🇺🇸English

Manage Serverless Project

Perform day-2 operations on Elastic Cloud Serverless projects using the Serverless REST API.

Prerequisites and permissions

• Ensure EC_API_KEY is configured. If not, run cloud-setup skill first.
• Updating project settings requires Admin or Editor role on the target project.
• This skill does not perform a separate role pre-check. Attempt the requested operation and let the API enforce authorization. If the API returns an authorization error (for example, 403 Forbidden), stop and ask the user to verify the provided API key permissions.

Manual setup fallback (when cloud-setup is unavailable)

If this skill is installed standalone and cloud-setup is not available, instruct the user to configure Cloud environment variables manually before running commands. Never ask the user to paste API keys in chat.

Note: If EC_API_KEY is missing, or the user does not have a Cloud API key yet, direct the user to generate one at Elastic Cloud API keys, then configure it locally using the steps below.

Preferred method (agent-friendly): create a .env file in the project root:

EC_API_KEY=your-api-key
EC_BASE_URL=https://api.elastic-cloud.com

All cloud/* scripts auto-load .env from the working directory.

Alternative: export directly in the terminal:

export EC_API_KEY="<your-cloud-api-key>"
export EC_BASE_URL="https://api.elastic-cloud.com"

Terminal exports may not be visible to sandboxed agents running in separate shell sessions, so prefer .env when using an agent.

Critical principles

• Never display secrets in chat. Do not echo, log, or repeat API keys, passwords, or credentials in conversation messages or agent thinking. Direct the user to the .elastic-credentials file instead. The admin password must never appear in chat history, thinking traces, or agent output — even when using it to create an API key, pass it directly via shell variable substitution without echoing.
• Confirm before destructive actions. Always ask the user to confirm before deleting a project or resetting credentials.
• Credentials are saved to file. After a credential reset, the script writes the new password to .elastic-credentials automatically. The password is redacted from stdout. Never read or display the contents of .elastic-credentials in chat.
• Admin credentials are for API key creation only. The admin password saved by create-project and reset-credentials exists solely to bootstrap a scoped API key — never use it for direct Elasticsearch operations. load-credentials excludes admin credentials by default; pass only for key creation.

Workflow: Connect to an existing project

Use this workflow when the user asks to query or manage a project the agent did not create in the current session. It resolves the project, saves its endpoints, and ensures working Elasticsearch credentials before proceeding.

This workflow only applies to Elastic Cloud Serverless projects. If the user's Elasticsearch instance is self-managed or Elastic Cloud Hosted, this skill does not apply — skip it and proceed with the relevant skill directly. If unsure, ask the user: "Is your Elasticsearch instance an Elastic Cloud Serverless project?"

Connect to Existing Project:
- [ ] Step 1: Resolve the project
- [ ] Step 2: Get project details and load credentials
- [ ] Step 3: Acquire Elasticsearch credentials

Step 1: Resolve the project

Ask the user for the project name if not already provided. Infer the project type from the user's request:

If the type is ambiguous, list all three types to find the project.

python3 skills/cloud/manage-project/scripts/manage-project.py list \
  --type elasticsearch

Match the user's reference (name, partial name, or alias) against the list results. If multiple projects match or none match, present the candidates and ask the user to pick.

Step 2: Get project details and load credentials

Once a single project is identified, check whether .elastic-credentials already has entries for this project (from a previous session). If so, load them with load-credentials:

eval $(python3 skills/cloud/manage-project/scripts/manage-project.py load-credentials \
  --name "<project-name>")

This sets all saved environment variables for the project — endpoints and any previously created Elasticsearch API keys — in a single command. Admin credentials (ELASTICSEARCH_USERNAME/ELASTICSEARCH_PASSWORD) are intentionally excluded. Later sections for the same project automatically overwrite earlier values, so the most recent credentials always win.

If load-credentials reports no matching entries, fetch the project details from the API and export endpoints manually:

python3 skills/cloud/manage-project/scripts/manage-project.py get \
  --type elasticsearch \
  --id <project-id>

Then export the endpoint URLs from the response. The available endpoints depend on the project type.

All project types:

export ELASTICSEARCH_URL="<elasticsearch_endpoint>"
export KIBANA_URL="<kibana_endpoint>"

Observability projects (additional):

export APM_URL="<apm_endpoint>"
export INGEST_URL="<ingest_endpoint>"

Security projects (additional):

export INGEST_URL="<ingest_endpoint>"

Step 3: Acquire Elasticsearch credentials

If load-credentials set ELASTICSEARCH_API_KEY, verify the credentials work:

curl -H "Authorization: ApiKey ${ELASTICSEARCH_API_KEY}" \
  "${ELASTICSEARCH_URL}/_security/_authenticate"

Confirm the response contains a valid username and "authentication_type": "api_key" before proceeding. If verification succeeds, skip the rest of this step.

If no credentials were loaded, or verification fails, ask the user: "Do you have an existing Elasticsearch API key for this project?"

