Swarmpit MCP server
Commit Oct 14, 2026Allows an AI client to manage Docker Swarm instances by interacting with the Swarmpit API to control services, stacks, nodes, and networks.
Also known as swarmpit/mcp
- Stars
- 7
- Tools
- 72
- Downloads, 30 days
- β
- Latest version
- β
- Last commit
- Oct 14, 2026
- License
- β
What is Swarmpit MCP?
Swarmpit allows an AI client to manage Docker Swarm instances by interacting with the Swarmpit API to control services, stacks, nodes, and networks. It exposes 72 tools, such as list_services, get_service, service_logs.
Summary generated from the project's README
About Swarmpit MCP server
Managing Docker Swarm instances through Swarmpit is what this MCP server enables for developers using compatible clients like Claude Code or opencode. It provides full coverage of the Swarmpit API, allowing an AI to interact with services, stacks, nodes, networks, volumes, and secrets. The server runs locally, ensuring that API tokens remain on your machine and never enter the LLM conversation context.
Users can configure the server to manage a single instance or multiple clusters simultaneously using a configuration file or environment variables. For security, it includes redaction modes to prevent sensitive data from being sent to cloud-hosted LLM providers. When managing multiple instances, read-only tools support fan-out queries, allowing you to check service status or image tags across several clusters with a single command. While read-only tools can query multiple servers at once, all mutating tools like scale_service or create_stack are restricted to a single target to prevent accidental mass changes.
What you can do with it
- 1Compare service versions across clustersAsk the AI to check if a specific image tag is running across all your production and staging environments.
- 2Scale service replicasInstruct the AI to increase the number of running containers for a specific service.
- 3Deploy new application stacksProvide a compose YAML file to the AI to create and launch a new set of services.
- 4Audit cluster resourcesRequest a list of all nodes and their current tasks to understand cluster health.
Written from the project's README. Every use case is checked against a quote from it.
Swarmpit MCP tools 72
Detected from the READMElist_servicesget_serviceservice_logscreate_serviceupdate_serviceredeploy_servicerollback_servicestop_servicescale_servicelist_service_tasksdelete_serviceupdate_service_env
Show all 72 toolsShow fewer tools
get_service_envget_service_composeget_service_networkslist_stacksget_stackcreate_stackupdate_stackredeploy_stackrollback_stackdeactivate_stackdelete_stackget_stack_tasksget_stack_volumesget_stack_networksget_stack_composeget_stack_secretsget_stack_configscreate_stack_filedelete_stack_filelist_networksget_networkcreate_networkdelete_networkget_network_serviceslist_nodesget_nodeget_node_tasksedit_nodedelete_nodelist_tasksget_tasklist_volumesget_volumecreate_volumedelete_volumeget_volume_serviceslist_secretsget_secretcreate_secretdelete_secretget_secret_serviceslist_configsget_configcreate_configdelete_configget_config_serviceslist_usersget_usercreate_useredit_userdelete_userpin_service_to_dashboardunpin_service_from_dashboardpin_node_to_dashboardunpin_node_from_dashboardget_nodes_timeseriesget_services_cpu_timeseriesget_services_memory_timeseriesget_task_timeseriesswarmpit_info
Configuration
DB_PASSWORDMY_DB_PASSNODE_ENVSWARMPIT_CONFIG_FILESWARMPIT_DEFAULT_SERVERSWARMPIT_PROD_EU_TOKEN_FILESWARMPIT_PROD_EU_URLSWARMPIT_PROD_US_TOKEN_FILESWARMPIT_PROD_US_URLSWARMPIT_REDACTSWARMPIT_REDACT_PATTERNSSWARMPIT_SERVERSSWARMPIT_TOKENSWARMPIT_TOKEN_FILESWARMPIT_URL
Automated checks
Ran Nov 14, 2026Full report βNot verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work Β· What to fix for more points
- Source repository linked and reachableswarmpit/mcp is public and reachablegithub.com/swarmpit/mcp βPass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-10-14github.com/swarmpit/mcp βPass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model72 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubmcp-swarmpit
MCP server for managing Swarmpit Docker Swarm instances from any MCP-compatible client. 100% Swarmpit API coverage (79 endpoints).
The server runs locally and holds API tokens β they never enter the LLM conversation context.
