Connectors · AI

LlamaCloud MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to LlamaCloud and the rest of your systems. It gives your agent 199 LlamaCloud actions (117 reads, 48 writes and 34 that wait for a confirmation) and holds the LlamaCloud credential itself, so the agent never does. It paces LlamaCloud's limits and records every call.

Connect LlamaCloud 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

199actionsin one signed file
117readlook, never change
48writecreate and update
34wait for a yesdestructive, confirmed first

Set up

Connect LlamaCloud 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 LlamaCloud.
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.
- access_tokenLlamaCloud API key (llx-...)
- hostWhere your LlamaCloud lives: your host
```
account { op: "connections.requirements", service: "llamacloud" }
# 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: "llamacloud.files.list" }# list files · read · 1 upstream callcheck { action: "llamacloud.directories.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

LlamaCloud 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: access_token
Setup fields: host
Limits we pace to: 300 calls a minute, per connection
API covered: Llama Platform API 0.1.0 (OpenAPI 3.1.0)api.cloud.llamaindex.ai
Built from: LlamaCloud's documentation, read 23 October 2026api.cloud.llamaindex.ai developers.llamaindex.ai
Service file: Version 1.0.0, signed (Ed25519)
Cached reads: 46 of 117 reads, for up to 5 minutes; a write clears what it affects
Shared entities: 4, so ask can line LlamaCloud up with your other systems
Data: Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in LlamaCloud.

199 actions in 39 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

117readlook, never change
48writecreate and update
34destructivewait for a confirmation

Pipelines
15
7 read · 5 write · 3 destructive
Chat · List Pipelines · Run Search · Search Pipelines
Extraction agents
10
7 read · 2 write · 1 destructive
Generate Extraction Schema · List Extract Agents · List Extraction Agents · Validate Extraction Schema
Pipeline documents
9
5 read · 3 write · 1 destructive
List Pipeline Documents · Paginated List Pipeline Documents · Get Pipeline Document · Get Pipeline Document Status
Retrievers
9
5 read · 3 write · 1 destructive
List Retrievers · Query Retrievers · Retrieve · Direct Retrieve
Parsing jobs
8
8 read · 0 write · 0 destructive
Get Job · Get Parsing Job Details · Generate Presigned Url · Get Job Json Result
Split jobs
8
4 read · 2 write · 2 destructive
List Split Jobs · List Split Jobs · Get Split Job · Get Split Job
Agent data
7
3 read · 2 write · 2 destructive
Aggregate Agent Data · Search Agent Data · Get Agent Data · Create Agent Data
Extract
7
4 read · 1 write · 2 destructive
Generate Extraction Schema · List Extract Jobs · Validate Extraction Schema · Get Extract Job

31 more areas · 126 actions

Pipeline files 7
Data sinks 6
Directory files 6
Indexes 6
Parse 6
Webhook configs 6
Chat sessions 5
Classify 5
Configurations 5
Data sources 5
Directories 5
Extraction jobs 5
Extraction runs 5
Files 5
Pipeline data sources 5
Verify 5
Batch processing 4
Batches 4
Embedding model configs 4
Organizations 4
Projects 4
Retrieval 4
File page figures 3
Attachments 2
Batch processing items 2
File page screenshots 2
Usage metrics 2
Extraction 1
Parsing 1
Pipeline document chunks 1
Pipeline files metadata 1

Top actions

The LlamaCloud API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 12 of LlamaCloud's 12 action names are shared with at least one other connector, so an agent learns them once.

Action	What it does	Effect	Same name in
`llamacloud.files.list`List Files	List files with optional filtering and pagination.	read	`content.file.list`77 connectors
`llamacloud.directories.list`List Directories	List Directories.	read	`content.folder.list`62 connectors
`llamacloud.projects.list`List Projects	List projects in an organization.	read	`work.project.list`109 connectors
`llamacloud.files.get`Get File	Get file metadata by ID.	read	`content.file.get`74 connectors
`llamacloud.directories.get`Get Directory	Retrieve a directory by its identifier.	read	`content.folder.get`47 connectors
`llamacloud.projects.get`Get Project	Get a project by ID.	read	`work.project.get`106 connectors
`llamacloud.directories.create`Create Directory	Create a new directory within the specified project.	write	`content.folder.create`62 connectors
`llamacloud.directories.update`Update Directory	Update directory metadata.	write	`content.folder.update`48 connectors
`llamacloud.files.delete`Delete File	Delete a file from the project.	destructive	`content.file.delete`68 connectors
`llamacloud.organizations.list`List Organizations	List organizations the current user can access.	read	`platform.tenant.list`70 connectors
`llamacloud.organizations.get`Get Organization	Get an organization by ID.	read	`platform.tenant.get`86 connectors
`llamacloud.parse.create`Parse File	Parse a file by file ID or URL.	write	this connector

Try it

Prompts to paste into Claude.

