Integration

Upstash Kafka integration

Serverless Kafka REST API for producing, consuming, and managing messages in Apache Kafka topics. Designed for serverless environments like AWS Lambda, Cloudflare Workers, Next.js Edge, and WebAssembly. Features include HTTP-based messaging, consumer groups, offset management, webhooks, and metadata retrieval. The only connectionless Kafka client that uses HTTP instead of TCP connections.

Connect Upstash Kafka How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Upstash Kafka.Built from the 13 Upstash Kafka tools below, on the connection you add once.

Common Upstash Kafka use cases

webhook forwarding
lag monitoring
message replay
event streaming
topic discovery
event processing
topic inspection
time-based replay
consumer monitoring
reliable processing

What you can do with Upstash Kafka

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.

Message, 6 operations

consume_messagesConsume messagesPOSTConsumes messages from an Upstash Kafka topic using consumer groups. Supports automatic offset management and configurable starting position. Returns array of messages with metadata.
fetch_messagesFetch messagesPOSTFetches messages from a specific Upstash Kafka partition and offset. Bypasses consumer group coordination for direct offset-based access.
produce_batchProduce batchPOSTProduces multiple messages to an Upstash Kafka topic in a single HTTP request. Supports keys, headers, partitions, and timestamps for each message. More efficient than individual produce calls.
produce_messageProduce messagePOSTProduces a single message to an Upstash Kafka topic via HTTP POST. Topic and value are specified in the request body. Returns partition and offset of the produced message.
produce_with_optionsProduce with optionsPOSTProduces a message to an Upstash Kafka topic with full control over all options. Specify topic, value, key, partition, timestamp, and headers in the request body.
webhook_produceWebhook producePOSTProduces messages via webhook endpoint for Upstash Kafka. Request body becomes message content. Supports query param auth for services without HTTP Basic Auth support.

Offset, 3 operations

commit_offsetsCommit offsetsPOSTCommits consumer offsets for an Upstash Kafka consumer group. Use after successfully processing messages when auto-commit is disabled to prevent reprocessing.
get_committed_offsetsGet committed offsetsPOSTRetrieves committed offsets for topic partitions in an Upstash Kafka consumer group. Shows the last successfully committed position for each specified partition.
get_offsets_by_timestampGet offsets by timestampPOSTFinds Upstash Kafka offsets at or after a timestamp for specified partitions. Use 'earliest' or 'latest' for partition boundaries.

Consumer, 2 operations

delete_consumerDelete consumerPOSTStops and removes a consumer instance from an Upstash Kafka consumer group. Triggers rebalance so remaining consumers pick up the deleted instance's partitions.
list_consumersList consumersGETLists all Upstash Kafka consumer groups and their partition assignments. Returns array of consumer group information including member assignments.

Topic, 2 operations

get_topic_partition_infoGet topic partition infoGETGets detailed information about an Upstash Kafka topic including partition count, configuration, and metadata.
list_topicsList topicsGETLists all Upstash Kafka topics in your cluster with partition counts. Returns a JSON map of topic names to their partition numbers.

Use Upstash Kafka from Claude Code, Cursor or Codex

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

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

Upstash Kafka integration FAQ

What can you do with the Upstash Kafka integration?

LiveContext exposes 13 operations on Upstash Kafka, covering message, offset, consumer and topic. Common uses include webhook forwarding, lag monitoring and message replay.