approve_blueprint
ChatGPTThis tool is in public alpha (early access). Access to this tool and its contract are subject to change. Approve and apply the Blueprint's newest planned sync after confirming that planning succeeded. Approval can update existing resources. After the first approval, Git pushes apply changes automatically when autoSync is enabled. Manually requested plans require approval even when autoSync is enabled. Call approve_blueprint only after the user authorizes applying the reviewed plan. Providing or allowing generation of manual environment values, or accepting costs, does not by itself authorize deployment. Supply a user-provided value in manualEnvVars for every entry in sync.requiredManualEnvVars. Use values the user has already supplied and ask only for missing values. Never invent a value. These values appear as plaintext in the agent context. If the user prefers to keep secrets outside that context, explain that they can supply manualEnvVars directly through POST /v1/blueprints/{blueprintId}/approve, or approve the sync at dashboardUrl and then set values on each service's Environment page. For the Dashboard option, explain that initial deployments may fail until the values are set. The tool returns before the sync and deployments finish. Report the returned sync state and share dashboardUrl so the user can track progress in the Render Dashboard.
cancel_cron_job_run
ChatGPTCancel the in-progress run of a cron job. Canceling stops the run partway, which can leave its work half done, so confirm with the user first. It does not pause the schedule: the next scheduled run still starts on time. Afterward, list_events with eventTypes cron_job_run_ended shows the run as canceled.
cancel_flow_run
ChatGPTRequest cancellation of a pending or running flow run. Cancellation stops the flow and cannot be undone. Returns once the request is accepted; poll get_flow_run until the status is canceled.
create_blueprint
ChatGPTThis tool is in public alpha (early access). Access to this tool and its contract are subject to change. Create a Render Blueprint from a Blueprint YAML file in a public repository or a repository accessible through a connected Git provider, and plan its first sync. By default, the plan creates separate resources and leaves existing resources unchanged. Resource changes are applied only after approval with approve_blueprint. After the first approval, later pushes deploy automatically when autoSync is enabled. All Blueprint changes are read from the remote repository. When working in a local checkout, push your changes first and pass its origin URL as repoUrl and current branch as branch. The tool returns blueprint, planningOutcome, sync, and notices. Use planningOutcome to determine whether planning succeeded and what to do next. Read planningOutcome to determine the next step. If planningOutcome is "failed", inspect the errors in notices. Address the reported issues and push any Blueprint file changes, then call plan_blueprint with the Blueprint ID again. Do not approve a failed plan, even if sync is present. If planningOutcome is "no_changes", this planning attempt found no infrastructure changes. Do not call approve_blueprint for this result. If planningOutcome is "planned", sync contains the proposed infrastructure changes. Summarize them for the user or share sync.dashboardUrl for review. To apply the changes, call approve_blueprint with the Blueprint ID and follow its guidance for supplying any required environment variable values. Call approve_blueprint only after the user authorizes applying the reviewed plan. Providing or allowing generation of manual environment values, or accepting costs, does not by itself authorize deployment.
create_cron_job
ChatGPTCreate a new cron job in your Render account. A cron job is a scheduled task that runs on a recurring schedule specified using cron syntax. Cron jobs are ideal for background tasks like data processing, cleanup operations, sending emails, or generating reports. By default, these services are automatically deployed when the specified branch is updated. This tool is currently limited to support only a subset of the cron job configuration parameters. Deploying prebuilt images from a container registry is not supported. To create a cron job without those limitations, please use the dashboard at: https://dashboard.render.com/create
create_key_value
ChatGPTCreate a new Key Value instance in your Render account
create_postgres
ChatGPTCreate a new Postgres instance in your Render account
create_static_site
ChatGPTCreate a new static site in your Render account. Apps that consist entirely of statically served assets (commonly HTML, CSS, and JS). Static sites have a public onrender.com subdomain and are served over a global CDN. Create a static site if you're building with a framework like: Create React App, Vue.js, Gatsby, etc.This tool is currently limited to support only a subset of the static site configuration parameters.To create a static site without those limitations, please use the dashboard at: https://dashboard.render.com/static/new
create_web_service
ChatGPTCreate a new web service in your Render account. A web service is a public-facing service that can be accessed by users on the internet. By default, these services are automatically deployed when the specified branch is updated and do not require a manual trigger of a deploy. The user should only be prompted to manually trigger a deploy if auto-deploy is disabled. This tool is currently limited to support only a subset of the web service configuration parameters. Deploying prebuilt images from a container registry is not supported. To create a service without those limitations, please use the dashboard at: https://dashboard.render.com/web/new
create_workflow
ChatGPTCreate a real workflow in the selected workspace from a Git repository Render can clone. The configuration request is limited to 256 KiB. Automatic deployment defaults to commit; creation starts the initial build unless autoDeploy is off. Do not immediately call create_workflow_version after creation. Use list_workflow_versions and get_workflow_version to check readiness. A timeout does not prove creation failed; reconcile with list_workflows before retrying. Task execution is separate.
