Skip to content
actionlake
Start free

Connectors · Identity & security

Panther MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Panther and the rest of your systems. It gives your agent 98 Panther actions (36 reads, 42 writes and 20 that wait for a confirmation) and holds the Panther credential itself, so the agent never does. It paces Panther's limits and records every call.

Connect Panther freeSee 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
the first call
do {  action: "panther.users.list",  intent: "check which Panther account is connected"}# List users · read · 1 upstream call
  • 98actionsin one signed file
  • 36readlook, never change
  • 42writecreate and update
  • 20wait for a yesdestructive, confirmed first

Set up

Connect Panther in three steps.

  1. 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
  2. 02

    Connect Panther.

    API key. 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.

    • api_keyPanther API token: in the Panther Console open Settings > API Tokens > Create New Token and grant the permissions…
    • hostWhere your Panther lives: your host
    account { op: "connections.requirements", service: "panther" }
# free: exactly what to paste, and what is found for you
  3. 03

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

Panther at a glance

Sign-in
API key. 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
api_key
Setup fields
host
Limits we pace to
600 calls a minute, per connection
API covered
Panther REST API 1.0 + GraphQL, at your Panther instance's API base URL, which you enter when connecting
Built from
Panther's documentation, read 23 October 2026openapi.gitbook.comdocs.panther.comdocs.panther.com
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
33 of 36 reads, for up to 1 minute; a write clears what it affects
Shared entities
4, so ask can line Panther up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Panther.

98 actions in 23 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 36readlook, never change
  • 42writecreate and update
  • 20destructivewait for a confirmation

  1. API tokens

    6

    2 read · 2 write · 2 destructive

    Create an api token · List api tokens · Get an api token · Delete api token

  2. Correlation rules

    5

    2 read · 2 write · 1 destructive

    Create correlation rule · List correlation rules · Get a correlation rule · Delete correlation rule

  3. Data models

    5

    2 read · 2 write · 1 destructive

    Create data model · List data models · Get data model · Delete data model

  4. Globals

    5

    2 read · 2 write · 1 destructive

    Create global · List globals · Get global · Delete global

  5. Policies

    5

    2 read · 2 write · 1 destructive

    List policies · Create policy · Get policy · Delete policy

  6. Queries

    5

    2 read · 2 write · 1 destructive

    Create query · List queries · Get query · Update query

  7. Roles

    5

    2 read · 2 write · 1 destructive

    List roles · Create a role · Get a role · Update a role

  8. Rules

    5

    2 read · 2 write · 1 destructive

    List rules · Create rule · Get rule · Delete rule

15 more areas · 57 actions
  • Scheduled rules 5
  • Simple rules 5
  • Users 5
  • Alert comments 4
  • Alert context tags 4
  • Alerts 4
  • Aws cloud accounts 4
  • GCS sources 4
  • HTTP sources 4
  • Log forwarder sources 4
  • Pubsub sources 4
  • S3 sources 4
  • Log source alarms 3
  • Graphql 2
  • Alert events 1

Top actions

The Panther API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 28 of Panther's 28 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
panther.users.listList usersList users.readidentity.user.list474 connectors
panther.roles.listList rolesList roles.readidentity.role.list184 connectors
panther.users.createCreate a userCreate a user.writeidentity.user.create262 connectors
panther.roles.createCreate a roleCreate a role.writeidentity.role.create105 connectors
panther.users.deleteDelete a userDelete a user.destructiveidentity.user.delete253 connectors
panther.policies.listList policiesList policies.readsecurity.policy.list36 connectors
panther.api_tokens.createCreate an api tokenCreate an api token.writeidentity.api_key.create100 connectors
panther.api_tokens.listList api tokensList api tokens.readidentity.api_key.list96 connectors
panther.policies.createCreate policyCreate policy.writesecurity.policy.create25 connectors
panther.alerts.listList alertsList alerts.readsecurity.alert.list22 connectors
panther.rules.listList rulesList rules.readsecurity.detection_rule.list13 connectors
panther.rules.createCreate ruleCreate rule.writesecurity.detection_rule.create11 connectors

Try it

Prompts to paste into Claude.

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

  1. Readread

    Which Panther alerts are open right now? Group them by service.

    callspanther.alerts.list

  2. Writewrite

    Create a user in Panther. Show me exactly what you will send before you save it.

    callspanther.users.create

Governance for Panther

Destructive actions wait for a yes.