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

Readread
Give me a one-line status for every active LlamaCloud project.
callsllamacloud.projects.list
Writewrite
Create Directory in LlamaCloud. Show me exactly what you will send before you save it.
callsllamacloud.directories.create

Governance for LlamaCloud

Destructive actions wait for a yes.

34 LlamaCloud actions are destructive. The first 10:

Delete Filellamacloud.files.delete
Delete Directoryllamacloud.directories.delete
Delete Parse Jobllamacloud.parse.delete
Delete Extract Jobllamacloud.extract.delete
Delete Indexllamacloud.indexes.delete
Delete Classify Jobllamacloud.classify.delete
Delete Pipelinellamacloud.pipelines.delete
Delete Agent Datallamacloud.agent_data.delete
Delete Data Sinkllamacloud.data_sinks.delete
Delete Retrieverllamacloud.retrievers.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.

dollamacloud.files.deleteconfirm_policy: human

Delete File?

intent: the user asked me to delete File

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

In the console, or from an emailed signed link.

a key for this connector

account {  op: "keys.create", name: "llamacloud-agent",  allowed_actions: ["llamacloud.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "llamacloud.files.delete", approver: "[email protected]" },    { match: "llamacloud.directories.delete", approver: "[email protected]" },    { match: "llamacloud.parse.delete", approver: "[email protected]" }  ]}

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

Cost

What LlamaCloud costs on actionlake.

Every LlamaCloud action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call LlamaCloud 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 199 LlamaCloud actions
199actions pageeach page of a long list is one call
46reads 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 LlamaCloud action.

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

Pipelines15

llamacloud.pipelines.cancel_syncCancel Pipeline Syncdestructive
llamacloud.pipelines.chatChatread
llamacloud.pipelines.copyCopy Pipelinewrite
llamacloud.pipelines.createCreate Pipelinewrite
llamacloud.pipelines.deleteDelete Pipelinedestructive
llamacloud.pipelines.force_deleteForce Delete Pipelinedestructive
llamacloud.pipelines.getGet Pipelineread
llamacloud.pipelines.get_playground_sessionGet Playground Sessionread
llamacloud.pipelines.get_statusGet Pipeline Statusread
llamacloud.pipelines.listList Pipelinesread
llamacloud.pipelines.retrieveRun Searchread
llamacloud.pipelines.searchSearch Pipelinesread
llamacloud.pipelines.syncSync Pipelinewrite
llamacloud.pipelines.updateUpdate Existing Pipelinewrite
llamacloud.pipelines.upsertUpsert Pipelinewrite

Extraction agents10

llamacloud.extraction_agents.createCreate Extraction Agentwrite
llamacloud.extraction_agents.deleteDelete Extraction Agentdestructive
llamacloud.extraction_agents.generate_schemaGenerate Extraction Schemaread
llamacloud.extraction_agents.getGet Extraction Agentread
llamacloud.extraction_agents.get_by_nameGet Extraction Agent By Nameread
llamacloud.extraction_agents.get_defaultGet Or Create Default Extraction Agentread
llamacloud.extraction_agents.listList Extract Agentsread
llamacloud.extraction_agents.list_v1List Extraction Agentsread
llamacloud.extraction_agents.updateUpdate Extraction Agentwrite
llamacloud.extraction_agents.validate_schemaValidate Extraction Schemaread

Pipeline documents9

llamacloud.pipeline_documents.create_batchCreate Batch Pipeline Documentswrite
llamacloud.pipeline_documents.deleteDelete Pipeline Documentdestructive
llamacloud.pipeline_documents.getGet Pipeline Documentread
llamacloud.pipeline_documents.get_statusGet Pipeline Document Statusread
llamacloud.pipeline_documents.get_status_countsGet Pipeline Document Status Countsread
llamacloud.pipeline_documents.listList Pipeline Documentsread
llamacloud.pipeline_documents.list_paginatedPaginated List Pipeline Documentsread
