Skip to content
actionlake
Start free

Connectors · MSP & PSA

Blumira MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Blumira and the rest of your systems. It gives your agent 59 Blumira actions (41 reads, 14 writes and 4 that wait for a confirmation) and holds the Blumira credential itself, so the agent never does. It paces Blumira's limits and records every call.

Connect Blumira 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: "blumira.users.list",  intent: "check which Blumira account is connected"}# List users · read · 1 upstream call
  • 59actionsin one signed file
  • 41readlook, never change
  • 14writecreate and update
  • 4wait for a yesdestructive, confirmed first

Set up

Connect Blumira 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 Blumira.

    OAuth 2.0, client credentials. Paste the app's client id and secret; actionlake fetches and renews the token, and nobody has to sign in. actionlake stores what you paste write-only, sealed under your tenant's key.

    • client_idBlumira API Client ID
    • client_secretBlumira API Client Secret, shown once when the credential pair is generated
    account { op: "connections.requirements", service: "blumira" }
# 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: "blumira.users.list" }# list users · read · 1 upstream callcheck { action: "blumira.webhooks.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Blumira at a glance

Sign-in
OAuth 2.0, client credentials. Paste the app's client id and secret; actionlake fetches and renews the token, and nobody has to sign in.
You provide
client_idclient_secret
Limits we pace to
600 calls a minute, per connection
API covered
Blumira Public API v1 (OpenAPI 3.0.0)api.blumira.com/public-api/v1
Built from
Blumira's documentation, read 23 October 2026api.blumira.comsupport.blumira.com
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
41 of 41 reads, for up to 5 minutes; a write clears what it affects
Shared entities
4, so ask can line Blumira up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Blumira.

59 actions in 1 area. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 41readlook, never change
  • 14writecreate and update
  • 4destructivewait for a confirmation

  1. Siem

    59

    41 read · 14 write · 4 destructive

    List users · List MSP sub-accounts · List users (sub-account) · List agent devices

Top actions

The Blumira API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 17 of Blumira's 17 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
blumira.users.listList usersGet or search users for your organization.readidentity.user.list474 connectors
blumira.msp_accounts.listList MSP sub-accountsGet or search sub-accounts for your MSP.readcrm.company.list162 connectors
blumira.msp_account_users.listList users (sub-account)Get or search users for your MSP sub-account.readidentity.user.list474 connectors
blumira.agent_devices.listList agent devicesGet or search agents devices.readdevice.endpoint.list65 connectors
blumira.msp_account_agent_devices.listList agent devices (sub-account)Get or search agents devices for your MSP sub-account.readdevice.endpoint.list65 connectors
blumira.msp_accounts.getGet an MSP sub-accountGet a specific MSP sub-account by ID.readcrm.company.get162 connectors
blumira.findings.listList findingsGet or search findings for your organization.readsecurity.alert.list22 connectors
blumira.webhook_deliveries.listList deliveries for a webhook endpointList delivery history for a webhook endpoint (paginated).readautomation.webhook_delivery.list33 connectors
blumira.webhooks.createCreate a webhook endpointCreate a webhook endpoint.writeautomation.webhook.create209 connectors
blumira.msp_webhooks.createCreate a webhook endpoint (MSP parent)Create a webhook endpoint for your MSP parent organization.writeautomation.webhook.create209 connectors
blumira.webhooks.updateUpdate a webhook endpointUpdate a webhook endpoint (partial update; no secret returned).writeautomation.webhook.update175 connectors
blumira.webhooks.deleteDelete a webhook endpointSoft-delete a webhook endpoint.destructiveautomation.webhook.delete211 connectors

Try it

Prompts to paste into Claude.

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

  1. Readread

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

    callsblumira.findings.list

  2. Writewrite

    Create a webhook endpoint in Blumira. Show me exactly what you will send before you save it.

    callsblumira.webhooks.create

  3. Across systemsread

    Which Blumira companies have invoices in NetSuite, and how many each?

    callsblumira.msp_accounts.listnetsuite.views.invoices

Across your systems

Blumira, joined to the rest of your business.