Works with opencode (recommended), Claude Code, and any other MCP client.
Configuration
opencode
Add to your .opencode.json:
{
"mcpServers": {
"swarmpit-prod": {
"type": "stdio",
"command": "npx",
"args": ["github:swarmpit/mcp"],
"env": {
"SWARMPIT_URL": "https://swarmpit.example.com",
"SWARMPIT_TOKEN": "your-api-token",
"SWARMPIT_REDACT": "sensitive"
}
}
}
}
Claude Code
Add to your .mcp.json (project-level) or ~/.claude.json (global):
{
"mcpServers": {
"swarmpit-prod": {
"command": "npx",
"args": ["github:swarmpit/mcp"],
"env": {
"SWARMPIT_URL": "https://swarmpit.example.com",
"SWARMPIT_TOKEN": "your-api-token",
"SWARMPIT_REDACT": "sensitive"
}
}
}
}
Get your API token from Swarmpit UI: Profile β API Access β Generate token.
Multiple instances
One process can manage several Swarmpit instances. Every tool then takes an optional server argument naming the target β the tool set is registered once instead of once per instance, which matters because the full surface is ~79 tools and the model loads all of them for every MCP server you wire up.
Point SWARMPIT_CONFIG_FILE at a JSON file:
{
"default": "prod-eu",
"servers": {
"prod-eu": { "url": "https://swarmpit.eu.example.com", "tokenFile": "~/.config/swarmpit/prod-eu" },
"prod-us": { "url": "https://swarmpit.us.example.com", "tokenFile": "~/.config/swarmpit/prod-us" }
}
}
{
"mcpServers": {
"swarmpit": {
"command": "npx",
"args": ["github:swarmpit/mcp"],
"env": { "SWARMPIT_CONFIG_FILE": "~/.config/swarmpit/servers.json", "SWARMPIT_REDACT": "sensitive" }
}
}
}
Or without a file, using per-name env vars (SWARMPIT_<NAME>_URL, with - becoming _ and the name upper-cased):
"env": {
"SWARMPIT_SERVERS": "prod-eu,prod-us",
"SWARMPIT_DEFAULT_SERVER": "prod-eu",
"SWARMPIT_PROD_EU_URL": "https://swarmpit.eu.example.com",
"SWARMPIT_PROD_EU_TOKEN_FILE": "~/.config/swarmpit/prod-eu",
"SWARMPIT_PROD_US_URL": "https://swarmpit.us.example.com",
"SWARMPIT_PROD_US_TOKEN_FILE": "~/.config/swarmpit/prod-us"
}
Then: list_services({ server: "prod-us" }). Omitting server uses the default. If several instances are configured and no default is set, the argument is required β a forgotten argument will never silently pick a cluster for you. swarmpit_info lists what's configured.
Querying several instances at once
Read-only tools also accept "*" or a list of names, and return results grouped by server:
// list_services({ server: "*" })
{
"queried": ["prod-eu", "prod-us"],
"results": {
"prod-eu": [ { "serviceName": "api", ... } ],
"prod-us": [ { "serviceName": "api", ... } ]
}
}
Useful for "which cluster runs this service?", comparing an image tag across regions, or checking whether a config exists everywhere β one tool call instead of one per cluster.
- Reads only.
list_*,get_*andservice_logsaccept fan-out. Every mutating tool (create_*,update_*,delete_*,scale_*,redeploy_*,rollback_*,stop_*,deactivate_*,pin_*/unpin_*,edit_*) takes a single name only β "apply this to every cluster" should not be expressible by accident. - Partial failure is reported, not fatal. An unreachable cluster, or one where the named resource doesn't exist, comes back as
{ "error": "..." }under its own key and is listed infailed. The other clusters' results still arrive. - Passing
"*"or a list always returns the grouped shape, even if it resolves to one server; passing a bare name returns the plain result.
Which pattern to use
Consolidate within a trust tier, isolate across tiers.
- One MCP server, several instances β the default for instances in the same trust tier (several prod clusters, several staging clusters). This is where the duplicated tool schemas actually cost you.
- Separate MCP servers β the right answer across trust tiers. Keeping prod in its own process means a test or play conversation cannot reach the prod token at all, no matter what the model is talked into. That is a stronger guarantee than a
serverargument the model chooses itself.
