Connectors · Identity & security

UpGuard MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to UpGuard and the rest of your systems. It gives your agent 152 UpGuard actions (97 reads, 43 writes and 12 that wait for a confirmation) and holds the UpGuard credential itself, so the agent never does. It paces UpGuard's limits and records every call.

Connect UpGuard free See 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

152actionsin one signed file
97readlook, never change
43writecreate and update
12wait for a yesdestructive, confirmed first

Set up

Connect UpGuard in three steps.

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
02
Connect UpGuard.
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_keyUpGuard API key
- hostWhere your UpGuard lives: your host
```
account { op: "connections.requirements", service: "upguard" }
# free: exactly what to paste, and what is found for you
```

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

UpGuard 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: 120 calls a minute, per connection
API covered: UpGuard CyberRisk API 1.13.2 (Swagger 2.0, 158 operations)cyber-risk.upguard.com/api/public
Built from: UpGuard's documentation, read 23 October 2026cyber-risk.upguard.com cyber-risk.upguard.com
Service file: Version 1.0.0, signed (Ed25519)
Cached reads: 97 of 97 reads, for up to 5 minutes; a write clears what it affects
Shared entities: 3, so ask can line UpGuard up with your other systems
Data: Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in UpGuard.

152 actions in 76 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

97readlook, never change
43writecreate and update
12destructivewait for a confirmation

Vendors
7
2 read · 4 write · 1 destructive
List monitored vendors · Start monitoring a vendor · Get vendor details · Assign or update the attributes for a vendor
Bulk hostnames
6
3 read · 2 write · 1 destructive
List hostnames and their risks · Register a list of hostnames to be scanned for risks · Get the details for a hostname · Assign new labels to a hostname
Threats
6
3 read · 3 write · 0 destructive
List threats · Update threat's investigator · Close threat · Count threats
Vendor questionnaires
6
4 read · 2 write · 0 destructive
List vendor questionnaires · List vendor questionnaires · Send a security questionnaire to a vendor · Get questionnaire questions and answers
Content library documents
5
2 read · 2 write · 1 destructive
List content library documents · Archive content library document · Get content library document · Update content library document
Domains
5
2 read · 2 write · 1 destructive
Add custom domains · Get a list of domains · Retrieve details for a domain · Assign labels to a domain
Ips
5
2 read · 2 write · 1 destructive
Add custom ips · Get a list of ips · Retrieve details for an IP address · Assign labels to an IP
Vendor contacts
5
2 read · 2 write · 1 destructive
List vendor contacts · Create a vendor contact · Get a vendor contact by ID · Delete a vendor contact

68 more areas · 107 actions

Vendor risks 5
Trust center access 4
Webhooks 4
Available risks 3
Subsidiary domains 3
Subsidiary ips 3
Trust center subscriptions 3
Trust center updates 3
Vendor domains 3
Vendor ips 3
Vips 3
Breaches 2
Dataleak disclosures 2
Onboarding requests 2
Reports 2
Risks 2
Threat remediation requests 2
Trust center access requests 2
Trust center nda 2
Trust centers 2
Typosquat domains 2
Vendor assessments 2
Vendor questionnaire comments 2
Vendor questionnaire risks 2
Content library document history 1
Content library types 1
Custom reports 1
Fourth parties 1
Labels 1
Notifications 1
Organisation 1
Questionnaires 1
Ranges 1
Subsidiaries 1
Subsidiary ranges 1
Threat comments 1
Trust center access log 1
Trust exchange questionnaires 1
User risk app categories 1
User risk app permissions 1
User risk app usage policies 1
User risk app users 1
User risk apps 1
User risk default usage policy 1
User risk identity breach users 1
User risk identity breaches 1
User risk permission apps 1
User risk permission users 1
User risk permissions 1
User risk roles 1
User risk teams 1
User risk user apps 1
User risk user identity breaches 1
User risk user permissions 1
User risk users 1
Vendor additional evidence 1
Vendor assessment versions 1
Vendor documents 1
Vendor questionnaire attachments 1
Vendor questionnaire collaborators 1
Vendor questionnaire recipients 1
Vendor questionnaire types 1
Vendor ranges 1
Vendor relationship questionnaires 1
Vendor risk diffs 1
Vendor vulnerabilities 1
Vulnerabilities 1
Webhook notification types 1

Top actions

The UpGuard API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 14 of UpGuard's 15 action names are shared with at least one other connector, so an agent learns them once.

