Connectors · Developer & infrastructure

Render MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Render and the rest of your systems. It gives your agent 225 Render actions (108 reads, 72 writes and 45 that wait for a confirmation) and holds the Render credential itself, so the agent never does. It paces Render's limits and records every call.

Connect Render free See pricing

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp

225actionsin one signed file
108readlook, never change
72writecreate and update
45wait for a yesdestructive, confirmed first

Set up

Connect Render in three steps.

01
Add actionlake to Claude.
Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.
https://connect.actionlake.com/mcp
02
Connect Render.
Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.
- tokenRender API key: create one in the Render Dashboard under Account Settings > API Keys
```
account { op: "connections.requirements", service: "render" }
# free: exactly what to paste, and what is found for you
```

Make the first call. Check before a write.

Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

do    { action: "render.services.list" }# list services · read · 1 upstream callcheck { action: "render.services.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Render at a glance

Sign-in: Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide: token
Limits we pace to: 400 calls a minute, per connection
API covered: Render Public API v1 (OpenAPI 3.0.2, spec 1.0.0, 228 operations)api.render.com/v1
Built from: Render's documentation, read 23 October 2026api-docs.render.com api-docs.render.com
Service file: Version 1.0.0, signed (Ed25519)
Cached reads: 83 of 108 reads, for up to 5 minutes; a write clears what it affects
Shared entities: 5, so ask can line Render up with your other systems
Data: Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Render.

225 actions in 62 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

108readlook, never change
72writecreate and update
45destructivewait for a confirmation

Metrics
17
17 read · 0 write · 0 destructive
Get active connection count · Get bandwidth usage · Get bandwidth usage breakdown by traffic source · Get CPU usage
Services
11
2 read · 8 write · 1 destructive
List services · Create service · Retrieve service · Update service
Postgres
10
3 read · 5 write · 2 destructive
List Postgres instances · Create Postgres instance · Retrieve Postgres instance · Update Postgres instance
Key value
8
3 read · 4 write · 1 destructive
Create Key Value instance · List Key Value instances · Retrieve Key Value instance · Delete Key Value instance
Redis
8
3 read · 4 write · 1 destructive
Create Redis instance · List Redis instances · Retrieve Redis instance · Retrieve Redis connection info
Build source env vars
5
2 read · 1 write · 2 destructive
List environment variables · Retrieve environment variable · Delete environment variable · Update environment variables
Build source secret files
5
2 read · 1 write · 2 destructive
List secret files · Retrieve secret file · Delete secret file · Update secret files
Build sources
5
2 read · 2 write · 1 destructive
Create a build source · List build sources · Retrieve a build source · Update a build source

54 more areas · 156 actions

Dedicated ips 5
Disks 5
Env groups 5
Environments 5
Projects 5
Registry credentials 5
Service custom domains 5
Service env vars 5
Service routes 5
Service secret files 5
Webhooks 5
Workflows 5
Blueprints 4
Maintenance 4
Postgres insights 4
Resource log streams 4
Service deploys 4
Service headers 4
Service jobs 4
Task runs 4
Build source builds 3
Env group env vars 3
Env group secret files 3
Metrics filters 3
Owner log stream 3
Owner members 3
Owner metrics stream 3
Postgres users 3
Workflow versions 3
Build source env groups 2
Cron job runs 2
Disk snapshots 2
Env group services 2
Environment resources 2
Owner notification settings 2
Owners 2
Postgres exports 2
Postgres recovery 2
Service autoscaling 2
Service notification overrides 2
Tasks 2
Blueprint syncs 1
Events 1
Log label values 1
Logs 1
Notification overrides 1
Organization audit logs 1
Owner audit logs 1
Service cache 1
Service events 1
Service instances 1
Service outbound ips 1
Users 1
Webhook events 1

Top actions

The Render API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 69 of Render's 70 action names are shared with at least one other connector, so an agent learns them once.