If yes — have the user add it to .elastic-credentials (see "Credential file format"). Do not accept keys in chat. Reload and verify:

eval $(python3 skills/cloud/manage-project/scripts/manage-project.py load-credentials \
  --name "<project-name>")
curl -H "Authorization: ApiKey ${ELASTICSEARCH_API_KEY}" \
  "${ELASTICSEARCH_URL}/_security/_authenticate"

If no — follow this recovery path:

1. Confirm with the user, then reset the admin bootstrap credentials:

   python3 skills/cloud/manage-project/scripts/manage-project.py reset-credentials \
     --type elasticsearch \
     --id <project-id>
   

The new password is saved to .elastic-credentials with the project name in the header. Direct the user to that file — do not display its contents.

1. Load credentials with--include-admin so the admin password is available for API key creation:

   eval $(python3 skills/cloud/manage-project/scripts/manage-project.py load-credentials \
     --name "<project-name>" --include-admin)
   

Use the admin credentials to create a scoped Elasticsearch API key via elasticsearch-authn if available. If that skill is not installed, ask the user to install it or create the key manually in Kibana > Stack Management > API keys. Scope the key to only the privileges the user needs.

1. After creating the API key, save it to .elastic-credentials using the project-specific header format (see "Credential file format" below). Then reload without--include-admin to drop admin credentials from the environment and verify:

   eval $(python3 skills/cloud/manage-project/scripts/manage-project.py load-credentials \
     --name "<project-name>")
   curl -H "Authorization: ApiKey ${ELASTICSEARCH_API_KEY}" \
     "${ELASTICSEARCH_URL}/_security/_authenticate"
   

Confirm the response shows a valid username and "authentication_type": "api_key" before proceeding.

Credential file format

See references/credential-file-format.md for the full format specification.

Workflow: Load project credentials

eval $(python3 skills/cloud/manage-project/scripts/manage-project.py load-credentials \
  --name "<project-name>")

Or by project ID:

eval $(python3 skills/cloud/manage-project/scripts/manage-project.py load-credentials \
  --id <project-id>)

Parses .elastic-credentials, merges all sections for the matching project, and prints export statements. Admin credentials (ELASTICSEARCH_USERNAME/ELASTICSEARCH_PASSWORD) are excluded by default — only endpoints and API keys are exported. Add --include-admin when you need admin credentials to create an API key.

Workflow: List projects

python3 skills/cloud/manage-project/scripts/manage-project.py list \
  --type elasticsearch

Use --type observability or --type security to list other project types.

Workflow: Get project details

python3 skills/cloud/manage-project/scripts/manage-project.py get \
  --type elasticsearch \
  --id <project-id>

Workflow: Update a project

python3 skills/cloud/manage-project/scripts/manage-project.py update \
  --type elasticsearch \
  --id <project-id> \
  --name "new-project-name"

Only the fields provided are updated (PATCH semantics). Supported fields: --name, --alias, --tag, --search-power, --boost-window, --max-retention-days, --default-retention-days.

Alias

The alias is an RFC-1035 domain label (lowercase alphanumeric and hyphens, max 50 chars) that becomes part of the project's endpoint URLs. Changing the alias changes all endpoint URLs , which breaks existing clients pointing to the old URLs. Warn the user about this before applying.

python3 skills/cloud/manage-project/scripts/manage-project.py update \
  --type elasticsearch \
  --id <project-id> \
  --alias "prod-search"

Tags

Tags are key-value metadata pairs for team tracking, cost attribution, and organization. Pass --tag KEY:VALUE for each tag. Multiple tags can be set in a single update.

python3 skills/cloud/manage-project/scripts/manage-project.py update \
  --type elasticsearch \
  --id <project-id> \
  --tag env:prod \
  --tag team:search

Tags are sent as metadata.tags in the API request. Setting tags replaces all existing tags on the project — include any existing tags the user wants to keep.

Elasticsearch search_lake settings

For Elasticsearch projects, two fields control query performance and data caching in the Search AI Lake. Ingested data is stored in cost-efficient general storage. A cache layer on top provides faster search speed for recent and frequently queried data — this cached data is considered search-ready.

Search Power

Search Power controls the speed of searches by provisioning more or fewer query resources. Common presets (matching the Cloud UI):

When the user asks for a preset by name, map it to the corresponding value. Custom values within 28–3000 are also valid.

Warn the user about cost implications before updatingsearch_power. Higher values increase VCU consumption and may result in higher bills. Confirm the new value with the user before applying.

Search Boost Window

Non-time-series data is always search-ready. The boost window determines how much time-series data (documents with a @timestamp field) is also kept in the fast cache layer. Increasing the window means a larger portion of time-series data becomes search-ready, which improves query speed for recent data but increases the search-ready data volume.

Security data retention settings

For security projects, two fields control how long data is retained in the Search AI Lake. Retention is configured per data stream, but these project-level settings enforce global boundaries.

• Maximum retention — enforces an upper bound across all data streams. When lowered, it replaces the retention for any stream that currently has a longer period. Data older than the new maximum is permanently deleted.
• Default retention — automatically applied to data streams that do not have a custom retention period set. Does not affect streams with an existing custom retention.

