Skip to content
actionlake
Start free

Connectors · MSP & PSA

Sublime Security MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Sublime Security and the rest of your systems. It gives your agent 100 Sublime Security actions (53 reads, 38 writes and 9 that wait for a confirmation) and holds the Sublime Security credential itself, so the agent never does. It paces Sublime Security's limits and records every call.

Connect Sublime Security 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: "sublime_security.scim_users.list",  intent: "check which Sublime Security account is connected"}# List SCIM users · read · 1 upstream call
  • 100actionsin one signed file
  • 53readlook, never change
  • 38writecreate and update
  • 9wait for a yesdestructive, confirmed first

Set up

Connect Sublime Security 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 Sublime Security.

    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.

    • api_keySublime API key: in the Sublime dashboard go to Automate > API, create a key and copy it
    • hostWhere your Sublime Security lives: your host
    account { op: "connections.requirements", service: "sublime_security" }
# 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: "sublime_security.scim_users.list" }# list scim users · read · 1 upstream callcheck { action: "sublime_security.scim_users.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Sublime Security 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
api_key
Setup fields
host
Limits we pace to
600 calls a minute, per connection
API covered
Sublime Platform API v0 (OpenAPI 3.0.1, generated) and the Multi-Tenancy API (beta), at your Sublime Security instance's API base URL, which you enter when connecting
Built from
Sublime Security's documentation, read 23 October 2026docs.sublime.securitydocs.sublime.securitydocs.sublime.security
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
47 of 53 reads, for up to 5 minutes; a write clears what it affects
Shared entities
3, so ask can line Sublime Security up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Sublime Security.

100 actions in 19 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 53readlook, never change
  • 38writecreate and update
  • 9destructivewait for a confirmation

  1. Message groups

    19

    6 read · 11 write · 2 destructive

    Retrieve details about the state of manual actions for a canonical group · Hunt message groups · List message groups · Search message groups

  2. Messages

    17

    12 read · 4 write · 1 destructive

    Analyze a message by ID · Analyze a raw message · Render image for attachment from the raw base64 encoded bytes · Evaluate attack score for a raw message

  3. Lists

    10

    4 read · 4 write · 2 destructive

    Create list · Get list entries · Add list entry · Retrieve lists

  4. Rules

    10

    5 read · 4 write · 1 destructive

    List rules · Create rule · Retrieve rule · Update rule

  5. Scim

    6

    6 read · 0 write · 0 destructive

    List SCIM resource types · List SCIM schemas · Validate SCIM specific auth · Get SCIM resource type

  6. Scim users

    6

    2 read · 3 write · 1 destructive

    List SCIM users · Create SCIM user · Get SCIM user · Patch SCIM user

  7. Child organizations

    5

    1 read · 4 write · 0 destructive

    Create child organization · List child organizations · Bulk update child organization licensing · Update child organization licensing

  8. Message exports

    5

    3 read · 1 write · 1 destructive

    Export dashboard report · List message export jobs · Estimate export size of dashboard report · Get message export job

11 more areas · 22 actions
  • DLP release requests 4
  • Email bombs 4
  • Audit log 3
  • Hunt jobs 3
  • Binexplode 2
  • Enrichment 1
  • Live flow 1
  • Mailboxes 1
  • Roles 1
  • Tasks 1
  • User reports 1

Top actions

The Sublime Security API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 11 of Sublime Security's 14 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
sublime_security.scim_users.listList SCIM usersList SCIM users.readidentity.user.list474 connectors
sublime_security.rules.listList rulesList rules.readsecurity.policy.list36 connectors
sublime_security.scim_users.createCreate SCIM userCreate SCIM user.writeidentity.user.create262 connectors
sublime_security.rules.createCreate ruleCreate rule.writesecurity.policy.create25 connectors
sublime_security.scim_users.deleteDelete SCIM userDelete SCIM user.destructiveidentity.user.delete253 connectors
sublime_security.mailboxes.listList mailboxesList mailboxes.readcomm.mailbox.list18 connectors
sublime_security.lists.listRetrieve listsRetrieve lists.readthis connector
sublime_security.lists.createCreate listCreate list.writethis connector
sublime_security.audit_log.listList events in audit logList events in audit log.readthis connector
sublime_security.messages.createCreate messageCreate message.writethis connector
sublime_security.email_bombs.listList email bombsList email bombs.readthis connector
sublime_security.hunt_jobs.createStart hunt jobStart hunt job.writethis connector

Try it

Prompts to paste into Claude.

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

  1. Readread

    Who has access in Sublime Security? List every user and their role.

    callssublime_security.scim_users.list

  2. Writewrite

    Create SCIM user in Sublime Security. Show me exactly what you will send before you save it.

    callssublime_security.scim_users.create

Governance for Sublime Security

Destructive actions wait for a yes.