Action	What it does	Effect	Same name in
`render.services.list`List services	List services.	read	`infra.container_service.list`11 connectors
`render.users.get_current`Get the authenticated user	Get the authenticated user.	read	`identity.current_user.get`307 connectors
`render.owner_members.list`List workspace members	List workspace members.	read	`identity.group_member.list`103 connectors
`render.service_deploys.list`List deploys	List deploys.	read	`devops.deployment.list`22 connectors
`render.services.create`Create service	Create service.	write	`infra.container_service.create`8 connectors
`render.services.delete`Delete service	Delete service.	destructive	`infra.container_service.delete`11 connectors
`render.service_instances.list`List instances	List instances.	read	`infra.instance.list`18 connectors
`render.workflows.list`List workflows	List workflows.	read	`automation.workflow.list`51 connectors
`render.service_jobs.list`List jobs	List jobs.	read	`infra.job.list`12 connectors
`render.disk_snapshots.list`List snapshots	List snapshots.	read	`infra.snapshot.list`12 connectors
`render.service_deploys.create`Trigger deploy	Trigger deploy.	write	`devops.deployment.create`17 connectors
`render.service_jobs.create`Create job	Create job.	write	`infra.job.create`10 connectors

Try it

Prompts to paste into Claude.

Each one names the Render actions it will call, so you know what it reads and what it changes before you send it.

Readread
List services in Render and tell me what stands out.
callsrender.services.list
Writewrite
Create service in Render. Show me exactly what you will send before you save it.
callsrender.services.create

Governance for Render

Destructive actions wait for a yes.

45 Render actions are destructive. The first 10:

Delete servicerender.services.delete
Delete diskrender.disks.delete
Delete workflowrender.workflows.delete
Delete a webhookrender.webhooks.delete
Delete Postgres instancerender.postgres.delete
Delete PostgreSQL Userrender.postgres_users.delete
Cancel deployrender.service_deploys.cancel
Cancel task runrender.task_runs.cancel
Delete Key Value instancerender.key_value.delete
Delete environment variablerender.service_env_vars.delete

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

dorender.services.deleteconfirm_policy: human

Delete service?

intent: the user asked me to delete service

run suspended · waiting for a named person · key render-agent cannot confirm itself

In the console, or from an emailed signed link.

a key for this connector

account {  op: "keys.create", name: "render-agent",  allowed_actions: ["render.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "render.services.delete", approver: "[email protected]" },    { match: "render.disks.delete", approver: "[email protected]" },    { match: "render.workflows.delete", approver: "[email protected]" }  ]}

Illustrative. Scoped to Render only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Render costs on actionlake.

Every Render action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Render refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

1upstream call per actionall 225 Render actions
225actions pageeach page of a long list is one call
83reads can be cacheda cache hit costs nothing
100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every Render action.

225 actions by area: the id your agent calls, what it does, and its effect.

Metrics17

render.metrics.get_active_connectionsGet active connection countread
render.metrics.get_bandwidthGet bandwidth usageread
render.metrics.get_bandwidth_sourcesGet bandwidth usage breakdown by traffic sourceread
render.metrics.get_cpuGet CPU usageread
render.metrics.get_cpu_limitGet CPU limitread
render.metrics.get_cpu_targetGet CPU targetread
render.metrics.get_disk_capacityGet disk capacityread
render.metrics.get_disk_usageGet disk usageread
render.metrics.get_http_latencyGet HTTP latencyread
render.metrics.get_http_requestsGet HTTP request countread
render.metrics.get_instance_countGet instance countread
render.metrics.get_memoryGet memory usageread
render.metrics.get_memory_limitGet memory limitread
render.metrics.get_memory_targetGet memory targetread
render.metrics.get_replication_lagGet replica lagread
render.metrics.get_task_runs_completedGet task runs completed countread
render.metrics.get_task_runs_queuedGet task runs queued countread

Services11

render.services.createCreate servicewrite
render.services.create_previewCreate service preview (image-backed)write
render.services.deleteDelete servicedestructive
render.services.getRetrieve serviceread
render.services.listList servicesread
render.services.restartRestart servicewrite
render.services.resumeResume servicewrite
render.services.rollbackRoll back deploywrite
render.services.scaleScale instance countwrite
render.services.suspendSuspend servicewrite
render.services.updateUpdate servicewrite

