Ragie MCP integration
Retrieves the passages that answer a query, ingests documents from files, URLs or raw text, and keeps the indexed material current.
31actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Create document
Lyro uploads and processes a document file in Ragie for immediate ingestion into the knowledge base. The document is parsed, indexed, and ready for RAG queries within moments.
Retrieve document chunks
Lyro finds the most relevant document chunks in Ragie based on a customer query. The agent cites specific passages so the customer knows exactly where the answer came from.
Get document chunk content
Lyro retrieves the full content of a specific chunk in the requested format with streaming support. The customer sees the exact text or media they need without truncation.
How businesses use Ragie + Lyro
Each card is one request a support team gets, and the Ragie actions Lyro runs to close it.
Pull the passage that actually answers the question
Lyro retrieves the document chunks that match a query, fetches the content of the most relevant one, and falls back to a generated summary when the question is about a whole document.
Retrieve Document ChunksGet Document Chunk ContentGet Document SummaryGet new material into the index
Lyro uploads a document file, ingests one from a publicly accessible URL, or pushes raw text or JSON straight in, so a policy change or a new article is searchable without a manual import.
Create DocumentCreate Document From URLCreate Document RawKeep the indexed source material current
Lyro refreshes a document from its source URL when the page changes, patches metadata fields without replacing the rest, and deletes material that has been superseded.
Update Document From URLPatch Document MetadataDelete DocumentExtract structured data as documents arrive
Lyro defines a natural-language instruction that runs against documents as they are ingested or updated, then reads back the entities it produced per document or per instruction.
Create InstructionList Entities By DocumentList Entities by Instruction
How it works
Get started in 3 steps
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Ragie actions it has and picks the ones a request needs.
- 01
Connect Ragie
Authorize the Ragie account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
- 02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Ragie actions that close it and chains as many as the request needs.
- 03
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free
Everything else about Ragie
Setup, permissions, and the limits of what Lyro can do inside Ragie.
Yes, that is what partitions are for. Create Partition scopes documents and connections to a workspace, Set Partition Limits caps monthly and maximum pages processed or hosted plus video and audio processing, and Get Partition returns the usage statistics and limits for one of them.
Every action available in Ragie
All 31 actions your agent can call on Ragie, straight from the live MCP connection.
Create document
Upload and process a document file in Ragie.
Create document from URL
Ingest a document from a publicly accessible URL.
Create document raw
Ingest a document as raw text or JSON.
Create instruction
Create a new instruction that applies natural language directives to documents as they're ingested or updated.
Create oauth redirect URL
Create an OAuth redirect URL for initializing embedded connector OAuth flows.
Create partition
Create a new partition for scoping documents and connections in Ragie.
Delete document
Delete a document from Ragie.
Delete instruction
Delete an instruction and all associated entities.
Delete partition
Delete a partition and all associated data irreversibly.
Get document
Retrieve a specific document by its unique identifier.
Get document chunk
Retrieve a specific document chunk by its document and chunk ID.
Get document chunk content
Retrieve document chunk content in requested format with streaming support for media.
Get document chunks
Retrieve document chunks with pagination support.
Get document content
Retrieve the content of a document by its ID.
Get document summary
Retrieve an LLM-generated summary of a document by its ID.
Get partition
Retrieve a partition by ID with usage statistics and resource limits.
Get response
Retrieve a response by its unique identifier.
List connections
List all connections sorted by creation date descending with pagination support.
List connection source types
List available connection source types like 'google_drive' and 'notion' along with their metadata.
List documents
List all documents sorted by creation date (descending) with pagination support.
List entities by document
Retrieve all extracted entities from a specific document with pagination support.
List entities by instruction
Retrieve entities generated by a specific instruction.
List instructions
Retrieve all instruction records from the Ragie system.
List partitions
Retrieve a paginated list of all partitions sorted by name in ascending order.
Patch document metadata
Update metadata for a specific document with partial update support.
Retrieve document chunks
Retrieve relevant document chunks based on a query.
Set partition limits
Set usage limits on partition pages and media.
Update document from URL
Update an existing document by fetching content from a publicly accessible URL.
Update document raw
Update a document's content from raw text or JSON data.
Update instruction
Update an instruction's active status.
The tools Ragie sits next to
Same connection, same setup. Pick the next one your team already uses.
Browser tool
Starts cloud browser tasks, polls their progress step by step, kills a stuck run and fetches the files a task produced.
Fal.ai
Searches model endpoints, estimates what a run will cost, follows a queued request through its logs, and returns or cancels it on request.
Kaggle
Searches datasets, models, and competitions, publishes and versions datasets, pulls notebook code and output, and files competition entries.
Openai
Reports on running batch and fine-tuning jobs, maintains and searches vector stores, transcribes or voices audio, and runs moderation and evals.
Stack Ai
Reports Stack AI health and license status, lists available providers, actions, and triggers, and returns the schema each one expects.
Writer
Queries a knowledge graph for grounded answers, uploads and indexes new documents into it, and unlinks the files that have gone out of date.
Ready to connect Ragie?
Authorize the account and your agent has all 31 actions from the first conversation.