20 Panther actions are destructive. These are all of them:

  • Delete a userpanther.users.delete
  • Delete a rolepanther.roles.delete
  • Delete api tokenpanther.api_tokens.delete
  • Delete policypanther.policies.delete
  • Delete rulepanther.rules.delete
  • Delete globalpanther.globals.delete
  • Delete querypanther.queries.delete
  • Rotate an api tokenpanther.api_tokens.rotate
  • Delete s3 sourcepanther.s3_sources.delete
  • Delete data modelpanther.data_models.delete
  • Delete gcs sourcepanther.gcs_sources.delete
  • Delete http sourcepanther.http_sources.delete
  • Delete simple rulepanther.simple_rules.delete
  • Delete pub/sub sourcepanther.pubsub_sources.delete
  • Delete scheduled rulepanther.scheduled_rules.delete
  • Delete correlation rulepanther.correlation_rules.delete
  • Delete log source alarmpanther.log_source_alarms.delete
  • Delete a custom context tagpanther.alert_context_tags.delete
  • Delete aws cloud accountpanther.aws_cloud_accounts.delete
  • Delete log forwarder sourcepanther.log_forwarder_sources.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.

dopanther.users.deleteconfirm_policy: human

Delete a user?

intent: the user asked me to delete a user

run suspended · waiting for a named person · key panther-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "panther-agent",  allowed_actions: ["panther.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "panther.users.delete", approver: "[email protected]" },    { match: "panther.roles.delete", approver: "[email protected]" },    { match: "panther.api_tokens.delete", approver: "[email protected]" }  ]}
Illustrative. Scoped to Panther only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Panther costs on actionlake.

Every Panther action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Panther 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 98 Panther actions
  • 98actions pageeach page of a long list is one call
  • 33reads 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 Panther action.