The two compose. One MCP server holding every prod cluster, a second holding every test cluster, gets you both the schema saving and a real boundary where it matters:
{
"mcpServers": {
"swarmpit-prod": {
"command": "npx",
"args": ["github:swarmpit/mcp"],
"env": { "SWARMPIT_CONFIG_FILE": "~/.config/swarmpit/prod.json", "SWARMPIT_REDACT": "sensitive" }
},
"swarmpit-test": {
"command": "npx",
"args": ["github:swarmpit/mcp"],
"env": { "SWARMPIT_CONFIG_FILE": "~/.config/swarmpit/test.json", "SWARMPIT_REDACT": "none" }
}
}
}
A single-instance setup is unchanged in every respect: SWARMPIT_URL + SWARMPIT_TOKEN/SWARMPIT_TOKEN_FILE still work, and no server argument is added to any tool.
Environment variables
| Variable | Required | Description |
|---|---|---|
SWARMPIT_URL |
YesΒΉ | Swarmpit instance URL (single-instance setup) |
SWARMPIT_TOKEN |
One ofΒΉ | API token (with or without Bearer prefix). Avoid putting in .mcp.json β see token handling. |
SWARMPIT_TOKEN_FILE |
One ofΒΉ | Path to a file containing the token. Takes precedence over SWARMPIT_TOKEN. Recommended for production use. |
SWARMPIT_CONFIG_FILE |
YesΒΉ | Path to a JSON file defining several instances. Takes precedence over everything below. |
SWARMPIT_SERVERS |
YesΒΉ | Comma-separated instance names, each configured via SWARMPIT_<NAME>_URL and SWARMPIT_<NAME>_TOKEN/_TOKEN_FILE |
SWARMPIT_DEFAULT_SERVER |
No | Instance used when a tool call omits server. Without it, the argument is required. |
SWARMPIT_REDACT |
No | Redaction mode: all (default), sensitive, or none. Applies to all instances in the process. |
SWARMPIT_REDACT_PATTERNS |
No | Comma-separated extra patterns to redact in sensitive mode (regex, case-insensitive) |
ΒΉ Exactly one of the three forms: SWARMPIT_CONFIG_FILE, SWARMPIT_SERVERS, or SWARMPIT_URL. They are tried in that order.
Redaction modes
| Mode | Env vars | Secrets/Configs data | User records |
|---|---|---|---|
all |
All values redacted | Redacted | Identity only (_id, username, role, email) |
sensitive |
Only names matching patterns | Redacted | Identity only |
none |
No redaction | Not redacted | Full record |
User records never contain a password hash (the Swarmpit server strips it), but in the non-none modes the API-token metadata (jti, mask) and CouchDB _rev are dropped too β list_users/get_user report only hasApiToken: true.
Warning:
nonemode sends all environment variables, secrets, and config data in full to the LLM provider. Only use this with a local model (e.g. via ollama/opencode) or on servers that definitely do not contain any sensitive environment variables or configs. Never usenonewith cloud-hosted LLM providers on production infrastructure.
Built-in sensitive patterns: pass, secret, token, key, auth, credential, private, dsn, connection_string.