Action	What it does	Effect	Same name in
`upguard.vendor_contacts.list`List vendor contacts	List vendor contacts.	read	`crm.contact.list`177 connectors
`upguard.vendors.list`List monitored vendors	List monitored vendors.	read	`crm.company.list`162 connectors
`upguard.user_risk_users.list`List users	List users.	read	`identity.user.list`474 connectors
`upguard.vendor_contacts.create`Create a vendor contact	Create a vendor contact.	write	`crm.contact.create`161 connectors
`upguard.vendor_contacts.delete`Delete a vendor contact	Delete a vendor contact.	destructive	`crm.contact.delete`147 connectors
`upguard.vulnerabilities.list`List potential vulnerabilities of your domains & IPs	List potential vulnerabilities of your domains & IPs.	read	`security.vulnerability.list`14 connectors
`upguard.webhooks.create`Create a new webhook	Create a new webhook.	write	`automation.webhook.create`209 connectors
`upguard.webhooks.list`List webhooks	List webhooks.	read	`automation.webhook.list`202 connectors
`upguard.threats.list`List threats	List threats.	read	`security.threat.list`7 connectors
`upguard.webhook_notification_types.list`Webhook notification types	Webhook notification types.	read	`automation.webhook_event_type.list`18 connectors
`upguard.risks.list`Get a list of active risks for your account	Get a list of active risks for your account.	read	`security.risk.list`4 connectors
`upguard.ips.add`Add custom ips	Add custom ips.	write	this connector

Try it

Prompts to paste into Claude.

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

Readread
Find the UpGuard contacts with no email address, so we can clean them up.
callsupguard.vendor_contacts.list
Writewrite
Create a vendor contact in UpGuard. Show me exactly what you will send before you save it.
callsupguard.vendor_contacts.create
Across systemsread
Which UpGuard companies have invoices in ConnectWise PSA, and how many each?
callsupguard.vendors.listconnectwise_manage.invoices.list

Across your systems

UpGuard, joined to the rest of your business.

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

Which UpGuard companies have invoices in ConnectWise PSA, and how many each?
upguard.vendors.list + connectwise_manage.invoices.list, on crm.company · ConnectWise PSA
Which UpGuard companies have invoices in NetSuite, and how many each?
upguard.vendors.list + netsuite.views.invoices, on crm.company · NetSuite

Also mapped by other connectorsidentity.user 517crm.company 227crm.contact 192

ask

ask {  intent: "which UpGuard companies have invoices in ConnectWise PSA, and how many each",  steps: [    { action: "upguard.vendors.list", as: "co", input: {}, limit: 100, max_pages: 5 },    { action: "connectwise_manage.invoices.list", 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 UpGuard

Destructive actions wait for a yes.

12 UpGuard actions are destructive. These are all of them:

Delete a vendor contactupguard.vendor_contacts.delete
Delete a webhookupguard.webhooks.delete
Remove custom ipsupguard.ips.remove
Remove a VIPupguard.vips.delete
Remove custom domainsupguard.domains.remove
Stop monitoring a vendorupguard.vendors.unmonitor
Revoke a user's NDAupguard.trust_center_nda.revoke
Deregister a list of hostnamesupguard.bulk_hostnames.deregister
Revoke Trust Center accessupguard.trust_center_access.revoke
Delete Trust Center updateupguard.trust_center_updates.delete
Delete content library documentupguard.content_library_documents.delete
Remove Trust Center subscribersupguard.trust_center_subscriptions.remove

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.

doupguard.vendor_contacts.deleteconfirm_policy: human

Delete a vendor contact?

intent: the user asked me to delete a vendor contact

run suspended · waiting for a named person · key upguard-agent cannot confirm itself

In the console, or from an emailed signed link.

a key for this connector

account {  op: "keys.create", name: "upguard-agent",  allowed_actions: ["upguard.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "upguard.vendor_contacts.delete", approver: "[email protected]" },    { match: "upguard.webhooks.delete", approver: "[email protected]" },    { match: "upguard.ips.remove", approver: "[email protected]" }  ]}

Illustrative. Scoped to UpGuard only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What UpGuard costs on actionlake.

Every UpGuard action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call UpGuard 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 152 UpGuard actions
152actions pageeach page of a long list is one call
97reads 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 UpGuard action.

