Integration

TextCortex integration

TextCortex is an AI platform offering many chat and image models behind one key. Generate chat completions with a chosen model, generate images, search the web for sources, list available models, retrieve relevant passages from knowledge bases, add uploaded files to a knowledge base, and check the account's credit balance and enabled capabilities. Streaming responses are not exposed. Authentication is a TextCortex API key sent as a Bearer token in the Authorization header.

Connect TextCortex How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in TextCortex.Built from the 17 TextCortex tools below, on the connection you add once.

What you can do with TextCortex

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

File, 6 operations

add_file_to_knowledge_baseAdd file to knowledge basePOSTAdd an uploaded file (file_id from upload_file) to an editable knowledge base. A 409 means it is already inserted, a 423 that processing still blocks insertion.
delete_fileDelete fileDELETEDelete one uploaded file owned by the API key's user.
get_fileGet fileGETGet the metadata of one accessible uploaded file: name, MIME type, size, SHA-256, owner flag, visibility and timestamps.
list_filesList filesGETList files uploaded with this API key, optionally filtered by file name (q filters names, not content). Zero-based page; read pagination.has_more.
list_knowledge_base_filesList knowledge base filesGETList the active file insertions of one knowledge base, with each file's insertion status. Zero-based page; read pagination.has_more.
upload_fileUpload filePOSTUpload one file for the API key's user, without adding it to a knowledge base. Pass the returned id to add_file_to_knowledge_base.

Model, 2 operations

get_modelGet modelGETGet one chat model's metadata (id, owner, creation time, deployment jurisdiction and serving country).
list_modelsList modelsGETList the chat model ids available to the API key, to pass as model to create_chat_completion or create_response. Image models are not listed here.

Search, 2 operations

search_knowledge_base_filesSearch knowledge base filesGETSearch indexed file content across every visible knowledge base, one result per file with a snippet and score. Zero-based page; read pagination.has_more.
search_webSearch webPOSTSearch the web and return titles, URLs and snippets (no AI answer, no full pages). Optional website restricts to one site. Each successful search is billed, even with no results.

Balance, 1 operation

get_balanceGet balanceGETGet the remaining API credit balance of the API key: remaining credits, currency, wallet and billing source.

Capability, 1 operation

get_capabilitiesGet capabilitiesGETGet which features the API key can use (chat completions, responses, images, files, models, balance, knowledge bases). Check it after a 403.

Completion, 1 operation

create_chat_completionCreate chat completionPOSTGenerate a chat answer with a model id from list_models (OpenAI-compatible). Read the text in choices[0].message.content. Billed per use; parameter support depends on the model.

Generation, 1 operation

create_imageCreate imagePOSTGenerate one image from a prompt. data[0].image_id can be reused as a reference image; data[0].url is a textcortex:// resource URI, not a download link. Billed per use.

Knowledge base, 1 operation

list_knowledge_basesList knowledge basesGETList the knowledge bases visible to the API key (id, name, description, owner flag, usability). Zero-based page; read pagination.has_more.

Query, 1 operation

query_knowledge_baseQuery knowledge basePOSTRetrieve the passages of one knowledge base most relevant to a query, with text, score, file and page references. It returns passages, not an AI answer.

Response, 1 operation

create_responseCreate responsePOSTGenerate text with the OpenAI Responses format (text-only subset). Read output[].content[] entries of type output_text. Use create_chat_completion for tools or JSON output.

Use TextCortex from Claude Code, Cursor or Codex

Connect TextCortex in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its TextCortex operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect TextCortex

Create your workspace
Sign up free. Nothing to install.
Connect TextCortex once
Add your TextCortex connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.