Add custom patterns via SWARMPIT_REDACT_PATTERNS:
"env": {
"SWARMPIT_REDACT": "sensitive",
"SWARMPIT_REDACT_PATTERNS": "GRAFANA,RPC,ENDPOINT,DATABASE"
}
Tools
Services
| Tool | Description |
|---|---|
list_services |
List all services |
get_service |
Get service details |
service_logs |
Get service logs |
create_service |
Create a service |
update_service |
Update a service |
redeploy_service |
Redeploy (optionally with new tag) |
rollback_service |
Rollback to previous version |
stop_service |
Stop a service |
scale_service |
Scale replicas |
list_service_tasks |
List service tasks/containers |
delete_service |
Delete (requires confirm: true) |
update_service_env |
Set/remove env vars (supports $env references) |
get_service_env |
Get specific env var values by name |
get_service_compose |
Get compose YAML for a service |
get_service_networks |
Get networks attached to a service |
Stacks
| Tool | Description |
|---|---|
list_stacks |
List all stacks |
get_stack |
Get stack services and compose file |
create_stack |
Create from compose YAML |
update_stack |
Update with new compose YAML |
redeploy_stack |
Redeploy all services |
rollback_stack |
Rollback all services |
deactivate_stack |
Stop all services in a stack |
delete_stack |
Delete (requires confirm: true) |
get_stack_tasks |
List all tasks in a stack |
get_stack_volumes |
List all volumes in a stack |
get_stack_networks |
List all networks in a stack |
get_stack_compose |
Get generated compose YAML |
get_stack_secrets |
List secrets in a stack |
get_stack_configs |
List configs in a stack |
create_stack_file |
Upload a compose file for a stack |
delete_stack_file |
Delete stack compose file (requires confirm: true) |
Networks
| Tool | Description |
|---|---|
list_networks |
List all networks |
get_network |
Get network details |
create_network |
Create a network |
delete_network |
Delete (requires confirm: true) |
get_network_services |
List services using a network |
Nodes
| Tool | Description |
|---|---|
list_nodes |
List all nodes |
get_node |
Get node details |
get_node_tasks |
List tasks running on a node |
edit_node |
Edit node properties |
delete_node |
Remove a node (requires confirm: true) |
Tasks
| Tool | Description |
|---|---|
list_tasks |
List all tasks |
get_task |
Get task details |
Volumes
| Tool | Description |
|---|---|
list_volumes |
List all volumes |
get_volume |
Get volume details |
create_volume |
Create a volume |
delete_volume |
Delete (requires confirm: true) |
get_volume_services |
List services using a volume |
Secrets
| Tool | Description |
|---|---|
list_secrets |
List all secrets (data redacted) |
get_secret |
Get secret details (data redacted) |
create_secret |
Create a secret (supports $env / $file references) |
delete_secret |
Delete (requires confirm: true) |
get_secret_services |
List services using a secret |
Configs
| Tool | Description |
|---|---|
list_configs |
List all configs (data redacted) |
get_config |
Get config details (data redacted) |
create_config |
Create a config (supports $env / $file references) |
delete_config |
Delete (requires confirm: true) |
get_config_services |
List services using a config |
Admin
| Tool | Description |
|---|---|
list_users |
List all Swarmpit users (redacted) |
get_user |
Get user details (redacted) |
create_user |
Create a user (password accepts $env/$file) |
edit_user |
Edit user properties (spec.password accepts $env/$file) |
delete_user |
Delete (requires confirm: true) |
Pass user passwords by reference so the plaintext never enters the conversation or the tool-call transcript:
{ "username": "svc", "role": "user", "password": { "$env": "NEW_USER_PASSWORD" } }
{ "$file": "/path/to/password" } works too. A literal string is still accepted, but it is recorded verbatim in the model's context and in the session transcript.
Dashboard
| Tool | Description |
|---|---|
pin_service_to_dashboard |
Pin a service to the Swarmpit dashboard |
unpin_service_from_dashboard |
Remove a service from the dashboard |
pin_node_to_dashboard |
Pin a node to the dashboard |
unpin_node_from_dashboard |
Remove a node from the dashboard |
Timeseries
| Tool | Description |
|---|---|
get_nodes_timeseries |
Node CPU/memory/disk over time |
get_services_cpu_timeseries |
Service CPU usage over time |
get_services_memory_timeseries |
Service memory usage over time |
get_task_timeseries |
Task metrics over time |
Utility
| Tool | Description |
|---|---|
swarmpit_info |
Show connected URL and redaction mode |
Token handling
Putting SWARMPIT_TOKEN directly in .mcp.json is convenient but risky: if anything (including Claude / the LLM) reads .mcp.json, the token leaks into the conversation and API logs. Two hardening steps you should take:
1. Block MCP config files from being read
Add this to your project .claude/settings.json so Claude Code refuses to Read credential-holding files:
{
"permissions": {
"deny": [
"Read(.mcp.json)",
"Read(**/.mcp.json)",
"Read(.env)",
"Read(.env.*)",
"Read(**/.env)",
"Read(**/.env.*)",
"Read(**/*credentials*)",
"Read(**/secrets/**)",
"Read(**/*.pem)",
"Read(**/*.key)"
]
}
}
2. Use SWARMPIT_TOKEN_FILE instead of inline
Store the token in a file outside the repo and reference it by path. The token never appears in .mcp.json itself:
# Write the token to a restricted file
install -m 600 /dev/stdin ~/.config/swarmpit/lark.token <<<'your-token-here'
{
"mcpServers": {
"swarmpit-lark": {
"command": "npx",
"args": ["github:swarmpit/mcp"],
"env": {
"SWARMPIT_URL": "https://swarmpit.example.com",
"SWARMPIT_TOKEN_FILE": "/Users/you/.config/swarmpit/lark.token",
"SWARMPIT_REDACT": "sensitive"
}
}
}
}
3. Password manager integration
For even stronger posture, have the MCP spawn with a secret manager:
{
"swarmpit-lark": {
"command": "op",
"args": ["run", "--", "npx", "github:swarmpit/mcp"],
"env": {
"SWARMPIT_URL": "https://swarmpit.example.com",
"SWARMPIT_TOKEN": "op://Private/Swarmpit Lark/token",
"SWARMPIT_REDACT": "sensitive"
}
}
}
1Password's op run substitutes op://... references at process start. macOS users can do the equivalent with security find-generic-password in a wrapper script.