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

Vendors7

upguard.vendors.getGet vendor detailsread
upguard.vendors.listList monitored vendorsread
upguard.vendors.monitorStart monitoring a vendorwrite
upguard.vendors.unmonitorStop monitoring a vendordestructive
upguard.vendors.update_attributesAssign or update the attributes for a vendorwrite
upguard.vendors.update_labelsAssign labels to a vendorwrite
upguard.vendors.update_tierAssign tier to a vendorwrite

Bulk hostnames6

upguard.bulk_hostnames.deregisterDeregister a list of hostnamesdestructive
upguard.bulk_hostnames.getGet the details for a hostnameread
upguard.bulk_hostnames.listList hostnames and their risksread
upguard.bulk_hostnames.registerRegister a list of hostnames to be scanned for riskswrite
upguard.bulk_hostnames.set_labelsAssign new labels to a hostnamewrite
upguard.bulk_hostnames.statsGet statistics around registered bulk hostnamesread

Threats6

upguard.threats.assign_investigatorUpdate threat's investigatorwrite
upguard.threats.closeClose threatwrite
upguard.threats.countCount threatsread
upguard.threats.getGet threat detailsread
upguard.threats.listList threatsread
upguard.threats.reopenReopen threatwrite

Vendor questionnaires6

upguard.vendor_questionnaires.answersGet questionnaire questions and answersread
upguard.vendor_questionnaires.getGet questionnaire metadataread
upguard.vendor_questionnaires.listList vendor questionnairesread
upguard.vendor_questionnaires.list_v2List vendor questionnairesread
upguard.vendor_questionnaires.sendSend a security questionnaire to a vendorwrite
upguard.vendor_questionnaires.update_statusUpdate questionnaire statuswrite

Content library documents5

upguard.content_library_documents.archiveArchive content library documentwrite
upguard.content_library_documents.deleteDelete content library documentdestructive
upguard.content_library_documents.getGet content library documentread
upguard.content_library_documents.listList content library documentsread
upguard.content_library_documents.updateUpdate content library documentwrite

Domains5

upguard.domains.addAdd custom domainswrite
upguard.domains.getRetrieve details for a domainread
upguard.domains.listGet a list of domainsread
upguard.domains.removeRemove custom domainsdestructive
upguard.domains.update_labelsAssign labels to a domainwrite

Ips5

upguard.ips.addAdd custom ipswrite
upguard.ips.getRetrieve details for an IP addressread
upguard.ips.listGet a list of ipsread
upguard.ips.removeRemove custom ipsdestructive
upguard.ips.update_labelsAssign labels to an IPwrite

Vendor contacts5

upguard.vendor_contacts.createCreate a vendor contactwrite
upguard.vendor_contacts.deleteDelete a vendor contactdestructive
upguard.vendor_contacts.getGet a vendor contact by IDread
upguard.vendor_contacts.listList vendor contactsread
upguard.vendor_contacts.updateUpdate a vendor contactwrite

Vendor risks5

upguard.vendor_risks.diffGet a list of risk changes for a vendorread
upguard.vendor_risks.hostnamesGet vendor hostnames affected by a riskread
upguard.vendor_risks.listGet a list of active risks for a vendorread
upguard.vendor_risks.list_allGet portfolio risk profile overviewread
upguard.vendor_risks.vendors_with_riskGet vendors affected by a riskread

Trust center access4

upguard.trust_center_access.get_userGet Trust Center access for a userread
upguard.trust_center_access.listGet Trust Center accessread
upguard.trust_center_access.revokeRevoke Trust Center accessdestructive
upguard.trust_center_access.setSet Trust Center accesswrite

Webhooks4

upguard.webhooks.createCreate a new webhookwrite
upguard.webhooks.deleteDelete a webhookdestructive
upguard.webhooks.listList webhooksread
upguard.webhooks.sampleWebhook example dataread

Available risks3

upguard.available_risks.getGet details for a risk in the platformread
upguard.available_risks.listGet a list of available risks in the platformread
upguard.available_risks.list_v2Get a list of available risks in the platformread

Subsidiary domains3

upguard.subsidiary_domains.getRetrieve details for a domainread
upguard.subsidiary_domains.listList subsidiary domainsread
upguard.subsidiary_domains.update_labelsAssign labels to a domainwrite

Subsidiary ips3

upguard.subsidiary_ips.getRetrieve details for an IP addressread
upguard.subsidiary_ips.listList subdiary ipsread
upguard.subsidiary_ips.update_labelsAssign labels to an IPwrite