9 Sublime Security actions are destructive. These are all of them:

  • Delete SCIM usersublime_security.scim_users.delete
  • Delete rulesublime_security.rules.delete
  • Delete listsublime_security.lists.delete
  • Assign role to usersublime_security.roles.assign
  • Trash messagesublime_security.messages.trash
  • Delete list entrysublime_security.lists.entry_delete
  • Trash message groupsublime_security.message_groups.trash
  • Delete message export jobsublime_security.message_exports.delete
  • Trash multiple message groupssublime_security.message_groups.bulk_trash

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.

dosublime_security.scim_users.deleteconfirm_policy: human

Delete SCIM user?

intent: the user asked me to delete SCIM user

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

Cost

What Sublime Security costs on actionlake.

Every Sublime Security action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Sublime Security 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 100 Sublime Security actions
  • 100actions pageeach page of a long list is one call
  • 47reads 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 Sublime Security action.

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

Message groups19
  • sublime_security.message_groups.action_states_listRetrieve details about the state of manual actions for a canonical groupread
  • sublime_security.message_groups.bulk_dismissDismiss multiple message groupswrite
  • sublime_security.message_groups.bulk_move_to_graymailGraymail multiple message groupswrite
  • sublime_security.message_groups.bulk_move_to_spamMove multiple message groups to spamwrite
  • sublime_security.message_groups.bulk_quarantineQuarantine multiple message groupswrite
  • sublime_security.message_groups.bulk_restoreRestore multiple message groupswrite
  • sublime_security.message_groups.bulk_reviewReview message groupswrite
  • sublime_security.message_groups.bulk_trashTrash multiple message groupsdestructive
  • sublime_security.message_groups.dismissDismiss message groupwrite
  • sublime_security.message_groups.getGet a single message groupread
  • sublime_security.message_groups.huntHunt message groupswrite
  • sublime_security.message_groups.hunt_results_getGet results of a huntread
  • sublime_security.message_groups.listList message groupsread
  • sublime_security.message_groups.quarantineQuarantine message groupwrite
  • sublime_security.message_groups.restoreRestore message groupwrite
  • sublime_security.message_groups.searchSearch message groupsread
  • sublime_security.message_groups.share_with_sublimeShare a message with Sublimewrite
  • sublime_security.message_groups.siem_summary_listGet SIEM-oriented summary of flagged message groupsread
  • sublime_security.message_groups.trashTrash message groupdestructive
Messages17
  • sublime_security.messages.actionPerform actions on an individual messagewrite
  • sublime_security.messages.analyzeAnalyze a message by IDread
  • sublime_security.messages.analyze_rawAnalyze a raw messageread
  • sublime_security.messages.asa_report_getRetrieve ASA report for a messageread
  • sublime_security.messages.asa_verdict_getRetrieve ASA verdict for a messageread
  • sublime_security.messages.attachment_image_getRetrieve image of PDF attachment by md5 hashread
  • sublime_security.messages.attachment_image_renderRender image for attachment from the raw base64 encoded bytesread
  • sublime_security.messages.attack_score_getEvaluate attack score against an existing messageread
  • sublime_security.messages.attack_score_rawEvaluate attack score for a raw messageread
  • sublime_security.messages.createCreate messagewrite
  • sublime_security.messages.data_model_getRetrieve the message's Message Data Modelread
  • sublime_security.messages.getRetrieve messageread
  • sublime_security.messages.image_getRetrieve image of messageread
  • sublime_security.messages.image_link_getRetrieve a temporary link to the image of messageread
  • sublime_security.messages.justification_setSet access justificationwrite
  • sublime_security.messages.restoreRestore a previously-trashed messagewrite
  • sublime_security.messages.trashTrash messagedestructive
Lists10
  • sublime_security.lists.createCreate listwrite
  • sublime_security.lists.deleteDelete listdestructive
  • sublime_security.lists.entries_listGet list entriesread
  • sublime_security.lists.entries_replaceSet list entrieswrite
  • sublime_security.lists.entry_addAdd list entrywrite
  • sublime_security.lists.entry_deleteDelete list entrydestructive
  • sublime_security.lists.entry_getGet list entryread
  • sublime_security.lists.getGet listread
  • sublime_security.lists.listRetrieve listsread
  • sublime_security.lists.updatePatch listwrite
Rules10
  • sublime_security.rules.activateActivate rulewrite
  • sublime_security.rules.createCreate rulewrite
  • sublime_security.rules.deactivateDeactivate rulewrite
  • sublime_security.rules.deleteDelete ruledestructive
  • sublime_security.rules.getRetrieve ruleread
  • sublime_security.rules.history_getRetrieve history of a ruleread
  • sublime_security.rules.history_listList history for rulesread
  • sublime_security.rules.listList rulesread
  • sublime_security.rules.updateUpdate rulewrite
  • sublime_security.rules.validateValidate ruleread
Scim6
  • sublime_security.scim.auth_validateValidate SCIM specific authread
  • sublime_security.scim.resource_type_getGet SCIM resource typeread
  • sublime_security.scim.resource_types_listList SCIM resource typesread
  • sublime_security.scim.schema_getGet SCIM schemaread
  • sublime_security.scim.schemas_listList SCIM schemasread
  • sublime_security.scim.service_provider_config_getGet SCIM service provider configurationread
Scim users6
  • sublime_security.scim_users.createCreate SCIM userwrite
  • sublime_security.scim_users.deleteDelete SCIM userdestructive
  • sublime_security.scim_users.getGet SCIM userread
  • sublime_security.scim_users.listList SCIM usersread
  • sublime_security.scim_users.patchPatch SCIM userwrite
  • sublime_security.scim_users.replaceUpdate SCIM userwrite
Child organizations5
  • sublime_security.child_organizations.createCreate child organizationwrite
  • sublime_security.child_organizations.licensing_bulk_updateBulk update child organization licensingwrite
  • sublime_security.child_organizations.licensing_updateUpdate child organization licensingwrite
  • sublime_security.child_organizations.listList child organizationsread
  • sublime_security.child_organizations.updateUpdate child organizationwrite
Message exports5
  • sublime_security.message_exports.dashboard_export_createExport dashboard reportwrite
  • sublime_security.message_exports.dashboard_export_estimateEstimate export size of dashboard reportread
  • sublime_security.message_exports.deleteDelete message export jobdestructive
  • sublime_security.message_exports.getGet message export jobread
  • sublime_security.message_exports.listList message export jobsread
DLP release requests4
  • sublime_security.dlp_release_requests.approveApprove a DLP release requestwrite
  • sublime_security.dlp_release_requests.denyDeny a DLP release requestwrite
  • sublime_security.dlp_release_requests.getGet a DLP release requestread
  • sublime_security.dlp_release_requests.listList DLP release requestsread
Email bombs4
  • sublime_security.email_bombs.createCreate email bombwrite
  • sublime_security.email_bombs.dismissDismiss email bombwrite
  • sublime_security.email_bombs.getGet email bombread
  • sublime_security.email_bombs.listList email bombsread
Audit log3
  • sublime_security.audit_log.event_types_listList event types for audit logread
  • sublime_security.audit_log.getRetrieve event from audit logread
  • sublime_security.audit_log.listList events in audit logread
Hunt jobs3
  • sublime_security.hunt_jobs.createStart hunt jobwrite
  • sublime_security.hunt_jobs.getGet hunt jobread
  • sublime_security.hunt_jobs.results_listGet hunt job resultsread
Binexplode2
  • sublime_security.binexplode.scan_createUpload a binary to be binexplodedwrite
  • sublime_security.binexplode.scan_getGet results of a binexplode scanread
Enrichment1
  • sublime_security.enrichment.link_analysis_evaluateAnalyze a provided link using ml.link_analysis functionalityread
Live flow1
  • sublime_security.live_flow.raw_message_analyzeProcess raw messagewrite
Mailboxes1
  • sublime_security.mailboxes.listList mailboxesread
Roles1
  • sublime_security.roles.assignAssign role to userdestructive
Tasks1
  • sublime_security.tasks.getRetrieve taskread
User reports1
  • sublime_security.user_reports.listList user reportsread