create_workflow_version
ChatGPTRequest a new deployment of an existing workflow. This changes which version subsequent task runs use once ready; it does not start a task run. Skip after creation or a push when an automatic deployment is already expected: commit starts on pushes, checksPass waits for repository checks. Use for manual deployment when autoDeploy is off, an explicitly requested redeploy, or a chosen commit. Returns acceptance, not readiness; follow with get_workflow_version or list_workflow_versions. Do not automatically retry a timed-out or disconnected request.
get_blueprint
ChatGPTThis tool is in public alpha (early access). Access to this tool and its contract are subject to change. Retrieve a Blueprint's settings and status, along with the IDs of the resources it manages. The tool returns the Blueprint detail object from the REST API. When autoSync is true, the Blueprint is configured to sync automatically on Git pushes to its configured branch. Automatic syncing requires approval of the Blueprint's first sync. When autoSync is false, syncing requires manual planning and approval. The Blueprint's status remains "created" until its first sync has been approved. After that approval, the status is "paused" whenever autoSync is false, regardless of the state of any manual sync. You can still use plan_blueprint and approve_blueprint while automatic syncing is paused. When autoSync is true and the first sync has been approved, the status reflects the latest sync. A status of "syncing" means that the sync is queued or running, and "error" means that it failed. The status can be "in_sync" when the latest sync has succeeded or when a plan is awaiting approval. Do not use the status alone to determine whether services are healthy or whether the infrastructure matches the current Blueprint file. To check for infrastructure changes, use plan_blueprint and follow its guidance for reviewing the plan with the user before approval. This tool does not create a plan or apply infrastructure changes.
get_deploy
ChatGPTRetrieve the details of a particular deploy for a particular service.
get_flow
ChatGPTGet a registered flow's name, workflow ID and version ID in the selected workspace.
get_flow_run
ChatGPTInspect a flow run's status, error, error details and attempts (zero-indexed). A flow run gets a new attempt when it resumes after its process is interrupted; it replays completed steps rather than rerunning them. Errors are capped at 4 KiB each with errorTruncated flags. Inputs and results are omitted: use get_flow_run_results for results, list_flow_run_steps for steps, and list_logs with the workflow ID as resource and this ID as taskRun for logs. Poll this tool to wait for a run started with start_flow_run. Flow failure is data, not a tool failure.
get_flow_run_results
ChatGPTRead a terminal flow run's results as paged JSON text, preserving arrays and integers exactly. Nonterminal runs return ready=false, not a final result. Concatenate content pages, passing nextOffset and sha256 on each follow-up; nextOffset=null marks the end. Do not infer success from ready=true: inspect status. Failed and canceled runs may have null or empty results.
get_flow_run_step
ChatGPTGet one flow run step's status, result, and error. The step's input is omitted. Errors are capped at 4 KiB each with errorTruncated flags. result is present only when the step succeeded; null means the step returned no value.
get_key_value
ChatGPTRetrieve a Key Value instance by ID
get_metrics
ChatGPTGet performance metrics for any Render resource (services, Postgres databases, key-value stores). Supports CPU usage/limits/targets, memory usage/limits/targets, service instance counts, HTTP request counts and response time metrics, bandwidth usage metrics, database active connection counts for debugging, capacity planning, and performance optimization. Returns time-series data with timestamps and values for the specified time range. HTTP metrics support filtering by host and path for more granular analysis. Limits and targets help understand resource constraints and autoscaling thresholds. Metrics may be empty if the metric is not valid for the given resource.
get_postgres
ChatGPTRetrieve a Postgres instance by ID
get_selected_workspace
ChatGPTGet the workspace stored in the session compatibility fallback. Request-scoped workspaces supplied with an explicit workspaceId are not reflected by this tool.
get_service
ChatGPTGet details about a specific service
get_workflow
ChatGPTGet a Workflow's configuration and verify it belongs to the selected workspace.
get_workflow_run
ChatGPTInspect a task run's status, errors and all attempts (zero-indexed), plus parent/root relationships. Errors are capped at 4 KiB each with errorTruncated flags. Inputs/results are omitted. Use get_workflow_run_results for results. Report attempts as returned; retries and timestamps alone do not prove how many attempts ran or how long they queued. Task failure is data, not a tool failure.