Postgres10

render.postgres.createCreate Postgres instancewrite
render.postgres.deleteDelete Postgres instancedestructive
render.postgres.failoverFailover Postgres instancedestructive
render.postgres.getRetrieve Postgres instanceread
render.postgres.get_connection_infoRetrieve Postgres connection inforead
render.postgres.listList Postgres instancesread
render.postgres.restartRestart Postgres instancewrite
render.postgres.resumeResume Postgres instancewrite
render.postgres.suspendSuspend Postgres instancewrite
render.postgres.updateUpdate Postgres instancewrite

Key value8

render.key_value.createCreate Key Value instancewrite
render.key_value.deleteDelete Key Value instancedestructive
render.key_value.getRetrieve Key Value instanceread
render.key_value.get_connection_infoRetrieve Key Value connection inforead
render.key_value.listList Key Value instancesread
render.key_value.resumeResume Key Value instancewrite
render.key_value.suspendSuspend Key Value instancewrite
render.key_value.updateUpdate Key Value instancewrite

Redis8

render.redis.createCreate Redis instancewrite
render.redis.deleteDelete Redis instancedestructive
render.redis.getRetrieve Redis instanceread
render.redis.get_connection_infoRetrieve Redis connection inforead
render.redis.listList Redis instancesread
render.redis.resumeResume Redis instancewrite
render.redis.suspendSuspend Redis instancewrite
render.redis.updateUpdate Redis instancewrite

Build source env vars5

render.build_source_env_vars.deleteDelete environment variabledestructive
render.build_source_env_vars.getRetrieve environment variableread
render.build_source_env_vars.listList environment variablesread
render.build_source_env_vars.replace_allUpdate environment variablesdestructive
render.build_source_env_vars.upsertAdd or update environment variablewrite

Build source secret files5

render.build_source_secret_files.deleteDelete secret filedestructive
render.build_source_secret_files.getRetrieve secret fileread
render.build_source_secret_files.listList secret filesread
render.build_source_secret_files.replace_allUpdate secret filesdestructive
render.build_source_secret_files.upsertAdd or update secret filewrite

Build sources5

render.build_sources.createCreate a build sourcewrite
render.build_sources.deleteDelete a build sourcedestructive
render.build_sources.getRetrieve a build sourceread
render.build_sources.listList build sourcesread
render.build_sources.updateUpdate a build sourcewrite

Dedicated ips5

render.dedicated_ips.createCreate dedicated IP setwrite
render.dedicated_ips.deleteDelete dedicated IP setdestructive
render.dedicated_ips.getRetrieve dedicated IP setread
render.dedicated_ips.listList dedicated IPsread
render.dedicated_ips.updateUpdate dedicated IP setwrite

Disks5

render.disks.createAdd diskwrite
render.disks.deleteDelete diskdestructive
render.disks.getRetrieve diskread
render.disks.listList disksread
render.disks.updateUpdate diskwrite

Env groups5

render.env_groups.createCreate environment groupwrite
render.env_groups.deleteDelete environment groupdestructive
render.env_groups.getRetrieve environment groupread
render.env_groups.listList environment groupsread
render.env_groups.updateUpdate environment groupwrite

Environments5

render.environments.createCreate environmentwrite
render.environments.deleteDelete environmentdestructive
render.environments.getRetrieve environmentread
render.environments.listList environmentsread
render.environments.updateUpdate environmentwrite

Projects5

render.projects.createCreate projectwrite
render.projects.deleteDelete projectdestructive
render.projects.getRetrieve Projectread
render.projects.listList projectsread
render.projects.updateUpdate projectwrite

Registry credentials5

render.registry_credentials.createCreate registry credentialwrite
render.registry_credentials.deleteDelete registry credentialdestructive
render.registry_credentials.getRetrieve registry credentialread
render.registry_credentials.listList registry credentialsread
render.registry_credentials.updateUpdate registry credentialwrite

Service custom domains5

render.service_custom_domains.createAdd custom domainwrite
render.service_custom_domains.deleteDelete custom domaindestructive
render.service_custom_domains.getRetrieve custom domainread
render.service_custom_domains.listList custom domainsread
render.service_custom_domains.verifyVerify DNS configurationwrite

Service env vars5

render.service_env_vars.deleteDelete environment variabledestructive
render.service_env_vars.getRetrieve environment variableread
render.service_env_vars.listList environment variablesread
render.service_env_vars.replace_allUpdate environment variablesdestructive
render.service_env_vars.upsertAdd or update environment variablewrite