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

API tokens6
  • panther.api_tokens.createCreate an api tokenwrite
  • panther.api_tokens.deleteDelete api tokendestructive
  • panther.api_tokens.getGet an api tokenread
  • panther.api_tokens.listList api tokensread
  • panther.api_tokens.rotateRotate an api tokendestructive
  • panther.api_tokens.updateUpdate an api tokenwrite
Correlation rules5
  • panther.correlation_rules.createCreate correlation rulewrite
  • panther.correlation_rules.deleteDelete correlation ruledestructive
  • panther.correlation_rules.getGet a correlation ruleread
  • panther.correlation_rules.listList correlation rulesread
  • panther.correlation_rules.updatePut correlation rulewrite
Data models5
  • panther.data_models.createCreate data modelwrite
  • panther.data_models.deleteDelete data modeldestructive
  • panther.data_models.getGet data modelread
  • panther.data_models.listList data modelsread
  • panther.data_models.updatePut data modelwrite
Globals5
  • panther.globals.createCreate globalwrite
  • panther.globals.deleteDelete globaldestructive
  • panther.globals.getGet globalread
  • panther.globals.listList globalsread
  • panther.globals.updatePut globalwrite
Policies5
  • panther.policies.createCreate policywrite
  • panther.policies.deleteDelete policydestructive
  • panther.policies.getGet policyread
  • panther.policies.listList policiesread
  • panther.policies.updatePut policywrite
Queries5
  • panther.queries.createCreate querywrite
  • panther.queries.deleteDelete querydestructive
  • panther.queries.getGet queryread
  • panther.queries.listList queriesread
  • panther.queries.updateUpdate querywrite
Roles5
  • panther.roles.createCreate a rolewrite
  • panther.roles.deleteDelete a roledestructive
  • panther.roles.getGet a roleread
  • panther.roles.listList rolesread
  • panther.roles.updateUpdate a rolewrite
Rules5
  • panther.rules.createCreate rulewrite
  • panther.rules.deleteDelete ruledestructive
  • panther.rules.getGet ruleread
  • panther.rules.listList rulesread
  • panther.rules.updatePut rulewrite
Scheduled rules5
  • panther.scheduled_rules.createCreate scheduled rulewrite
  • panther.scheduled_rules.deleteDelete scheduled ruledestructive
  • panther.scheduled_rules.getGet scheduled ruleread
  • panther.scheduled_rules.listList scheduled rulesread
  • panther.scheduled_rules.updatePut scheduled rulewrite
Simple rules5
  • panther.simple_rules.createCreate simple rulewrite
  • panther.simple_rules.deleteDelete simple ruledestructive
  • panther.simple_rules.getGet a simple ruleread
  • panther.simple_rules.listList simple rulesread
  • panther.simple_rules.updatePut simple rulewrite
Users5
  • panther.users.createCreate a userwrite
  • panther.users.deleteDelete a userdestructive
  • panther.users.getGet a userread
  • panther.users.listList usersread
  • panther.users.updateUpdate a userwrite
Alert comments4
  • panther.alert_comments.createCreate a comment for an alertwrite
  • panther.alert_comments.getGet a comment for an alertread
  • panther.alert_comments.listList alert commentsread
  • panther.alert_comments.updateUpdate a comment for an alertwrite
Alert context tags4
  • panther.alert_context_tags.createCreate a custom context tagwrite
  • panther.alert_context_tags.deleteDelete a custom context tagdestructive
  • panther.alert_context_tags.listList all context tagsread
  • panther.alert_context_tags.updateRename a custom context tagwrite
Alerts4
  • panther.alerts.bulk_updateUpdate the status, assignee, quality or contextTags of multiple alertswrite
  • panther.alerts.getGet an alertread
  • panther.alerts.listList alertsread
  • panther.alerts.updateUpdate the status, assignee, quality or contextTags of an alertwrite
Aws cloud accounts4
  • panther.aws_cloud_accounts.createCreate aws cloud accountwrite
  • panther.aws_cloud_accounts.deleteDelete aws cloud accountdestructive
  • panther.aws_cloud_accounts.getGet aws cloud accountread
  • panther.aws_cloud_accounts.updatePut aws cloud accountwrite
GCS sources4
  • panther.gcs_sources.createCreate gcs sourcewrite
  • panther.gcs_sources.deleteDelete gcs sourcedestructive
  • panther.gcs_sources.getGet gcs sourceread
  • panther.gcs_sources.updatePut gcs sourcewrite
HTTP sources4
  • panther.http_sources.createCreate http sourcewrite
  • panther.http_sources.deleteDelete http sourcedestructive
  • panther.http_sources.getGet http sourceread
  • panther.http_sources.updatePut http sourcewrite
Log forwarder sources4
  • panther.log_forwarder_sources.createCreate log forwarder sourcewrite
  • panther.log_forwarder_sources.deleteDelete log forwarder sourcedestructive
  • panther.log_forwarder_sources.getGet log forwarder sourceread
  • panther.log_forwarder_sources.updatePut log forwarder sourcewrite
Pubsub sources4
  • panther.pubsub_sources.createCreate pub/sub sourcewrite
  • panther.pubsub_sources.deleteDelete pub/sub sourcedestructive
  • panther.pubsub_sources.getGet pub/sub sourceread
  • panther.pubsub_sources.updatePut pub/sub sourcewrite
S3 sources4
  • panther.s3_sources.createCreate s3 sourcewrite
  • panther.s3_sources.deleteDelete s3 sourcedestructive
  • panther.s3_sources.getGet s3 sourceread
  • panther.s3_sources.updatePut s3 sourcewrite
Log source alarms3
  • panther.log_source_alarms.deleteDelete log source alarmdestructive
  • panther.log_source_alarms.getGet log source alarmread
  • panther.log_source_alarms.updatePut log source alarmwrite
Graphql2
  • panther.graphql.mutateRun a GraphQL mutationwrite
  • panther.graphql.queryRun a GraphQL queryread
Alert events1
  • panther.alert_events.listList alert eventsread

Questions

The Panther MCP server, answered.

Is there a Panther MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 98 Panther actions across API tokens, correlation rules, data models and globals, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Panther.

What do I need to connect Panther?

Panther API token: in the Panther Console open Settings > API Tokens > Create New Token and grant the permissions…. Plus your host. The free call account { op: "connections.requirements", service: "panther" } lists exactly what to paste.

Can an AI agent delete or change things in Panther?

Only if its key allows it, and only with an explicit confirmation. 20 Panther actions are destructive, including delete a user, delete a role and delete api token. 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 Panther API limit?

actionlake paces every call to the limits in the Panther service file: 600 calls a minute per connection. Repeated reads are answered from cache (33 Panther actions can be), which never reaches Panther.

What does a Panther action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (98 Panther actions page). Cache hits, searches, dry runs and calls Panther 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 Panther API does it cover?

The Panther REST API 1.0 + GraphQL at your Panther instance's API base URL, which you enter when connecting. It is built from Panther's documentation as read on 23 October 2026. 98 actions in 23 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Panther data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 1 minute, 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 Panther 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.

More connectors like Panther

Shares the most action names with

Joins with, on shared entities

Browse

actionlake is independent. It is not made or endorsed by Panther; the name is the vendor's own. Counts are from the Panther service file, version 1.0.0.

Give your agent Panther today.

Connect Panther freeSee pricing

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