get_workflow_run_results
ChatGPTRead a terminal run's or attempt's results as paged JSON text, preserving arrays and integers exactly. Nonterminal states return ready=false, not a final result. Concatenate content pages, passing nextOffset and sha256 on each follow-up; nextOffset=null marks the end. Do not unwrap the API's results array or infer success from ready=true: inspect status. Failed/canceled runs may have null/empty results.
get_workflow_task
ChatGPTGet a registered task's name, workflow ID and version ID in the selected workspace.
get_workflow_version
ChatGPTGet a Workflow version's build/registration status in the selected workspace.
list_deploys
ChatGPTList deploys matching the provided filters. If no filters are provided, all deploys for the service are returned.
list_events
ChatGPTList a service's event history: deploys, builds, restarts, failures, scaling, suspensions, and disk changes. Use it to find out what happened to a service and why. Failure events carry the reason a service went down, such as out-of-memory kills, non-zero exits, failed health checks, and evictions, which may not show up in logs. The first page covers the last 7 days unless startTime says otherwise. For older events, page with the cursor from the previous call. If the first page comes back empty there is no cursor to follow, so set an earlier startTime instead. Events cover services only, not Postgres or Key Value instances.
list_flow_run_steps
ChatGPTList a flow run's steps in the order the flow started them, with type, status, and timestamps. Use get_flow_run_step for a step's result and error.
list_flow_runs
ChatGPTList flow runs with status and timestamps. A page is not the entire history. Use get_flow_run for errors and attempts, get_flow_run_results for results, and list_flow_run_steps for steps.
list_key_value
ChatGPTList all Key Value instances in your Render account
list_log_label_values
ChatGPTList all values for a given log label in the logs matching the provided filters. This can be used to discover what values are available for filtering logs using the list_logs tool. You can query for logs across multiple resources, but all resources must be in the same region and belong to the same owner.
list_logs
ChatGPTList logs matching the provided filters. Logs are paginated by start and end timestamps. There are more logs to fetch if hasMore is true in the response. Provide the nextStartTime and nextEndTime timestamps as the startTime and endTime query parameters to fetch the next page of logs. You can query for logs across multiple resources, but all resources must be in the same region and belong to the same owner.
list_postgres_instances
ChatGPTList all Postgres databases in your Render account
list_services
ChatGPTList all services in your Render account
list_workflow_runs
ChatGPTList task runs with status, attempts and parent/root relationships. A page is not the entire history. The API does not support status/time filters here. Use get_workflow_run for errors and get_workflow_run_results for results.
list_workflow_tasks
ChatGPTDiscover registered tasks, their IDs and versions in the selected workspace. Use nextCursor for another page.
list_workflow_versions
ChatGPTList Workflow versions and their build/registration status. Use nextCursor for another page.
list_workflows
ChatGPTDiscover Workflows in the selected workspace. Returns one page and nextCursor; follow until null or an empty page.
list_workspaces
ChatGPTList the workspaces that you have access to
plan_blueprint
ChatGPTThis tool is in public alpha (early access). Access to this tool and its contract are subject to change. Preview infrastructure changes for an existing Blueprint using its configured Git branch and Blueprint file path. Push any local Blueprint file changes before calling this tool so that the plan includes them. Planning does not apply infrastructure changes. Review the plan with the user before calling approve_blueprint, even when auto-sync is enabled. If another sync is pending or running, wait for it to finish before requesting a new plan. The tool waits for planning to finish and returns planningOutcome, sync, and notices. Use planningOutcome to determine whether planning succeeded and what to do next. Read planningOutcome to determine the next step. If planningOutcome is "failed", inspect the errors in notices. Address the reported issues and push any Blueprint file changes, then call plan_blueprint with the Blueprint ID again. Do not approve a failed plan, even if sync is present. If planningOutcome is "no_changes", this planning attempt found no infrastructure changes. Do not call approve_blueprint for this result. If planningOutcome is "planned", sync contains the proposed infrastructure changes. Summarize them for the user or share sync.dashboardUrl for review. To apply the changes, call approve_blueprint with the Blueprint ID and follow its guidance for supplying any required environment variable values. Call approve_blueprint only after the user authorizes applying the reviewed plan. Providing or allowing generation of manual environment values, or accepting costs, does not by itself authorize deployment.
query_render_postgres
ChatGPTRun a read-only SQL query against a Render-hosted Postgres database. This tool creates a new connection for each query and closes it after the query completes.
