Skip to content
Changelog

Report a bug

Textcortex integration: operations for AI agents

Textcortex connects to Type.com as an integration. This page lists the 17 operations documented for Claude and Codex in Type.com: 11 read, 5 write, 1 destructive.

About Textcortex

TextCortex offers an AI-powered text generation API that enables developers to integrate advanced language models into their applications for tasks such as content creation, paraphrasing, and more.

Categories: Marketing & Social

How to connect Textcortex to Type.com

Access
Organization connection: one shared account for the workspace.
MCP
Selected AI media-generation operations are not available through Type’s MCP server. Other operations remain available through MCP, subject to your connection’s permissions. These MCP restrictions do not apply within Type.

To add the connection, follow the steps in Space connections.

Documented operations

17 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.

Files

  • Read

    List owned uploaded files

    List uploaded files owned by the current API key user. Uses the current API key's permissions. Check GET /capabilities for availability. q filters filenames, not document content. total may be approximate; use totalisexact and hasmore. Pagination starts at page=0.

  • Read

    Retrieve file metadata

    Retrieve public API Platform metadata for one accessible uploaded file. Uses the current API key's permissions. Check GET /capabilities for availability. Returns metadata for an owned file, not file bytes or extracted text.

  • Write

    Upload a file

    Upload one file for the current API key user without KB insertion. Uses the current API key's permissions. Check GET /capabilities for availability. Send multipart/form-data with field file. This stores an owned file without KB insertion.

  • Destructive

    Delete an owned file

    Delete one uploaded file owned by the current API key user. Uses the current API key's permissions. Check GET /capabilities for availability. Deletes the owned file and its associated KB insertions; this is not a detach-from-one-KB operation.

Knowledge Bases

  • Read

    List accessible knowledge bases

    List knowledge bases visible to the current API key. Uses the current API key's permissions. Check GET /capabilities for availability. Create a knowledge base in the TextCortex app first; this public API does not expose KB creation. Use the returned id as kbid.

  • Read

    Search file contents across knowledge bases

    Search file contents across knowledge bases visible to the current API key. Uses the current API key's permissions. Check GET /capabilities for availability. Searches indexed content across accessible KBs and collapses matches to one result per file. Pagination starts at page=0.

  • Read

    List knowledge-base file insertions

    List active file insertions for one accessible knowledge base. Uses the current API key's permissions. Check GET /capabilities for availability.

  • Read

    Retrieve relevant document passages

    Query one accessible knowledge base through the public API Platform contract. Uses the current API key's permissions. Check GET /capabilities for availability. Returns relevant excerpts, not an AI-generated answer. Pass results[].text to Chat Completions.

  • Write

    Add an uploaded file to a knowledge base

    Insert one owned uploaded file into an editable knowledge base. Uses the current API key's permissions. Check GET /capabilities for availability. Requires ownership of the uploaded file and edit access to the KB. Poll the file-insertion list for indexing status before querying.

Balance

  • Read

    Retrieve API credit balance

    Returns the remaining API credit balance for the authenticated TextCortex API key. API-credit fields are preserved even when model requests use wallet funding. Inspect billingsource and optional wallet for that funding source. Unavailable projections are not zero balances.

Capabilities

  • Read

    Discover API capabilities

    Return the public capability surface for the current API key. Uses the current API key's permissions. Check GET /capabilities for availability.

Chat Completions

  • Write

    Create a chat completion

    Creates a chat completion using an OpenAI-compatible request body. Use model ids returned by GET /models, and set reasoningeffort to control how much the model reasons before answering.

Images

  • Write

    Generate an image

    Generate one image from a prompt. data[0].url is a TextCortex resource URI (textcortex://images/ ), not a directly downloadable HTTP URL. Keep data[0].imageid to reuse the image in another generation. Check GET /capabilities for access.

Models

  • Read

    List models

    Returns the TextCortex models available through the OpenAI-compatible public API. A model whose reasoning can be varied is listed once, under its base id; control its reasoning with reasoningeffort on the request rather than by choosing a model id.

  • Read

    Retrieve a model

    Returns metadata for one TextCortex model available through the OpenAI-compatible public API.

Responses

  • Write

    Create a response

    Creates a response using an OpenAI-compatible request body. Use model ids returned by GET /models. This endpoint is a text-only subset. Send input as text or supported text messages, and optionally instructions.

Web Search

  • Read

    Search the web

    Search the web and return titles, URLs and snippets. This request does not generate an AI answer, fetch full pages, or select a chat model. Check GET /capabilities for access and current pricing. Search, then answer 1. Send {"query":"What changed in Python 3.13?","website":"docs.

See How connections work for access and permissions, or browse all integrations.