Service routes5

render.service_routes.createAdd redirect/rewrite ruleswrite
render.service_routes.deleteDelete redirect/rewrite ruledestructive
render.service_routes.listList redirect/rewrite rulesread
render.service_routes.replace_allUpdate redirect/rewrite rulesdestructive
render.service_routes.update_priorityUpdate redirect/rewrite rule prioritywrite

Service secret files5

render.service_secret_files.deleteDelete secret filedestructive
render.service_secret_files.getRetrieve secret fileread
render.service_secret_files.listList secret filesread
render.service_secret_files.replace_allUpdate secret filesdestructive
render.service_secret_files.upsertAdd or update secret filewrite

Webhooks5

render.webhooks.createCreate a webhookwrite
render.webhooks.deleteDelete a webhookdestructive
render.webhooks.getRetrieve a webhookread
render.webhooks.listList webhooksread
render.webhooks.updateUpdate a webhookwrite

Workflows5

render.workflows.createCreate a workflowwrite
render.workflows.deleteDelete workflowdestructive
render.workflows.getRetrieve workflowread
render.workflows.listList workflowsread
render.workflows.updateUpdate workflowwrite

Blueprints4

render.blueprints.disconnectDisconnect Blueprintdestructive
render.blueprints.getRetrieve Blueprintread
render.blueprints.listList Blueprintsread
render.blueprints.updateUpdate Blueprintwrite

Maintenance4

render.maintenance.getRetrieve maintenance runread
render.maintenance.listList maintenance runsread
render.maintenance.triggerTrigger maintenance runwrite
render.maintenance.updateUpdate maintenance runwrite

Postgres insights4

render.postgres_insights.list_processesList live queriesread
render.postgres_insights.list_sizesList database, table, and index sizesread
render.postgres_insights.list_table_scansList table scansread
render.postgres_insights.list_top_queriesList top queriesread

Resource log streams4

render.resource_log_streams.deleteDelete log stream overridedestructive
render.resource_log_streams.getRetrieve log stream overrideread
render.resource_log_streams.listList log stream overridesread
render.resource_log_streams.updateUpdate log stream overridewrite

Service deploys4

render.service_deploys.cancelCancel deploydestructive
render.service_deploys.createTrigger deploywrite
render.service_deploys.getRetrieve deployread
render.service_deploys.listList deploysread

Service headers4

render.service_headers.createAdd header rulewrite
render.service_headers.deleteDelete header ruledestructive
render.service_headers.listList header rulesread
render.service_headers.replace_allReplace header rulesdestructive

Service jobs4

render.service_jobs.cancelCancel running jobdestructive
render.service_jobs.createCreate jobwrite
render.service_jobs.getRetrieve jobread
render.service_jobs.listList jobsread

Task runs4

render.task_runs.cancelCancel task rundestructive
render.task_runs.createRun taskwrite
render.task_runs.getRetrieve task runread
render.task_runs.listList task runsread

Build source builds3

render.build_source_builds.getRetrieve a buildread
render.build_source_builds.listList builds in a build sourceread
render.build_source_builds.triggerTrigger a buildwrite

Env group env vars3

render.env_group_env_vars.deleteRemove environment variabledestructive
render.env_group_env_vars.getRetrieve environment variableread
render.env_group_env_vars.upsertAdd or update environment variablewrite

Env group secret files3

render.env_group_secret_files.deleteRemove secret filedestructive
render.env_group_secret_files.getRetrieve secret fileread
render.env_group_secret_files.upsertAdd or update secret filewrite

Metrics filters3

render.metrics_filters.list_application_valuesList queryable instance valuesread
render.metrics_filters.list_http_valuesList queryable status codes and host valuesread
render.metrics_filters.list_path_valuesList queryable pathsread

Owner log stream3

render.owner_log_stream.deleteDelete log streamdestructive
render.owner_log_stream.getRetrieve log streamread
render.owner_log_stream.updateUpdate log streamwrite

Owner members3

render.owner_members.listList workspace membersread
render.owner_members.removeRemove workspace memberdestructive
render.owner_members.updateUpdate workspace member rolewrite

Owner metrics stream3

render.owner_metrics_stream.deleteDelete metrics streamdestructive
render.owner_metrics_stream.getRetrieve metrics streamread
render.owner_metrics_stream.upsertCreate or update metrics streamwrite