One ask fetches from Blumira and another system, joins the rows on the same customer on our side, and hands your agent the answer, not every row.

  • Which Blumira companies have invoices in NetSuite, and how many each?

    blumira.msp_accounts.list + netsuite.views.invoices, on crm.company · NetSuite

  • Which Blumira companies have tickets in HubSpot CRM, and how many each?

    blumira.msp_accounts.list + hubspot_crm.tickets.list, on crm.company · HubSpot CRM

Also mapped by other connectorsidentity.user 517crm.company 227device.endpoint 69monitoring.alert 56
ask
ask {  intent: "which Blumira companies have invoices in NetSuite, and how many each",  steps: [    { action: "blumira.msp_accounts.list", as: "co", input: {}, limit: 100, max_pages: 5 },    { action: "netsuite.views.invoices", as: "inv", input: {}, limit: 100, max_pages: 5 },    { join: {        left: "co",        right: "inv",        on: "crm.company",        group_by: "co.name",        select: ["co.name", "count(inv.id) as invoices"]    } }  ]}
Example. Run it through check first: it validates the steps and prices them, and it is free.

Governance for Blumira

Destructive actions wait for a yes.

4 Blumira actions are destructive. These are all of them:

  • Delete a webhook endpointblumira.webhooks.delete
  • Delete a webhook endpoint (MSP parent)blumira.msp_webhooks.delete
  • Rotate a webhook endpoint's signing secretblumira.webhooks.rotate_secret
  • Rotate a webhook endpoint's signing secret (MSP parent)blumira.msp_webhooks.rotate_secret

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.

doblumira.webhooks.deleteconfirm_policy: human

Delete a webhook endpoint?

intent: the user asked me to delete a webhook endpoint

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

Cost

What Blumira costs on actionlake.

Every Blumira action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Blumira 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 59 Blumira actions
  • 59actions pageeach page of a long list is one call
  • 41reads 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 Blumira action.

