Fetches the parsed text and metadata for Metaphor documents by ID, several at a time, turning a set of result IDs into readable content.
1actions available
Every action runs live through MCP. Nothing to build, nothing to maintain.
Retrieve parsed HTML/text contents and metadata for documents by their IDs." Use when you need to fetch the full text and metadata of multiple documents at once.
Each card is one request a support team gets, and the Metaphor actions Ayro runs to close it.
Ayro fetches the parsed contents for the Metaphor document IDs it was given, so a set of links becomes text somebody can actually answer from.
The action accepts multiple IDs at once, so Ayro pulls the whole set in a single call rather than walking them one at a time.
Each document comes back with its metadata, so Ayro can say where a passage came from and not only what it says.
When a request needs evidence, Ayro retrieves the documents behind the IDs as one step and keeps handling the rest of the conversation.
How it works
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Metaphor actions it has and picks the ones a request needs.
Authorize the Metaphor account your team already uses — one consent screen, no API keys, no mapping tables. Ayro can only do what you granted that account, and you can disconnect it at any time.
Describe the job the way you would hand it to a teammate. Ayro maps it to the Metaphor actions that close it and chains as many as the request needs.
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 freeMetaphor · Ayro
What can you do in Metaphor without me setting anything up?
These, right away:
Great, let's start with the first one.
FAQ
Setup, permissions, and the limits of what Ayro can do inside Metaphor.
No, and it is the limit worth knowing up front. The connected toolkit exposes one action, Get Document Contents by IDs, which fetches content for documents you already have identifiers for. Issuing the neural search that produces those IDs is not part of this connection.
All 1 actions your agent can call on Metaphor, straight from the live MCP connection.
Retrieve parsed HTML/text contents and metadata for documents by their IDs." Use when you need to fetch the full text and metadata of multiple documents at once.
Same connection, same setup. Pick the next one your team already uses.
Compares model pricing and limits, creates assistants and threads, drives runs and submits tool outputs, and checks on batch and video jobs.
Adds documents, files, and web pages to the knowledge base, asks bots sourced questions, and keeps folders and history in order.
Speaks written answers aloud with a chosen voice and reports whether an avatar video render has finished and where the file sits.
Creates and reconfigures pipes, manages retrieval memories and threads, and pulls execution traces when a run needs debugging.
Runs a template against supplied data, reports app job status and results, and manages the webhook subscriptions behind those jobs.
Registers and announces agents, discovers peers by capability, opens and answers collaboration requests, and checks SwarmScore and trust records.

Authorize the account and your agent has all 1 actions from the first conversation.
