Connectors · AI

Azure AI Document Intelligence MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Azure AI Document Intelligence and the rest of your systems. It gives your agent 23 Azure AI Document Intelligence actions (11 reads, 8 writes and 4 that wait for a confirmation) and holds the Azure AI Document Intelligence credential itself, so the agent never does. It paces Azure AI Document Intelligence's limits and records every call.

Connect Azure AI Document Intelligence 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

the first call

do {  action: "azure_document_intelligence.document_models.list",  intent: "check which Azure AI Document Intelligence account is connected"}# List all document models · read · 1 upstream call

23actionsin one signed file
11readlook, never change
8writecreate and update
4wait for a yesdestructive, confirmed first

Set up

Connect Azure AI Document Intelligence 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 Azure AI Document Intelligence.
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_keyDocument Intelligence resource key (KEY 1 or KEY 2)
- hostWhere your Azure AI Document Intelligence lives: your host
```
account { op: "connections.requirements", service: "azure_document_intelligence" }
# 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: "azure_document_intelligence.document_models.list" }# list all document models · read · 1 upstream callcheck { action: "azure_document_intelligence.document_models.build", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Azure AI Document Intelligence 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: 15 calls a second, per connection
API covered: Azure AI Document Intelligence API 2024-11-30, at your Azure AI Document Intelligence instance's API base URL, which you enter when connecting (path /documentintelligence)
Built from: Azure AI Document Intelligence's documentation, read 23 October 2026OpenAPI spec (GitHub)learn.microsoft.com
Service file: Version 1.0.0, signed (Ed25519)
Cached reads: 11 of 11 reads, for up to an hour; a write clears what it affects
Shared entities: 2, so ask can line Azure AI Document Intelligence up with your other systems
Data: Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Azure AI Document Intelligence.

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

11readlook, never change
8writecreate and update
4destructivewait for a confirmation

Document processing
23
11 read · 8 write · 4 destructive
List all document models · Lists all operations · List batch document analysis results · Analyzes batch documents with document model

Top actions

The Azure AI Document Intelligence API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems.

Action	What it does	Effect	Same name in
`azure_document_intelligence.operations.list`Lists all operations	Lists all operations.	read	this connector
`azure_document_intelligence.document_models.list`List all document models	List all document models.	read	this connector
`azure_document_intelligence.document_models.build`Builds a custom document analysis model	Builds a custom document analysis model.	write	this connector
`azure_document_intelligence.document_models.compose`Creates a new document model from document types of existing document models	Creates a new document model from document types of existing document models.	write	this connector
`azure_document_intelligence.analyze_batch_results.list`List batch document analysis results	List batch document analysis results.	read	this connector
`azure_document_intelligence.operations.get`Gets operation info	Gets operation info.	read	this connector
`azure_document_intelligence.resource.get_details`Return information about the current resource	Return information about the current resource.	read	this connector
`azure_document_intelligence.analyze_batch_results.get`Gets the result of batch document analysis	Gets the result of batch document analysis.	read	this connector
`azure_document_intelligence.document_classifiers.list`List all document classifiers	List all document classifiers.	read	this connector
`azure_document_intelligence.document_classifiers.build`Builds a custom document classifier	Builds a custom document classifier.	write	this connector
`azure_document_intelligence.analyze_results.get`Gets the result of document analysis	Gets the result of document analysis.	read	this connector
`azure_document_intelligence.analyze_results.delete`Mark the result of document analysis for deletion	Mark the result of document analysis for deletion.	destructive	this connector

Try it

Prompts to paste into Claude.

Each one names the Azure AI Document Intelligence actions it will call, so you know what it reads and what it changes before you send it.

Readread
List all document models in Azure AI Document Intelligence and tell me what stands out.
callsazure_document_intelligence.document_models.list
Writewrite
Builds a custom document analysis model in Azure AI Document Intelligence. Show me exactly what you will send before you save it.
callsazure_document_intelligence.document_models.build

Governance for Azure AI Document Intelligence

Destructive actions wait for a yes.

4 Azure AI Document Intelligence actions are destructive. These are all of them:

Deletes document modelazure_document_intelligence.document_models.delete
Mark the batch document analysis result for deletionazure_document_intelligence.analyze_batch_results.delete
Mark the result of document analysis for deletionazure_document_intelligence.analyze_results.delete
Deletes document classifierazure_document_intelligence.document_classifiers.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.

doazure_document_intelligence.document_models.deleteconfirm_policy: human

Deletes document model?

