Integration

Anthropic integration

Claude AI assistant API for intelligent text generation, analysis, and conversation. Access Anthropic's advanced language models for chatbots, content creation, code assistance, document analysis, and natural language understanding tasks. Supports both synchronous and streaming responses, batch processing, token counting, model management, file uploads, extended thinking, tool use (including web search, code execution), and structured output.

Connect Anthropic How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Anthropic.Built from the 16 Anthropic tools below, on the connection you add once.

Common Anthropic use cases

file management
document analysis
data removal
batch management
file backup
batch cleanup
batch dashboard
cost estimation
model discovery
storage cleanup

What you can do with Anthropic

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.

Batch, 6 operations

cancel_batchCancel batchPOSTCancels a message batch that is still in progress. The batch enters a 'canceling' state, where in-progress non-interruptible requests may still complete before finalizing cancellation. Already completed results remain available. Returns the update...
create_batchCreate batchPOSTCreates a message batch for asynchronous processing by submitting multiple message requests at once. Processes requests asynchronously within 24 hours at 50% reduced cost compared to synchronous calls. Each request includes a custom_id for trackin...
delete_batchDelete batchDELETEDeletes a message batch that has finished processing. Message Batches can only be deleted once they've finished processing - if you'd like to delete an in-progress batch, you must first cancel it. Returns DeletedMessageBatch object with id and typ...
get_batchGet batchGETGets batch processing status by retrieving the current state of a message batch by its ID. Returns processing_status ('in_progress', 'canceling', 'ended'), request_counts broken down by state (processing, succeeded, errored, canceled, expired), cr...
get_batch_resultsGet batch resultsGETGets batch results after processing completes by streaming the output of a completed message batch as a JSONL file. Each line contains custom_id (matching your original request) and result with type: 'succeeded' (with full message response), 'erro...
list_batchesList batchesGETLists all message batches for your workspace, returning a paginated list with status, timestamps, request counts, and results URLs. Most recently created batches are returned first. Each batch includes id, processing_status, request_counts by stat...

File, 5 operations

delete_fileDelete fileDELETEDeletes an uploaded file by its ID. Once deleted, the file cannot be referenced in subsequent API calls and any existing references will fail. Returns DeletedFile object with id and type ('file_deleted'). Use for cleanup and storage management. Re...
download_fileDownload fileGETDownloads the content of an uploaded file by its ID. Returns the raw file content (binary). Use to retrieve files that have been created by skills or the code execution tool, or to backup uploaded content. Only works for files marked as downloadab...
get_fileGet fileGETGets metadata about a specific uploaded file by its ID. Returns FileMetadata with id, filename, mime_type, size_bytes, created_at, type, and downloadable status. Use to verify file exists before referencing in messages or to retrieve file details ...
list_filesList filesGETLists all uploaded files for your account with metadata. Returns paginated list of files with id, filename, mime_type, size_bytes, created_at, type, and downloadable status. Supports cursor-based pagination with before_id/after_id. Requires 'anthr...
upload_fileUpload filePOSTUploads a file for use with the Claude API via multipart/form-data. Files can be referenced in subsequent API calls without re-uploading content, making it efficient for repeated use of the same documents. Returns file metadata including id, filen...

Message, 2 operations

create_messageCreate messagePOSTCreates a message with Claude AI by sending a conversation and receiving an intelligent response. Supports multi-turn conversations via messages array with role/content pairs (user, assistant). Configure generation with temperature (creativity con...
create_message_streamCreate message streamPOSTCreates a streaming message with Claude AI by sending a prompt and receiving the response as a stream of Server-Sent Events (SSE). Each event contains incremental tokens as they're generated, enabling real-time display of responses. Uses the same ...

Model, 2 operations

get_modelGet modelGETGets detailed information about a specific Claude model by its ID or alias. Returns model metadata including id (unique identifier), display_name (human-readable name), created_at (release date as RFC 3339 datetime), and type ('model'). Use to res...
list_modelsList modelsGETLists all available Claude models with their unique identifiers, display names, and release dates. Returns a paginated list with more recently released models listed first. Each model includes id (unique identifier like 'claude-sonnet-4-20250514')...

Token, 1 operation

count_tokensCount tokensPOSTCounts tokens in a message before sending it to Claude, without actually generating a response. Takes the same message format as create_message including model, messages array, optional system prompt, tools, and thinking config. Returns input_toke...

Use Anthropic from Claude Code, Cursor or Codex

Connect Anthropic in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Anthropic 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 Anthropic

Create your workspace
Sign up free. Nothing to install.
Connect Anthropic once
Add your Anthropic 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.

Anthropic integration FAQ

What can you do with the Anthropic integration?

LiveContext exposes 16 operations on Anthropic, covering batch, file, message and model. Common uses include file management, document analysis and data removal.