by title.
projectTypeOPTIONAL- Filter apps by project type, such as ios or android.
list_builds
appSlugREQUIRED- Bitrise app slug.
sortByOPTIONAL- Build sort order.
branchOPTIONAL- Filter builds by branch.
workflowOPTIONAL- Filter builds by workflow name.
commitMessageOPTIONAL- Filter builds by commit message.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Build
Retrieve one Bitrise build by app slug and build slug. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_buildControl Trigger Build
Trigger a Bitrise build or pipeline for an app. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
trigger_buildVerify with List Apps
List Bitrise apps available to the authenticated account. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
list_appsSAFETY BOUNDARY
Operate Bitrise with explicit limits
- Authorize Bitrise with API key and grant only the provider access required by the selected actions.
- 1 action is change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Bitrise rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Bitrise task completed successfully.
CONNECTION MODEL
API key
Bitrise API token sent as the Authorization header. Create or view Personal Access Tokens and Workspace API tokens from Bitrise API settings at https://app.bitrise.io/me/profile#/security.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 3
- WRITE SIGNALS
- 1
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Bitrise.