llamacloud.pipeline_documents.syncSync Pipeline Documentwrite
llamacloud.pipeline_documents.upsert_batchUpsert Batch Pipeline Documentswrite

Retrievers9

llamacloud.retrievers.createCreate Retrieverwrite
llamacloud.retrievers.deleteDelete Retrieverdestructive
llamacloud.retrievers.getGet Retrieverread
llamacloud.retrievers.listList Retrieversread
llamacloud.retrievers.queryQuery Retrieversread
llamacloud.retrievers.retrieveRetrieveread
llamacloud.retrievers.retrieve_directDirect Retrieveread
llamacloud.retrievers.updateUpdate Retrieverwrite
llamacloud.retrievers.upsertUpsert Retrieverwrite

Parsing jobs8

llamacloud.parsing_jobs.getGet Jobread
llamacloud.parsing_jobs.get_detailsGet Parsing Job Detailsread
llamacloud.parsing_jobs.get_file_urlGenerate Presigned Urlread
llamacloud.parsing_jobs.get_json_resultGet Job Json Resultread
llamacloud.parsing_jobs.get_markdown_resultGet Job Resultread
llamacloud.parsing_jobs.get_parametersGet Job Parametersread
llamacloud.parsing_jobs.get_structured_resultGet Job Structured Resultread
llamacloud.parsing_jobs.get_text_resultGet Job Text Resultread

Split jobs8

llamacloud.split_jobs.cancelCancel Split Jobdestructive
llamacloud.split_jobs.createCreate Split Jobwrite
llamacloud.split_jobs.create_betaCreate Split Jobwrite
llamacloud.split_jobs.deleteDelete Split Jobdestructive
llamacloud.split_jobs.getGet Split Jobread
llamacloud.split_jobs.get_betaGet Split Jobread
llamacloud.split_jobs.listList Split Jobsread
llamacloud.split_jobs.list_betaList Split Jobsread

Agent data7

llamacloud.agent_data.aggregateAggregate Agent Dataread
llamacloud.agent_data.createCreate Agent Datawrite
llamacloud.agent_data.deleteDelete Agent Datadestructive
llamacloud.agent_data.delete_by_queryDelete Agent Data By Querydestructive
llamacloud.agent_data.getGet Agent Dataread
llamacloud.agent_data.searchSearch Agent Dataread
llamacloud.agent_data.updateUpdate Agent Datawrite

Extract7

llamacloud.extract.cancelCancel Extract Jobdestructive
llamacloud.extract.createCreate Extract Jobwrite
llamacloud.extract.deleteDelete Extract Jobdestructive
llamacloud.extract.generate_schemaGenerate Extraction Schemaread
llamacloud.extract.getGet Extract Jobread
llamacloud.extract.listList Extract Jobsread
llamacloud.extract.validate_schemaValidate Extraction Schemaread

Pipeline files7

llamacloud.pipeline_files.addAdd Files To Pipeline Apiwrite
llamacloud.pipeline_files.deleteDelete Pipeline Filedestructive
llamacloud.pipeline_files.get_statusGet Pipeline File Statusread
llamacloud.pipeline_files.get_status_countsGet Pipeline File Status Countsread
llamacloud.pipeline_files.listList Pipeline Filesread
llamacloud.pipeline_files.list_v1List Pipeline Files2read
llamacloud.pipeline_files.updateUpdate Pipeline Filewrite

Data sinks6

llamacloud.data_sinks.createCreate Data Sinkwrite
llamacloud.data_sinks.deleteDelete Data Sinkdestructive
llamacloud.data_sinks.getGet Data Sinkread
llamacloud.data_sinks.listList Data Sinksread
llamacloud.data_sinks.list_v1List Data Sinksread
llamacloud.data_sinks.updateUpdate Data Sinkwrite

Directory files6

llamacloud.directory_files.bulk_deleteBulk Delete Directory Filesdestructive
llamacloud.directory_files.createAdd Directory Filewrite
llamacloud.directory_files.deleteDelete Directory Filedestructive
llamacloud.directory_files.getGet Directory Fileread
llamacloud.directory_files.listList Directory Filesread
llamacloud.directory_files.updateUpdate Directory Filewrite

Indexes6

llamacloud.indexes.cancel_syncCancel Index Syncdestructive
llamacloud.indexes.createCreate Indexwrite
llamacloud.indexes.deleteDelete Indexdestructive
llamacloud.indexes.getGet Indexread
llamacloud.indexes.listList Indexesread
llamacloud.indexes.syncSync Indexwrite

Parse6

llamacloud.parse.cancelCancel Parse Jobdestructive
llamacloud.parse.createParse Filewrite
llamacloud.parse.deleteDelete Parse Jobdestructive
llamacloud.parse.getGet Parse Jobread
llamacloud.parse.listList Parse Jobsread