run_cron_job
ChatGPTStart a run of a cron job now, outside its schedule. The run uses the cron job's currently deployed build, command, and environment variables. It does not build or deploy new code: if the cron job needs a code or config change first, use trigger_deploy and wait for the deploy to go live. Do not use this to make a scheduled run happen; the schedule already does that. A cron job runs at most one run at a time, and starting a new run cancels the one in progress. This tool checks for an in-progress run and refuses if it finds one, unless cancelActiveRun is true. Returns the new run (usually with status "pending") and, if one was canceled, the canceled run. Before returning, the tool waits up to about 20 seconds for the run to be recorded as started, so that a later run_cron_job call can see it. If the result has a warning, the run was not recorded in time: do not call run_cron_job for this cron job again until the warning says it is safe. The run continues after this tool returns. To see its output, call list_logs with the cron job's ID in resource. To see how it ended, call list_events with eventTypes cron_job_run_ended.
select_workspace
ChatGPTDeprecated: this tool is scheduled for removal; pass the confirmed workspaceId directly on each tool call instead. Select a workspace for clients that rely on MCP session state. This tool should only be used after explicitly asking the user to select one, it should not be invoked as part of an automated process. Having the wrong workspace selected can lead to destructive actions being performed on unintended resources.
trigger_deploy
ChatGPTTrigger a new deploy for a service. Services with autoDeploy enabled deploy automatically when their branch or image is updated, so do NOT use this tool after pushing code to such a service — the push already triggers a deploy. Use it only when a deploy won't happen automatically: services with autoDeploy disabled, redeploying without a code change, or redeploying with a cleared build cache.
update_blueprint
ChatGPTThis tool is in public alpha (early access). Access to this tool and its contract are subject to change. Update a Blueprint's name, Git branch, Blueprint file path, or auto-sync setting. Provide the Blueprint ID and at least one setting. Omitted settings retain their current values. Empty or whitespace-only names, branches, and paths are rejected. If all supplied values match the Blueprint's current settings, the tool returns the Blueprint without updating it or creating a plan. Changing the branch or path also creates a plan. Changing only the name or auto-sync setting does not create a plan. Planning uses the Blueprint file in the remote Git repository. When changing the branch or path, ensure any local Blueprint file changes intended for the plan have been pushed. The tool waits for planning to finish before returning. Changes to the Blueprint's settings take effect immediately. Review any returned plan with the user before calling approve_blueprint, even when auto-sync is enabled. To request a plan without updating the Blueprint, use plan_blueprint. If an update request fails, changes may still have been applied to the Blueprint. Consider checking its current settings before retrying. The response includes blueprint, planningOutcome, sync, notices, and error. If planningOutcome and error are both null, planning was skipped. Report the Blueprint update and the planning outcome separately to the user. If error is non-null, explain that the Blueprint was updated but no planning result is available. When planningOutcome is non-null, use it to determine the next step. Read planningOutcome to determine the next step. If planningOutcome is "failed", inspect the errors in notices. Address the reported issues and push any Blueprint file changes, then call plan_blueprint with the Blueprint ID again. Do not approve a failed plan, even if sync is present. If planningOutcome is "no_changes", this planning attempt found no infrastructure changes. Do not call approve_blueprint for this result. If planningOutcome is "planned", sync contains the proposed infrastructure changes. Summarize them for the user or share sync.dashboardUrl for review. To apply the changes, call approve_blueprint with the Blueprint ID and follow its guidance for supplying any required environment variable values. Call approve_blueprint only after the user authorizes applying the reviewed plan. Providing or allowing generation of manual environment values, or accepting costs, does not by itself authorize deployment.
update_environment_variables
ChatGPTUpdate environment variables for a service. By default, environment variables passed in will be merged with the service's existing environment variables. This makes it safe to update environment variableswithout pulling the existing ones into the MCP host's context. To replace all existing environment variables, set the 'replace' parameter to 'true'.
create_cron_job
Claudecreate_key_value
Claudecreate_postgres
Claudecreate_static_site
Claudecreate_web_service
Claudeget_deploy
Claudeget_key_value
Claudeget_metrics
Claudeget_postgres
Claudeget_selected_workspace
Claudeget_service
Claudelist_deploys
Claudelist_key_value
Claudelist_log_label_values
Claudelist_logs
Claudelist_postgres_instances
Claudelist_services
Claudelist_workspaces
Claudequery_render_postgres
Claudeselect_workspace
Claudetrigger_deploy
Claudeupdate_cron_job
Claudeupdate_environment_variables
Claudeupdate_static_site
Claudeupdate_web_service
Claude