Warn the user before reducingmax-retention-days. Lowering the maximum permanently deletes data older than the new limit. Confirm the new value with the user before applying.

Workflow: Reset project credentials

Always confirm with the user before resetting.

python3 skills/cloud/manage-project/scripts/manage-project.py reset-credentials \
  --type elasticsearch \
  --id <project-id>

The new password is saved to .elastic-credentials automatically. Tell the user to open that file — do not display its contents in chat.

Workflow: Delete a project

Always confirm with the user before deleting.

python3 skills/cloud/manage-project/scripts/manage-project.py delete \
  --type elasticsearch \
  --id <project-id>

Workflow: Resume a suspended project

Projects can be automatically suspended after their trial period expires. Resume with:

python3 skills/cloud/manage-project/scripts/manage-project.py resume \
  --type elasticsearch \
  --id <project-id>

After resuming, poll the project status until the phase changes from initializing to initialized.

Examples

List all security projects

python3 skills/cloud/manage-project/scripts/manage-project.py list --type security

Update search power on an Elasticsearch project

python3 skills/cloud/manage-project/scripts/manage-project.py update \
  --type elasticsearch \
  --id abc123def456abc123def456abc12345 \
  --search-power 500

Set data retention on a security project

python3 skills/cloud/manage-project/scripts/manage-project.py update \
  --type security \
  --id abc123def456abc123def456abc12345 \
  --max-retention-days 396 \
  --default-retention-days 396

Change project alias

python3 skills/cloud/manage-project/scripts/manage-project.py update \
  --type elasticsearch \
  --id abc123def456abc123def456abc12345 \
  --alias "prod-search"

Tag a project for cost tracking

python3 skills/cloud/manage-project/scripts/manage-project.py update \
  --type observability \
  --id abc123def456abc123def456abc12345 \
  --tag env:prod \
  --tag team:platform

Rename an observability project

python3 skills/cloud/manage-project/scripts/manage-project.py update \
  --type observability \
  --id abc123def456abc123def456abc12345 \
  --name "production-logs"

Connect to an existing project (credentials on file)

User: I want to run a query against my search project "prod-search"
Agent: Let me find that project.
       [runs: list --type elasticsearch]
       I found "prod-search" (ID: abc123...). Loading saved credentials...
       [runs: eval $(load-credentials --name prod-search)]
       Credentials loaded. Verifying...
       [runs: curl -H "Authorization: ApiKey ..." "${ELASTICSEARCH_URL}/_security/_authenticate"]
       Verified — authenticated as user "my-service" via API key. You're all set.

Connect to a project (no saved credentials)

User: let's ingest some logs into my o11y project "siem-prod"
Agent: Let me find that project.
       [runs: list --type observability]
       Found "siem-prod" (ID: def456...). No saved credentials found for this project.
       [runs: get --type observability --id def456...]
       Endpoints set. Since there are no Elasticsearch credentials on file, I can reset the
       admin bootstrap password to get initial access. Shall I proceed?
User: yes
Agent: [runs: reset-credentials --type observability --id def456...]
       Credentials saved to .elastic-credentials — open that file to retrieve the password.
       [runs: eval $(load-credentials --name siem-prod --include-admin)]
       Admin credentials loaded for API key creation. Creating a scoped Elasticsearch API key
       now — what access does it need?
User: read-only on logs-*
Agent: [creates scoped API key via elasticsearch-authn using admin credentials]
       [appends API key to .elastic-credentials with project header]
       [runs: eval $(load-credentials --name siem-prod)]
       [verifies against ELASTICSEARCH_URL]
       API key created and verified. Admin credentials removed from environment.

Delete a project after confirmation

User: delete my elasticsearch project abc123...
Agent: Are you sure you want to delete project abc123...? This cannot be undone.
User: yes



python3 skills/cloud/manage-project/scripts/manage-project.py delete \
  --type elasticsearch \
  --id abc123def456abc123def456abc12345

Guidelines

• Run the cloud-setup skill first if EC_API_KEY is not set.
• Use the cloud-create-project skill to create new projects — this skill handles existing projects only.
• When the user refers to a project the agent did not create, follow the "Connect to an existing project" workflow.
• Deletion is permanent. Always confirm with the user before proceeding.
• After resetting credentials, remind the user to update any stored passwords or environment variables.
• Warn about cost implications before increasing search_power. Confirm the new value with the user first.
• Warn about data loss before reducing max-retention-days. Data older than the new maximum is permanently deleted.
• Warn users that changing a project alias changes all endpoint URLs, which breaks existing clients.
• Setting tags replaces all existing tags. Retrieve current tags with get first and include any the user wants to keep.

Script reference

Environment variables

Additional resources

• For full API details, request/response schemas, and project-type options, see the Serverless Projects API
• For official documentation on Search AI Lake settings, data retention, and project features, see Project settings

Weekly Installs

140

Repository

elastic/agent-skills

GitHub Stars

136

First Seen

12 days ago

Security Audits

Gen Agent Trust HubPassSocketPassSnykPass

Installed on

cursor126

github-copilot118

opencode117

gemini-cli117

codex117

amp117