Connect TextCortex to Your AI Agent

Inspect available model metadata and submit non-streaming OpenAI-compatible chat messages. Ask your connected AI assistant to explain the results or carry out the specified operation.

3 tools API key

Connect TextCortex Install OOMOL

Try a TextCortex Task

Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.

oo Skill TextCortex

Ask a Selected Model

Choose a model and submit explicit role-based messages.

/oo TextCortex: List TextCortex models, then create a chat completion with model [model ID] and messages [role/content messages] to explain [topic].

Inspect a Model

Read model metadata before choosing generation settings.

/oo TextCortex: Retrieve TextCortex model [model ID] and summarize its returned metadata before a chat request.

Start Working with TextCortex

Install OOMOL

Set up oo CLI and the oo Skill in your agent.
Install OOMOL →
Connect TextCortex

Connect with a TextCortex API key.
Connect TextCortex →
Give Your Agent a Task

Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →

Choose Your Agent

Codex Claude Code Cursor Hermes

A TextCortex API key with model access.
Chat returns a non-streaming response. Tool definitions may guide the model, but the connector does not automatically execute returned tool calls.

TextCortex Tools

TextCortex connects supported service operations to your AI assistant. Inspect available model metadata and submit non-streaming OpenAI-compatible chat messages.

Models

List available models and retrieve model metadata.

Chat

Create a non-streaming chat completion with supported response or tool settings.

3 tools

List Models

List TextCortex models available to the API key.

textcortex.list_models

Retrieve Model

Retrieve metadata for one TextCortex model by model id.

textcortex.retrieve_model

Create Chat Completion

Create a non-streaming OpenAI-compatible chat completion with TextCortex.

textcortex.create_chat_completion

Frequently Asked Questions

Can the action stream tokens?

The current action creates a non-streaming completion.

Does a tool call automatically run a tool?

No. Returned tool calls are model output for a caller to handle.

How do I choose a model?

List models and inspect the selected model metadata before sending messages.