Postgres users3

render.postgres_users.createCreate PostgreSQL Userwrite
render.postgres_users.deleteDelete PostgreSQL Userdestructive
render.postgres_users.listList PostgreSQL Usersread

Workflow versions3

render.workflow_versions.createDeploy a workflow versionwrite
render.workflow_versions.getRetrieve workflow versionread
render.workflow_versions.listList workflow versionsread

Build source env groups2

render.build_source_env_groups.linkLink environment groupwrite
render.build_source_env_groups.unlinkUnlink environment groupdestructive

Cron job runs2

render.cron_job_runs.cancelCancel running cron jobdestructive
render.cron_job_runs.triggerTrigger cron job runwrite

Disk snapshots2

render.disk_snapshots.listList snapshotsread
render.disk_snapshots.restoreRestore snapshotdestructive

Env group services2

render.env_group_services.linkLink servicewrite
render.env_group_services.unlinkUnlink servicedestructive

Environment resources2

render.environment_resources.addAdd resources to environmentwrite
render.environment_resources.removeRemove resources from environmentdestructive

Owner notification settings2

render.owner_notification_settings.getRetrieve notification settingsread
render.owner_notification_settings.updateUpdate notification settingswrite

Owners2

render.owners.getRetrieve workspaceread
render.owners.listList workspacesread

Postgres exports2

render.postgres_exports.createCreate Postgres exportwrite
render.postgres_exports.listList Postgres exportsread

Postgres recovery2

render.postgres_recovery.createTrigger point-in-time recoverywrite
render.postgres_recovery.getRetrieve point-in-time recovery statusread

Service autoscaling2

render.service_autoscaling.deleteDelete autoscaling configdestructive
render.service_autoscaling.setUpdate autoscaling configwrite

Service notification overrides2

render.service_notification_overrides.getRetrieve notification overrideread
render.service_notification_overrides.updateUpdate notification overridewrite

Tasks2

render.tasks.getRetrieve taskread
render.tasks.listList tasksread

Blueprint syncs1

render.blueprint_syncs.listList Blueprint syncsread

Events1

render.events.getRetrieve eventread

Log label values1

render.log_label_values.listList log label valuesread

Logs1

render.logs.listList logsread

Notification overrides1

render.notification_overrides.listList notification overridesread

Organization audit logs1

render.organization_audit_logs.listList organization audit logsread

Owner audit logs1

render.owner_audit_logs.listList workspace audit logsread

Service cache1

render.service_cache.purgePurge Web Service Cachedestructive

Service events1

render.service_events.listList eventsread

Service instances1

render.service_instances.listList instancesread

Service outbound ips1

render.service_outbound_ips.getRetrieve service outbound IPsread

Users1

render.users.get_currentGet the authenticated userread

Webhook events1

render.webhook_events.listList webhook eventsread

Questions

The Render MCP server, answered.

Is there a Render MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 225 Render actions across metrics, services, postgres and key value, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Render.

What do I need to connect Render?

Render API key: create one in the Render Dashboard under Account Settings > API Keys. The free call account { op: "connections.requirements", service: "render" } lists exactly what to paste.

Can an AI agent delete or change things in Render?

Only if its key allows it, and only with an explicit confirmation. 45 Render actions are destructive, including delete service, delete disk and delete workflow. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my Render API limit?

actionlake paces every call to the limits in the Render service file: 400 calls a minute per connection. Repeated reads are answered from cache (83 Render actions can be), which never reaches Render.

What does a Render action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (225 Render actions page). Cache hits, searches, dry runs and calls Render refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which Render API does it cover?

The Render Public API v1 (OpenAPI 3.0.2, spec 1.0.0, 228 operations) at api.render.com/v1. It is built from Render's documentation as read on 23 October 2026. 225 actions in 62 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Render data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Render credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

Give your agent Render today.

Connect Render free See pricing

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.

Render MCP server for AI agents.

Connect Render in three steps.

Add actionlake to Claude.

Connect Render.

Make the first call. Check before a write.

What an AI agent can do in Render.

Metrics

Services

Postgres

Key value

Redis

Build source env vars

Build source secret files

Build sources