llamacloud.parse.list_versionsList Parse Versionsread

Webhook configs6

llamacloud.webhook_configs.createCreate Webhook Configwrite
llamacloud.webhook_configs.deleteDelete Webhook Configdestructive
llamacloud.webhook_configs.getGet Webhook Configread
llamacloud.webhook_configs.listList Webhook Configsread
llamacloud.webhook_configs.queryQuery Webhook Configsread
llamacloud.webhook_configs.updateUpdate Webhook Configwrite

Chat sessions5

llamacloud.chat_sessions.createCreate Sessionwrite
llamacloud.chat_sessions.deleteDelete Sessiondestructive
llamacloud.chat_sessions.getGet Full Sessionread
llamacloud.chat_sessions.get_summaryGet Session Summaryread
llamacloud.chat_sessions.listList Sessionsread

Classify5

llamacloud.classify.cancelCancel Classify Jobdestructive
llamacloud.classify.createCreate Classify Jobwrite
llamacloud.classify.deleteDelete Classify Jobdestructive
llamacloud.classify.getGet Classify Jobread
llamacloud.classify.listList Classify Jobsread

Configurations5

llamacloud.configurations.createCreate Configurationwrite
llamacloud.configurations.deleteDelete Configurationdestructive
llamacloud.configurations.getGet Configurationread
llamacloud.configurations.listList Configurationsread
llamacloud.configurations.updateUpdate Configurationwrite

Data sources5

llamacloud.data_sources.createCreate Data Sourcewrite
llamacloud.data_sources.deleteDelete Data Sourcedestructive
llamacloud.data_sources.getGet Data Sourceread
llamacloud.data_sources.listList Data Sourcesread
llamacloud.data_sources.updateUpdate Data Sourcewrite

Directories5

llamacloud.directories.createCreate Directorywrite
llamacloud.directories.deleteDelete Directorydestructive
llamacloud.directories.getGet Directoryread
llamacloud.directories.listList Directoriesread
llamacloud.directories.updateUpdate Directorywrite

Extraction jobs5

llamacloud.extraction_jobs.getGet Jobread
llamacloud.extraction_jobs.get_resultGet Job Resultread
llamacloud.extraction_jobs.listList Jobsread
llamacloud.extraction_jobs.runRun Jobwrite
llamacloud.extraction_jobs.run_batchRun Batch Jobswrite

Extraction runs5

llamacloud.extraction_runs.deleteDelete Extraction Rundestructive
llamacloud.extraction_runs.getGet Runread
llamacloud.extraction_runs.get_by_jobGet Run By Job Idread
llamacloud.extraction_runs.get_latest_from_uiGet Latest Run From Uiread
llamacloud.extraction_runs.listList Extract Runsread

Files5

llamacloud.files.deleteDelete Filedestructive
llamacloud.files.getGet Fileread
llamacloud.files.get_content_urlRead File Contentread
llamacloud.files.listList Filesread
llamacloud.files.queryQuery Filesread

Pipeline data sources5

llamacloud.pipeline_data_sources.addAdd Data Sources To Pipelinewrite
llamacloud.pipeline_data_sources.get_statusGet Pipeline Data Source Statusread
llamacloud.pipeline_data_sources.listList Pipeline Data Sourcesread
llamacloud.pipeline_data_sources.syncSync Pipeline Data Sourcewrite
llamacloud.pipeline_data_sources.updateUpdate Pipeline Data Sourcewrite

Verify5

llamacloud.verify.cancelCancel Verify Jobdestructive
llamacloud.verify.createCreate Verify Jobwrite
llamacloud.verify.getGet Verify Jobread
llamacloud.verify.get_detailsGet Verify Job Detailsread
llamacloud.verify.listList Verify Jobsread

Batch processing4

llamacloud.batch_processing.cancelCancel Batch Jobdestructive
llamacloud.batch_processing.createCreate Batch Jobwrite
llamacloud.batch_processing.get_statusGet Batch Job Statusread
llamacloud.batch_processing.listList Batch Jobsread

Batches4

llamacloud.batches.cancelCancel Batchdestructive
llamacloud.batches.createCreate Batchwrite
llamacloud.batches.getGet Batchread
llamacloud.batches.listList Batchesread

Embedding model configs4

llamacloud.embedding_model_configs.createCreate a new Embedding Model Configurationwrite
llamacloud.embedding_model_configs.deleteDelete Embedding Model Configdestructive
llamacloud.embedding_model_configs.listList Embedding Model Configsread