Trust center subscriptions3

upguard.trust_center_subscriptions.addAdd Trust Center subscriberswrite
upguard.trust_center_subscriptions.listGet Trust Center subscriptionsread
upguard.trust_center_subscriptions.removeRemove Trust Center subscribersdestructive

Trust center updates3

upguard.trust_center_updates.addAdd Trust Center updatewrite
upguard.trust_center_updates.deleteDelete Trust Center updatedestructive
upguard.trust_center_updates.editEdit Trust Center updatewrite

Vendor domains3

upguard.vendor_domains.getRetrieve details for a domainread
upguard.vendor_domains.listList vendor domainsread
upguard.vendor_domains.update_labelsAssign labels to a domainwrite

Vendor ips3

upguard.vendor_ips.getRetrieve details for an IP addressread
upguard.vendor_ips.listList vendor ipsread
upguard.vendor_ips.update_labelsAssign labels to an IPwrite

Vips3

upguard.vips.addAdd a VIPwrite
upguard.vips.deleteRemove a VIPdestructive
upguard.vips.listGet a list of VIPsread

Breaches2

upguard.breaches.getGet the details for an identity breachread
upguard.breaches.listGet a list of breached identitiesread

Dataleak disclosures2

upguard.dataleak_disclosures.listGet a list of disclosuresread
upguard.dataleak_disclosures.update_statusUpdate the status of a disclosurewrite

Onboarding requests2

upguard.onboarding_requests.getGet onboarding request detailsread
upguard.onboarding_requests.listList onboarding requestsread

Reports2

upguard.reports.queueQueue a report exportwrite
upguard.reports.statusGet the status of an exported reportread

Risks2

upguard.risks.diffGet a list of risk changes for your accountread
upguard.risks.listGet a list of active risks for your accountread

Threat remediation requests2

upguard.threat_remediation_requests.addAdd remediation request to threatwrite
upguard.threat_remediation_requests.closeClose threat's remediation requestwrite

Trust center access requests2

upguard.trust_center_access_requests.approveApprove Trust Center access requestwrite
upguard.trust_center_access_requests.rejectReject Trust Center access requestwrite

Trust center nda2

upguard.trust_center_nda.approveManually approve a user's NDAwrite
upguard.trust_center_nda.revokeRevoke a user's NDAdestructive

Trust centers2

upguard.trust_centers.getGet Trust Centerread
upguard.trust_centers.listList Trust Centersread

Typosquat domains2

upguard.typosquat_domains.getRetrieve typosquat details for a domain.read
upguard.typosquat_domains.listList typosquat domainsread

Vendor assessments2

upguard.vendor_assessments.getGet vendor assessment detailsread
upguard.vendor_assessments.listList vendor assessmentsread

Vendor questionnaire comments2

upguard.vendor_questionnaire_comments.addCreate a comment on a questionnairewrite
upguard.vendor_questionnaire_comments.listGet questionnaire commentsread

Vendor questionnaire risks2

upguard.vendor_questionnaire_risks.listGet a list of questionnaire risks for one or more watched vendors or a specific questionnaireread
upguard.vendor_questionnaire_risks.list_v2(V2) Get a list of questionnaire risks for one or more watched vendors or a specific questionnaireread

Content library document history1

upguard.content_library_document_history.listGet content library document historyread

Content library types1

upguard.content_library_types.listList content library document typesread

Custom reports1

upguard.custom_reports.listGet the list of custom report templates defined for the accountread