If your token has already been exposed (e.g. you saw it scroll through a log), rotate it in Swarmpit UI β Profile β API Access β regenerate.
Secret handling
Secrets in .mcp.json env are passed to the MCP server process but never sent to the LLM.
Reading from local files
For large payloads (HTML pages, compose files, certs) use $file to have the MCP server read from disk instead of passing content through the LLM context:
create_config(configName: "my_dashboard", data: { "$file": "/path/to/index.html" })
create_secret(secretName: "tls_cert", data: { "$file": "/etc/ssl/server.crt" })
create_stack(name: "myapp", compose: { "$file": "/path/to/stack.yml" })
update_stack(name: "myapp", compose: { "$file": "/path/to/stack.yml" })
Saves context/credits on anything larger than a few hundred bytes. $env: references inside the file are still resolved before sending to Swarmpit.
Service env vars
Use $env references to set secrets without them entering the conversation:
update_service_env(id: "my-service", set: {
"NODE_ENV": "production",
"DB_PASSWORD": { "$env": "MY_DB_PASS" }
})
MY_DB_PASS is resolved from the MCP server's environment. Add it to .mcp.json env:
"env": {
"SWARMPIT_URL": "...",
"SWARMPIT_TOKEN": "...",
"MY_DB_PASS": "the-actual-password"
}
Stack compose files
When reading stacks, env var values are redacted according to the redaction mode. When updating, [REDACTED] values are automatically preserved from the current stack β only changed values are updated:
# Returned by get_stack (sensitive mode):
environment:
NODE_ENV: production # visible
DB_PASSWORD: [REDACTED] # redacted
# Sent to update_stack β only NODE_ENV changed:
environment:
NODE_ENV: staging # new value
DB_PASSWORD: [REDACTED] # preserved from current stack
Use $env:VAR_NAME for new secrets in compose:
environment:
NEW_SECRET: $env:MY_SECRET # resolved locally
Preserved values are read from the live service state, not the stored stack file β the two diverge whenever a var is changed through update_service_env or the Swarmpit UI. If they disagree for a var being restored, update_stack says so in its result.
Restoration is structural: each placeholder is filled from the same service and key (or the same path outside services), so two services sharing a name like ALERT_WEBHOOK each keep their own value. Quoted ('[REDACTED]', "[REDACTED]"), list (- KEY=[REDACTED], - "KEY=[REDACTED]") and commented forms all work. A placeholder that neither the live state nor the stack file can fill makes update_stack refuse the write (and dry_run reports it) instead of shipping the literal string.
Service specs
update_service applies the same protection: any env var left as [REDACTED] is restored from the live service before the write, so a get_service β edit one field β update_service round-trip can't overwrite secrets with the placeholder. Restored names are listed in the result as restoredVars.
A [REDACTED] variable the live service doesn't have is refused rather than written.
As a last line of defence the client never sends a write request whose body contains [REDACTED], whichever tool built it.