llamacloud.embedding_model_configs.updateUpdate Embedding Model Configwrite

Organizations4

llamacloud.organizations.getGet Organizationread
llamacloud.organizations.get_v1Get Organizationread
llamacloud.organizations.listList Organizationsread
llamacloud.organizations.list_v1List Organizationsread

Projects4

llamacloud.projects.getGet Projectread
llamacloud.projects.get_v1Get Projectread
llamacloud.projects.listList Projectsread
llamacloud.projects.list_v1List Projectsread

Retrieval4

llamacloud.retrieval.find_filesFind Filesread
llamacloud.retrieval.grep_fileGrep Fileread
llamacloud.retrieval.read_fileRead Fileread
llamacloud.retrieval.retrieveRetrieveread

File page figures3

llamacloud.file_page_figures.create_presigned_urlGenerate File Page Figure Presigned Urlread
llamacloud.file_page_figures.getList File Page Figuresread
llamacloud.file_page_figures.listList File Pages Figuresread

Attachments2

llamacloud.attachments.getGet Attachmentread
llamacloud.attachments.listList Attachmentsread

Batch processing items2

llamacloud.batch_processing_items.get_processing_resultsGet Item Processing Resultsread
llamacloud.batch_processing_items.listList Batch Job Itemsread

File page screenshots2

llamacloud.file_page_screenshots.create_presigned_urlGenerate File Page Screenshot Presigned Urlread
llamacloud.file_page_screenshots.listList File Page Screenshotsread

Usage metrics2

llamacloud.usage_metrics.aggregateAggregate Usage Metricsread
llamacloud.usage_metrics.listList Usage Metricsread

Extraction1

llamacloud.extraction.run_statelessExtract Statelesswrite

Parsing1

llamacloud.parsing.list_supported_file_extensionsGet Supported File Extensionsread

Pipeline document chunks1

llamacloud.pipeline_document_chunks.listList Pipeline Document Chunksread

Pipeline files metadata1

llamacloud.pipeline_files_metadata.deleteDelete Pipeline Files Metadatadestructive

Questions

The LlamaCloud MCP server, answered.

Is there a LlamaCloud MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 199 LlamaCloud actions across pipelines, extraction agents, pipeline documents and retrievers, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by LlamaCloud.

What do I need to connect LlamaCloud?

LlamaCloud API key (llx-...). Plus your host. The free call account { op: "connections.requirements", service: "llamacloud" } lists exactly what to paste.

Can an AI agent delete or change things in LlamaCloud?

Only if its key allows it, and only with an explicit confirmation. 34 LlamaCloud actions are destructive, including delete File, delete Directory and delete Parse Job. 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 LlamaCloud API limit?

actionlake paces every call to the limits in the LlamaCloud service file: 300 calls a minute per connection. Repeated reads are answered from cache (46 LlamaCloud actions can be), which never reaches LlamaCloud.

What does a LlamaCloud action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (199 LlamaCloud actions page). Cache hits, searches, dry runs and calls LlamaCloud 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 LlamaCloud API does it cover?

The Llama Platform API 0.1.0 (OpenAPI 3.1.0) at api.cloud.llamaindex.ai by default, or the base URL set when you connect. It is built from LlamaCloud's documentation as read on 23 October 2026. 199 actions in 39 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my LlamaCloud 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 LlamaCloud 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 LlamaCloud today.

Connect LlamaCloud free See pricing

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

LlamaCloud MCP server for AI agents.

Connect LlamaCloud in three steps.

Add actionlake to Claude.

Connect LlamaCloud.

Make the first call. Check before a write.

What an AI agent can do in LlamaCloud.

Pipelines

Extraction agents

Pipeline documents

Retrievers

Parsing jobs

Split jobs

Agent data

Extract