Fourth parties1

upguard.fourth_parties.listList fourth party vendorsread

Labels1

upguard.labels.listGet the list of registered labelsread

Notifications1

upguard.notifications.listGet a list of notifications for your organization.read

Organisation1

upguard.organisation.getGet the current organisationread

Questionnaires1

upguard.questionnaires.list_allList all questionnairesread

Ranges1

upguard.ranges.listGet a list of ip rangesread

Subsidiaries1

upguard.subsidiaries.listGet a list of subsidiariesread

Subsidiary ranges1

upguard.subsidiary_ranges.listList subsidiary ip rangesread

Threat comments1

upguard.threat_comments.addAdd comment to threatwrite

Trust center access log1

upguard.trust_center_access_log.listGet Trust Center access logread

Trust exchange questionnaires1

upguard.trust_exchange_questionnaires.listList inbound questionnairesread

User risk app categories1

upguard.user_risk_app_categories.listList app categoriesread

User risk app permissions1

upguard.user_risk_app_permissions.listList app permissionsread

User risk app usage policies1

upguard.user_risk_app_usage_policies.updateUpdate app usage policywrite

User risk app users1

upguard.user_risk_app_users.listList app usersread

User risk apps1

upguard.user_risk_apps.listList appsread

User risk default usage policy1

upguard.user_risk_default_usage_policy.updateUpdate default usage policywrite

User risk identity breach users1

upguard.user_risk_identity_breach_users.listList identity breach usersread

User risk identity breaches1

upguard.user_risk_identity_breaches.listList identity breachesread

User risk permission apps1

upguard.user_risk_permission_apps.listList permission appsread

User risk permission users1

upguard.user_risk_permission_users.listList permission usersread

User risk permissions1

upguard.user_risk_permissions.listList permissionsread

User risk roles1

upguard.user_risk_roles.listList rolesread

User risk teams1

upguard.user_risk_teams.listList teamsread

User risk user apps1

upguard.user_risk_user_apps.listList a user appsread

User risk user identity breaches1

upguard.user_risk_user_identity_breaches.listList a user identity breachesread

User risk user permissions1

upguard.user_risk_user_permissions.listList a user permissionsread

User risk users1

upguard.user_risk_users.listList usersread

Vendor additional evidence1

upguard.vendor_additional_evidence.listList vendor additional evidence instancesread

Vendor assessment versions1

upguard.vendor_assessment_versions.listList vendor assessment versionsread

Vendor documents1

upguard.vendor_documents.listList vendor documentsread

Vendor questionnaire attachments1

upguard.vendor_questionnaire_attachments.listList vendor questionnaire attachmentsread

Vendor questionnaire collaborators1

upguard.vendor_questionnaire_collaborators.addAdd collaborators to a questionnairewrite

Vendor questionnaire recipients1

upguard.vendor_questionnaire_recipients.addAdd recipients to a questionnairewrite

Vendor questionnaire types1

upguard.vendor_questionnaire_types.listList available vendor questionnaire typesread

Vendor ranges1

upguard.vendor_ranges.listList vendor ip rangesread

Vendor relationship questionnaires1

upguard.vendor_relationship_questionnaires.sendSend a relationship questionnaire about a vendorwrite

Vendor risk diffs1

upguard.vendor_risk_diffs.listGet a list of risk changes for monitored vendorsread

Vendor vulnerabilities1

upguard.vendor_vulnerabilities.listList potential vulnerabilities of a vendorread

Vulnerabilities1

upguard.vulnerabilities.listList potential vulnerabilities of your domains & IPsread

Webhook notification types1

upguard.webhook_notification_types.listWebhook notification typesread

Questions

The UpGuard MCP server, answered.

Is there an UpGuard MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 152 UpGuard actions across vendors, bulk hostnames, threats and vendor questionnaires, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by UpGuard.

What do I need to connect UpGuard?

UpGuard API key. Plus your host. The free call account { op: "connections.requirements", service: "upguard" } lists exactly what to paste.

Can an AI agent delete or change things in UpGuard?

Only if its key allows it, and only with an explicit confirmation. 12 UpGuard actions are destructive, including delete a vendor contact, delete a webhook and remove custom ips. 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 UpGuard API limit?

actionlake paces every call to the limits in the UpGuard service file: 120 calls a minute per connection. Repeated reads are answered from cache (97 UpGuard actions can be), which never reaches UpGuard.

What does an UpGuard action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (152 UpGuard actions page). Cache hits, searches, dry runs and calls UpGuard 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 UpGuard API does it cover?

The UpGuard CyberRisk API 1.13.2 (Swagger 2.0, 158 operations) at cyber-risk.upguard.com/api/public by default, or the base URL set when you connect. It is built from UpGuard's documentation as read on 23 October 2026. 152 actions in 76 areas, each one in the signed service file (version 1.0.0).

Can I combine UpGuard with my other systems?

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

Does actionlake keep my UpGuard 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 UpGuard 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.

Give your agent UpGuard today.

Connect UpGuard free See pricing

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

UpGuard MCP server for AI agents.

Connect UpGuard in three steps.

Add actionlake to Claude.

Connect UpGuard.

Make the first call. Check before a write.

What an AI agent can do in UpGuard.

Vendors

Bulk hostnames

Threats

Vendor questionnaires

Content library documents

Domains

Ips

Vendor contacts