Questions

The Sublime Security MCP server, answered.

Is there a Sublime Security MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 100 Sublime Security actions across message groups, messages, lists and rules, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Sublime Security.

What do I need to connect Sublime Security?

Sublime API key: in the Sublime dashboard go to Automate > API, create a key and copy it. Plus your host. The free call account { op: "connections.requirements", service: "sublime_security" } lists exactly what to paste.

Can an AI agent delete or change things in Sublime Security?

Only if its key allows it, and only with an explicit confirmation. 9 Sublime Security actions are destructive, including delete SCIM user, delete rule and delete list. 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 Sublime Security API limit?

actionlake paces every call to the limits in the Sublime Security service file: 600 calls a minute per connection. Repeated reads are answered from cache (47 Sublime Security actions can be), which never reaches Sublime Security.

What does a Sublime Security action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (100 Sublime Security actions page). Cache hits, searches, dry runs and calls Sublime Security 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 Sublime Security API does it cover?

The Sublime Platform API v0 (OpenAPI 3.0.1, generated) and the Multi-Tenancy API (beta) at your Sublime Security instance's API base URL, which you enter when connecting. It is built from Sublime Security's documentation as read on 23 October 2026. 100 actions in 19 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Sublime Security 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 Sublime Security 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 Sublime Security

Shares the most action names with

Joins with, on shared entities

Browse

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

Give your agent Sublime Security today.

Connect Sublime Security freeSee pricing

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