Metatextai MCP integration
Labels incoming text, extracts structured fields, and screens drafted replies against the guardrail policies your application already enforces.
13actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Chat completions
Ayro generates responses that are automatically guardrailed for safety. Customers get accurate answers while your team avoids harmful or policy-violating outputs.
Evaluate messages
Ayro validates responses against safety policies before sending. Your team catches risky content before it reaches customers, protecting brand reputation.
Update policy guardrails
Ayro adjusts safety rules for different customer scenarios. Your team enforces stricter guardrails for sensitive issues or loosens them for casual conversations.
How businesses use Metatextai + Ayro
Each card is one request a support team gets, and the Metatextai actions Ayro runs to close it.
Turn a free-text message into structured fields
Ayro classifies the message against a trained MetatextAI model and runs extraction over the same text, so an intent, a date, or an order number arrives as labelled data instead of a paragraph to read.
Classify TextRun ExtractionList ModelsDraft a reply and screen it in one pass
Ayro generates the wording with a project model, then evaluates the result against your policies and gets back violation details or a correction before the message is ever shown to a customer.
Generate TextChat CompletionsEvaluate MessagesKeep guardrail policies current
Ayro lists the policies attached to an application, adds a new rule, or amends an existing one, so the constraints your content has to satisfy live in one place rather than scattered across prompts.
List Guardrail PoliciesCreate Policy GuardrailsUpdate Policy GuardrailsRed-team an application against known probes
Ayro lists the available red team probes and runs a vulnerability scan against a named application on request, so a security check is something a person asks for rather than a job someone has to schedule.
List Red Team Test ProbesRun Red Team Test ScanList Applications
How it works
Get started in 3 steps
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Metatextai actions it has and picks the ones a request needs.
Connect Metatextai
Authorize the Metatextai 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.
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Ayro maps it to the Metatextai 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
Metatextai · Ayro
What can you do in Metatextai without me setting anything up?
These, right away:
- Create policy guardrails
- List applications
- Delete guardrail policy
Great, let's start with the first one.
FAQ
Everything else about Metatextai
Setup, permissions, and the limits of what Ayro can do inside Metatextai.
For classification, yes. Classify Text returns labels and confidence scores from a model trained in your MetatextAI project, so the label set is yours rather than a generic taxonomy. List Models shows which models exist and what tasks each supports, and Ayro reads that before choosing one.
Every action available in Metatextai
All 13 actions your agent can call on Metatextai, straight from the live MCP connection.
Chat completions
Generate chat completions.
Classify text
Classify text.
Create policy guardrails
Create a policy guardrail.
Delete guardrail policy
Delete a guardrail policy.
Evaluate messages
Evaluate LLM messages against policies/guardrails.
Run extraction
Run information extraction.
Generate text
Generate text for a project model.
List applications
Retrieve a list of all existing applications.
List models
Retrieve a list of all available models and their supported tasks.
List guardrail policies
List all guardrail policies for a specific application.
List red team test probes
List all available red team test probes.
Run red team test scan
Run a vulnerability red-team test scan.
Update policy guardrails
Update an existing policy's guardrails.
The tools Metatextai sits next to
Same connection, same setup. Pick the next one your team already uses.
Chatbotkit
Pulls bot transcripts and usage figures, clones blueprints into new bots, resyncs training datasets, and wires up messaging channels.
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.
Kieai
Submits image, video, and music generations, polls the tasks they create, edits existing audio tracks, and reports remaining account credits.
Pinecone
Runs similarity searches and reranks results, upserts records with generated embeddings, provisions indexes and namespaces, and runs backups and imports.
Studio By Ai21 Labs
Creates and edits AI21 assistants, validates the Python behind their plans, indexes site content, and runs an assistant on request.
Zep
Writes thread messages into a user graph, retrieves the context relevant to the conversation, searches it semantically, and deletes data on request.
Ready to connect Metatextai?
Authorize the account and your agent has all 13 actions from the first conversation.