Previewing a write
update_service and update_stack take dry_run: true, which computes everything β [REDACTED] restoration, $env: resolution, null normalisation β and reports what would change without sending it:
// update_service({ id, spec, dry_run: true })
{
"dryRun": true,
"restoredVars": ["RPC_URL"],
"changes": {
"fields": { "replicas": { "from": 1, "to": 3 } },
"variables": { "changed": ["LOG_LEVEL"], "added": ["NEW"], "removed": ["OLD"], "unchanged": 4 }
}
}
For stacks the diff is semantic, not line-based β the two composes are parsed and compared service by service:
// update_stack({ name, compose, dry_run: true })
{
"dryRun": true,
"changes": {
"changed": true,
"services": {
"added": ["cache"],
"removed": ["worker"],
"changed": {
"web": {
"image": { "from": "nginx:1.0", "to": "nginx:2.0" },
"ports": { "added": ["443:443"] },
"environment": { "added": ["NEW_VAR"], "changed": ["DB_PASSWORD"] }
}
}
},
"secretsChanged": ["DB_PASSWORD"]
}
}
Compared with a text diff this survives duplicate lines (restart: always in three services), key reordering, and the $$ escaping Swarmpit applies to generated compose β and every change arrives attributed to the service it belongs to.
Env var values only appear when the redaction mode would have shown them anyway: never in all, only for non-sensitive names in sensitive, and freely in none. A changed value you can't see is still reported by name, both in environment.changed and in the document-wide secretsChanged list, so you always know that a secret moved without it being printed into the conversation.
Compose history
If your Swarmpit serves /api/stacks/{name}/history, get_stack_history lists past revisions of a stack β newest first, metadata only by default, since an uncapped history of full composes is exactly the payload problem to avoid:
{ "entries": [
{ "index": 0, "at": "...", "by": "claude", "comment": "bump nginx for CVE-2026-1234", "trigger": {"kind": "stack-update"} },
{ "index": 1, "at": "...", "by": "admin", "comment": "initial rollout", "trigger": {"kind": "stack-create"} } ] }
Pass index for one revision's compose (sanitized like every other compose path), or index + diff: true to get the semantic diff between that revision and the live stack.
Every stack write β create_stack, update_stack, redeploy_stack, rollback_stack β takes an optional comment: a one-line title for the change, written like a commit subject. It is recorded in the history and shown in Swarmpit's UI, which has no field for it, so an agent making the change is the one best placed to explain it. Older Swarmpit versions ignore the parameter.
Large payloads
Two tool families return far more than fits comfortably in context, so both reduce server-side:
- Timeseries (
get_nodes_timeseries,get_services_*_timeseries,get_task_timeseries) acceptpoints(bucket count, default 12),agg(avg/max/min),match(filter series by name) andstats_only. Summary statistics are computed from the full series before downsampling, sostats.maxis the real peak, not the peak of an average. A 30-service / 720-sample payload comes back over 10Γ smaller by default. service_logsacceptsgrep(substring, or/regex/flags) andtail, applied before the result is returned. The reply reportstotal,returnedand what wasdropped, so a filtered view never looks like the whole log.
Development
git clone https://github.com/swarmpit/mcp
cd mcp
npm install
npm run build # compile TypeScript
npm run dev # watch mode
npm test # run tests
When developing locally, point .mcp.json at your local build:
{
"mcpServers": {
"swarmpit-dev": {
"command": "node",
"args": ["/path/to/mcp/dist/index.js"],
"env": {
"SWARMPIT_URL": "https://swarmpit.example.com",
"SWARMPIT_TOKEN": "your-token",
"SWARMPIT_REDACT": "sensitive"
}
}
}
}
License
MIT
Swarmpit MCP questions
What tools does Swarmpit MCP provide?
It exposes 72 tools, including list_services, get_service, service_logs, create_service, update_service.
How do I get an API token for Swarmpit?
You can obtain your API token directly from the Swarmpit UI by navigating to Profile β API Access β Generate token.
Can I manage multiple Swarmpit instances with one server?
Yes, one process can manage several Swarmpit instances by using a configuration file or specific environment variables for each instance.
Is my sensitive data safe when using cloud-hosted LLMs?
To protect sensitive data, use the 'all' or 'sensitive' redaction modes. Avoid using 'none' mode with cloud-hosted LLM providers on production infrastructure.
Can I query multiple clusters at once?
Yes, read-only tools allow you to pass '*' or a list of names to query multiple instances simultaneously and receive grouped results.