Can Lyro run a Metaphor search through this integration?

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.

Where do the document IDs come from, then?

From a Metaphor search run outside this integration - in your own application code, or in another connected tool that hands back IDs. Lyro takes it from there, pulling the parsed content and metadata so the material can be read, quoted, or summarised in the conversation.

What does the action return for each document?

Parsed HTML or text contents plus the document's metadata, not just a URL. That is the difference between handing someone a link and handing them the page, and it is what makes the result usable in an answer without a second fetch.

Does Lyro have to fetch documents one at a time?

No. Get Document Contents by IDs is built to take multiple IDs in a single call, so a whole set of documents comes back together instead of as a series of round trips.

Metaphor MCP integration

Fetches the parsed text and metadata for Metaphor documents by ID, several at a time, turning a set of result IDs into readable content.

Connect Metaphor See all integrations

1actions available

What your agent can do with Metaphor

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.

See all 1 actions

How businesses use Metaphor + Lyro

Each card is one request a support team gets, and the Metaphor actions Lyro runs to close it.

Turn a list of result IDs into readable text
Lyro fetches the parsed contents for the Metaphor document IDs it was given, so a set of links becomes text somebody can actually answer from.
Get Document Contents By IdsRead Parsed Text
Fetch several documents in one pass
The action accepts multiple IDs at once, so Lyro pulls the whole set in a single call rather than walking them one at a time.
Get Document Contents By IdsBatch Multiple Ids
Read the metadata alongside the text
Each document comes back with its metadata, so Lyro can say where a passage came from and not only what it says.
Get Document Contents By IdsRead Document Metadata
Ground a longer answer in fetched sources
When a request needs evidence, Lyro retrieves the documents behind the IDs as one step and keeps handling the rest of the conversation.
Get Document Contents By IdsRead Parsed Text

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 Metaphor actions it has and picks the ones a request needs.

01
Connect Metaphor
Authorize the Metaphor 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 Metaphor 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

Metaphor · Lyro

Everything else about Metaphor

Setup, permissions, and the limits of what Lyro 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.

Every action available in Metaphor

All 1 actions your agent can call on Metaphor, straight from the live MCP connection.

Get document contents by ids
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.