Railway MCP integration for AI agents.
Connect AI agents to Railway through 9 structured actions, including get deployment, upsert variable, deploy service, and rollback deployment. Review authent…
- ACTION CONTRACTS
- 9
- 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 Railway integration exposes
The Railway Agent App exposes 9 provider-backed actions for developer tools and infrastructure work. Its current contract lets an authorized agent get one railway deployment and its redeploy and rollback capabilities, create or update one railway variable for an environment or service, and trigger a railway deployment for a service, optionally at a specific connected-repository commit. 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 Railway account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Railway capabilities.
Showing 9 of 9 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_deploymentREADGet one Railway deployment and its redeploy and rollback capabilities.
INPUTS: deploymentId
upsert_variableWRITECreate or update one Railway variable for an environment or service.
INPUTS: projectId / serviceId / environmentId / name / value
deploy_serviceHIGH IMPACTTrigger a Railway deployment for a service, optionally at a specific connected-repository commit.
INPUTS: serviceId / environmentId / commitSha
rollback_deploymentREVIEWRoll a Railway service back to a deployment that Railway marks as rollback-capable.
INPUTS: deploymentId
get_deployment_logsREADRead runtime logs for a Railway deployment with optional text and time filters.
INPUTS: deploymentId / limit / filter / startDate / endDate
get_projectREADGet a Railway project together with its services and environments.
INPUTS: projectId
get_service_instanceREADGet Railway service configuration and its latest deployment in one environment.
INPUTS: serviceId / environmentId
list_deploymentsREADList recent Railway deployments for a service and environment.
INPUTS: projectId / serviceId / environmentId / limit
list_projectsREADList Railway projects available to the configured account or workspace token.
INPUT CONTRACTS
Know what the action needs before it runs.
get_deployment
deploymentIdOPTIONAL- Railway deployment ID.
upsert_variable
projectIdREQUIRED- Railway project ID.
serviceIdOPTIONAL- Railway service ID.
environmentIdREQUIRED- Railway environment ID.
nameREQUIRED- Variable name.
valueREQUIRED- Variable value. This may contain a Railway variable reference.
deploy_service
serviceIdREQUIRED- Railway service ID.
environmentIdREQUIRED- Railway environment ID.
commitShaOPTIONAL- Commit SHA from the repository connected to the Railway service.
rollback_deployment
deploymentIdOPTIONAL- Rollback-capable Railway deployment ID.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Deployment
Get one Railway deployment and its redeploy and rollback capabilities. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_deploymentControl Upsert Variable
Create or update one Railway variable for an environment or service. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
upsert_variableVerify with Get Deployment Logs
Read runtime logs for a Railway deployment with optional text and time filters. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_deployment_logsSAFETY BOUNDARY
Operate Railway with explicit limits
- Authorize Railway with API key and grant only the provider access required by the selected actions.
- 2 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `deploy_service` as high-impact operations and require an explicit approval boundary.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Railway rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Railway task completed successfully.
CONNECTION MODEL
API key
A Railway account or workspace token sent as a Bearer token. Create one at https://railway.com/account/tokens. Project tokens use a different authentication header and are not supported by this credential type.
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
- 6
- WRITE SIGNALS
- 1
- HIGH IMPACT
- 1
- REVIEW SIGNALS
- 1
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 Railway.