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

Siem59
  • blumira.agent_action_catalog.listList available response actionsread
  • blumira.agent_commands.getGet a response action command statusread
  • blumira.agent_devices.dispatch_actionDispatch a response action to an agent devicewrite
  • blumira.agent_devices.getGet an agent deviceread
  • blumira.agent_devices.listList agent devicesread
  • blumira.agent_keys.getGet an agent installation keyread
  • blumira.agent_keys.listList agent installation keysread
  • blumira.detection_rules.getGet a detection ruleread
  • blumira.detection_rules.listList detection rulesread
  • blumira.finding_comments.createAdd a comment to a findingwrite
  • blumira.finding_comments.listList comments on a findingread
  • blumira.finding_evidence.getGet evidence for a findingread
  • blumira.findings.assignAssign owners to a findingwrite
  • blumira.findings.getGet a findingread
  • blumira.findings.get_detailsGet a finding's full detailsread
  • blumira.findings.listList findingsread
  • blumira.findings.resolveResolve a findingwrite
  • blumira.health.getGet API healthread
  • blumira.msp_account_agent_commands.getGet a response action command status (sub-account)read
  • blumira.msp_account_agent_devices.dispatch_actionDispatch a response action to an agent device (sub-account)write
  • blumira.msp_account_agent_devices.getGet an agent device (sub-account)read
  • blumira.msp_account_agent_devices.listList agent devices (sub-account)read
  • blumira.msp_account_agent_keys.getGet an agent installation key (sub-account)read
  • blumira.msp_account_agent_keys.listList agent installation keys (sub-account)read
  • blumira.msp_account_detection_rules.getGet a detection rule (sub-account)read
  • blumira.msp_account_detection_rules.listList detection rules (sub-account)read
  • blumira.msp_account_finding_comments.createAdd a comment to a finding (sub-account)write
  • blumira.msp_account_finding_comments.listList comments on a finding (sub-account)read
  • blumira.msp_account_finding_evidence.getGet evidence for a finding (sub-account)read
  • blumira.msp_account_findings.assignAssign owners to a finding (sub-account)write
  • blumira.msp_account_findings.getGet a finding (sub-account)read
  • blumira.msp_account_findings.listList findings (sub-account)read
  • blumira.msp_account_findings.resolveResolve a finding (sub-account)write
  • blumira.msp_account_users.listList users (sub-account)read
  • blumira.msp_accounts.getGet an MSP sub-accountread
  • blumira.msp_accounts.listList MSP sub-accountsread
  • blumira.msp_basis_detection_rules.getGet a basis detection rule (MSP catalogue)read
  • blumira.msp_basis_detection_rules.listList basis detection rules (MSP catalogue)read
  • blumira.msp_findings.listList findings across all MSP sub-accountsread
  • blumira.msp_webhook_deliveries.getGet a webhook delivery (MSP parent)read
  • blumira.msp_webhook_deliveries.listList deliveries for a webhook endpoint (MSP parent)read
  • blumira.msp_webhooks.createCreate a webhook endpoint (MSP parent)write
  • blumira.msp_webhooks.deleteDelete a webhook endpoint (MSP parent)destructive
  • blumira.msp_webhooks.getGet a webhook endpoint (MSP parent)read
  • blumira.msp_webhooks.listList webhook endpoints (MSP parent)read
  • blumira.msp_webhooks.rotate_secretRotate a webhook endpoint's signing secret (MSP parent)destructive
  • blumira.msp_webhooks.testSend a test delivery to a webhook endpoint (MSP parent)write
  • blumira.msp_webhooks.updateUpdate a webhook endpoint (MSP parent)write
  • blumira.resolutions.listList finding resolution optionsread
  • blumira.users.listList usersread
  • blumira.webhook_deliveries.getGet a webhook deliveryread
  • blumira.webhook_deliveries.listList deliveries for a webhook endpointread
  • blumira.webhooks.createCreate a webhook endpointwrite
  • blumira.webhooks.deleteDelete a webhook endpointdestructive
  • blumira.webhooks.getGet a webhook endpointread
  • blumira.webhooks.listList webhook endpointsread
  • blumira.webhooks.rotate_secretRotate a webhook endpoint's signing secretdestructive
  • blumira.webhooks.testSend a test delivery to a webhook endpointwrite
  • blumira.webhooks.updateUpdate a webhook endpointwrite

Questions

The Blumira MCP server, answered.

Is there a Blumira MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 59 Blumira actions, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Blumira.

What do I need to connect Blumira?

Blumira API Client ID and Blumira API Client Secret, shown once when the credential pair is generated. The free call account { op: "connections.requirements", service: "blumira" } lists exactly what to paste.

Can an AI agent delete or change things in Blumira?

Only if its key allows it, and only with an explicit confirmation. 4 Blumira actions are destructive, including delete a webhook endpoint, delete a webhook endpoint (MSP parent) and rotate a webhook endpoint's signing secret. 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 Blumira API limit?

actionlake paces every call to the limits in the Blumira service file: 600 calls a minute per connection. Repeated reads are answered from cache (41 Blumira actions can be), which never reaches Blumira.

What does a Blumira action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (59 Blumira actions page). Cache hits, searches, dry runs and calls Blumira 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 Blumira API does it cover?

The Blumira Public API v1 (OpenAPI 3.0.0) at api.blumira.com/public-api/v1. It is built from Blumira's documentation as read on 23 October 2026. 59 actions in 1 area, each one in the signed service file (version 1.0.0).

Can I combine Blumira with my other systems?

Yes. ask joins Blumira to NetSuite or HubSpot CRM on the same customer and returns the answer rather than every row. Blumira maps crm.company, which 227 other connectors also map.

Does actionlake keep my Blumira 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 Blumira 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 Blumira

Shares the most action names with

Joins with, on shared entities

Browse

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

Give your agent Blumira today.

Connect Blumira freeSee pricing

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