intent: the user asked me to deletes document model

run suspended · waiting for a named person · key azure-document-intelligence-agent cannot confirm itself

In the console, or from an emailed signed link.

a key for this connector

account {  op: "keys.create", name: "azure-document-intelligence-agent",  allowed_actions: ["azure_document_intelligence.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "azure_document_intelligence.document_models.delete", approver: "[email protected]" },    { match: "azure_document_intelligence.analyze_batch_results.delete", approver: "[email protected]" },    { match: "azure_document_intelligence.analyze_results.delete", approver: "[email protected]" }  ]}

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

Cost

What Azure AI Document Intelligence costs on actionlake.

Every Azure AI Document Intelligence action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Azure AI Document Intelligence 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 23 Azure AI Document Intelligence actions
23actions pageeach page of a long list is one call
11reads 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 Azure AI Document Intelligence action.

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

Document processing23

azure_document_intelligence.analyze_batch_results.deleteMark the batch document analysis result for deletiondestructive
azure_document_intelligence.analyze_batch_results.getGets the result of batch document analysisread
azure_document_intelligence.analyze_batch_results.listList batch document analysis resultsread
azure_document_intelligence.analyze_results.deleteMark the result of document analysis for deletiondestructive
azure_document_intelligence.analyze_results.getGets the result of document analysisread
azure_document_intelligence.classify_results.getGets the result of document classifierread
azure_document_intelligence.document_classifiers.authorize_copydocument classifiers authorize copywrite
azure_document_intelligence.document_classifiers.buildBuilds a custom document classifierwrite
azure_document_intelligence.document_classifiers.copy_toCopies document classifier to the target resource, region, and classifierIdwrite
azure_document_intelligence.document_classifiers.deleteDeletes document classifierdestructive
azure_document_intelligence.document_classifiers.getGets detailed document classifier informationread
azure_document_intelligence.document_classifiers.listList all document classifiersread
azure_document_intelligence.document_models.analyze_batchAnalyzes batch documents with document modelwrite
azure_document_intelligence.document_models.authorize_copydocument models authorize copywrite
azure_document_intelligence.document_models.buildBuilds a custom document analysis modelwrite
azure_document_intelligence.document_models.composeCreates a new document model from document types of existing document modelswrite
azure_document_intelligence.document_models.copy_toCopies document model to the target resource, region, and modelIdwrite
azure_document_intelligence.document_models.deleteDeletes document modeldestructive
azure_document_intelligence.document_models.getGets detailed document model informationread
azure_document_intelligence.document_models.listList all document modelsread
azure_document_intelligence.operations.getGets operation inforead
azure_document_intelligence.operations.listLists all operationsread
azure_document_intelligence.resource.get_detailsReturn information about the current resourceread

Questions

The Azure AI Document Intelligence MCP server, answered.

Is there an Azure AI Document Intelligence MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 23 Azure AI Document Intelligence actions, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Azure AI Document Intelligence.

What do I need to connect Azure AI Document Intelligence?

Document Intelligence resource key (KEY 1 or KEY 2). Plus your host. The free call account { op: "connections.requirements", service: "azure_document_intelligence" } lists exactly what to paste.

Can an AI agent delete or change things in Azure AI Document Intelligence?

Only if its key allows it, and only with an explicit confirmation. 4 Azure AI Document Intelligence actions are destructive, including deletes document model, mark the batch document analysis result for deletion and mark the result of document analysis for deletion. 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 Azure AI Document Intelligence API limit?

actionlake paces every call to the limits in the Azure AI Document Intelligence service file: 15 calls a second per connection. Repeated reads are answered from cache (11 Azure AI Document Intelligence actions can be), which never reaches Azure AI Document Intelligence.

What does an Azure AI Document Intelligence action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (23 Azure AI Document Intelligence actions page). Cache hits, searches, dry runs and calls Azure AI Document Intelligence 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 Azure AI Document Intelligence API does it cover?

The Azure AI Document Intelligence API 2024-11-30 at your Azure AI Document Intelligence instance's API base URL, which you enter when connecting (path /documentintelligence). It is built from Azure AI Document Intelligence's documentation as read on 23 October 2026. 23 actions in 1 area, each one in the signed service file (version 1.0.0).

Does actionlake keep my Azure AI Document Intelligence data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to an hour, 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 Azure AI Document Intelligence 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 Azure AI Document Intelligence today.