Openai MCP integration
Reports on running batch and fine-tuning jobs, maintains and searches vector stores, transcribes or voices audio, and runs moderation and evals.
126actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Create chat completion
Lyro generates conversational responses using OpenAI models to solve customer problems instantly. The customer gets precise, helpful answers powered by advanced reasoning.
Search vector store
Lyro searches an OpenAI vector store to find the most relevant document chunks for a customer query. Results are ranked by relevance so the agent answers with the most accurate sources.
Upload file
Lyro uploads files to OpenAI for use in embeddings, batch processing, or assistant tools. The files are now available for all downstream API calls that reference them.
How businesses use Openai + Lyro
Each card is one request a support team gets, and the Openai actions Lyro runs to close it.
Check on the jobs already running
Lyro lists the batches in flight, retrieves the one in question with its status, and reads the events logged against a fine-tuning job, so whether a run finished is answered without opening a dashboard.
List BatchesRetrieve BatchList Fine-Tuning Job EventsKeep a vector store current and searchable
Lyro adds the new document to the vector store, searches it to confirm the content comes back, and removes the file a policy change made obsolete, so retrieval stays aligned with the source.
Create Vector Store FileSearch Vector StoreDelete Vector Store FileMove a file between audio and text
Lyro transcribes a recording, translates a foreign-language file into English, and voices a written answer as speech, so a call recording or a written reply changes format on request.
Create Audio TranscriptionCreate Audio TranslationCreate Speech (TTS)Check output before it goes anywhere
Lyro runs a moderation pass over the text, starts an evaluation run against a defined eval, and grades the result, so a change is measured rather than shipped on the strength of one spot check.
Create ModerationCreate Evaluation RunRun Grader
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 Openai actions it has and picks the ones a request needs.
Connect Openai
Authorize the Openai 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.
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Openai actions that close it and chains as many as the request needs.
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
Openai · Lyro
What can you do in Openai without me setting anything up?
These, right away:
- Add upload part
- Get chat completion
- Cancel batch
Great, let's start with the first one.
FAQ
Everything else about Openai
Setup, permissions, and the limits of what Lyro can do inside Openai.
It can count them, not price them. Get Input Token Counts returns the token count for an input before it is sent, and List Batches with Retrieve Batch show the volume already processed. Billing is not part of this toolkit, so an actual figure still comes from OpenAI's own usage reporting.
Every action available in Openai
All 126 actions your agent can call on Openai, straight from the live MCP connection.
Add upload part
Add a part (chunk of bytes) to an Upload object.
Cancel batch
Cancel an in-progress batch.
Cancel evaluation run
Cancel an ongoing evaluation run.
Cancel response
Cancel a background model response by its ID.
Cancel run
Cancel a run that is currently in progress.
Cancel upload
Cancel an upload.
Compact response
Compact a conversation or response to reduce token usage.
Create audio transcription
Transcribe audio files to text via OpenAI Audio Transcriptions API.
Create audio translation
Translate audio files to English text via OpenAI Audio Translations API.
Create batch
Create and execute a batch from an uploaded file of requests.
Create chat completion
Create a chat completion response from OpenAI models.
Create completion (legacy)
Generate text completions using OpenAI's legacy Completions API.
Create container
Create a new container with configurable memory, expiration, file access, and network policies.
Create container file
Create a file in a container.
Create conversation
Create a new conversation for multi-turn interactions.
Create conversation items
Create items in a conversation with the given ID.
Create embeddings
Generate text embeddings via the OpenAI embeddings endpoint.
Create eval
Create an evaluation structure for testing a model's performance.
Create evaluation run
Create a new evaluation run for testing model configurations.
Create fine-tuning job
Create a fine-tuning job which begins the process of creating a new model from a given dataset.
Generate image
Generate an image via the OpenAI Images API and return hosted image asset URL and metadata.
Edit image
Create edited or extended images via OpenAI Images Edit API.
Create image variation
Create a variation of a given image using the OpenAI Images API.
Create message
Create a new message in a specific thread.
Create moderation
Classify text and/or image inputs for potentially harmful content via the OpenAI Moderation API.
Create realtime call
Create a Realtime API call over WebRTC and receive the SDP answer needed to complete the peer connection.
Create realtime client secret
Create an ephemeral client secret for authenticating Realtime API connections.
Create realtime session
Create an ephemeral API token for client-side Realtime API applications.
Create realtime transcription session
Create an ephemeral API token for realtime transcriptions via the Realtime API.
Create response
Generate a one-shot model response via the Responses API.
The tools Openai sits next to
Same connection, same setup. Pick the next one your team already uses.
Api labz
Searches Trello cards semantically, lists the tables in an Airtable base, validates an IBAN, and pushes a prepared deal record in.
Datarobot
Reports deployment accuracy and drift, starts Autopilot runs, queues batch predictions, and keeps datasets linked to the right use case.
Groqcloud
Generates chat completions, transcribes and translates audio recordings, and checks the live model catalogue before every request.
Metaphor
Fetches the parsed text and metadata for Metaphor documents by ID, several at a time, turning a set of result IDs into readable content.
Rev.ai
Turns recordings and live audio into transcripts with speaker labels, produces SRT and VTT subtitles, and clears finished jobs on request.
Typefully
Creates Typefully drafts from a request, checks what is already scheduled or published, and clears the notification inbox.
Ready to connect Openai?
Authorize the account and your agent has all 126 actions from the first conversation.