Skip to main content

An AWS Labs Model Context Protocol (MCP) server for kinesis

Project description

AWS Labs Kinesis MCP Server

The official MCP Server for interacting with AWS Kinesis

Available MCP Tools

Read Only Operations

  • describe_limits - Describes the limits for a Kinesis data stream in the specified region.
  • describe_stream - Describes the specified stream.
  • describe_stream_consumer - Describes a Kinesis data stream consumer.
  • describe_stream_summary - Describes the stream summary.
  • get_records - Retrieves records from a Kinesis shard.
  • get_resource_policy - Retrieves the resource policy for a Kinesis data stream.
  • get_shard_iterator - Retrieves a shard iterator for a specified shard.
  • list_tags_for_resource - Lists the tags associated with a Kinesis data stream.
  • list_shards - Lists the shards in a Kinesis data stream.
  • list_stream_consumers - Lists the consumers of a Kinesis data stream.
  • list_streams - Lists the Kinesis data streams.

Non Read Only Operations (requires KINESIS-READONLY flag to be set to false)

  • create_stream - Creates a new Kinesis data stream with the specified name and shard count.
  • decrease_stream_retention_period - Decreases the retention period of a Kinesis data stream.
  • delete_resource_policy - Deletes the resource policy for a Kinesis data stream.
  • delete_stream - Deletes a Kinesis data stream.
  • deregister_stream_consumer - Deregisters a consumer from a Kinesis data stream.
  • disable_enhanced_monitoring - Disables enhanced monitoring for a Kinesis data stream.
  • enable_enhanced_monitoring - Enables enhanced monitoring for a Kinesis data stream.
  • increase_stream_retention_period - Increases the retention period of a Kinesis data stream.
  • merge_shards - Merges two adjacent shards in a Kinesis data stream.
  • put_record - Writes a single data record into a Kinesis data stream.
  • put_records - Writes multiple data records to a Kinesis data stream in a single call.
  • put_resource_policy - Attaches a resource policy to a Kinesis data stream.
  • register_stream_consumer - Registers a consumer with a Kinesis data stream.
  • split_shard - Splits a shard into two shards in a Kinesis data stream.
  • start_stream_encryption - Starts encryption for a Kinesis data stream.
  • stop_stream_encryption - Stops encryption for a Kinesis data stream.
  • update_shard_count - Updates the shard count of a Kinesis data stream.
  • update_stream_mode - Updates the mode of a Kinesis data stream.

Instructions

The official MCP Server for interacting with AWS Kinesis provides a comprehensive set of tools for managing Kinesis resources. Each tool maps directly to Kinesis API operations and supports all relevant parameters.

To use these tools, ensure you have proper AWS credentials configured with appropriate permissions for Kinesis operations. The server will automatically use credentials from environment variables (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN) or other standard AWS credential sources.

All tools support an optional region_name parameter to specify which AWS region to operate in. If not provided, it will use the AWS_REGION environment variable or default to 'us-west-2'.

IMPORTANT: If you want to have access to non read only tools, you must set the flag in KINESIS-READONLY to false. The default setup will have this flag set to true.

Prerequisites

  1. Install uv from Astral or the Github README
  2. Install Python using uv python install 3.10
  3. Set up AWS credentials with access to AWS services

Installation

Add the MCP to your favorite agentic tools. e.g. for Amazon Q Developer CLI MCP, ~/.aws/amazonq/mcp.json:

{
  "mcpServers": {
    "awslabs.kinesis-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.kinesis-mcp-server@latest"],
      "env": {
        "KINESIS-READONLY": "true",
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

or after a successful docker build -t awslabs/kinesis-mcp-server .:

{
    "mcpServers": {
      "awslabs.kinesis-mcp-server": {
        "command": "docker",
        "args": [
          "run",
          "--rm",
          "--interactive",
          "--env",
          "KINESIS-READONLY=true",
          "awslabs/kinesis-mcp-server:latest"
        ],
        "env": {},
        "disabled": false,
        "autoApprove": []
      }
    }
  }

Quick Installation

Run the installation script:

curl -sSL https://raw.githubusercontent.com/jbrub/mcp/main/src/kinesis-mcp-server/install.sh | bash

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

awslabs_kinesis_mcp_server-0.1.1.tar.gz (92.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

awslabs_kinesis_mcp_server-0.1.1-py3-none-any.whl (20.9 kB view details)

Uploaded Python 3

File details

Details for the file awslabs_kinesis_mcp_server-0.1.1.tar.gz.

File metadata

File hashes

Hashes for awslabs_kinesis_mcp_server-0.1.1.tar.gz
Algorithm Hash digest
SHA256 96ca89b2120f1fbc1c6b0c00d3f7101d9cfab94ad95700d61ff9dffb1d39c74c
MD5 6cdc990c40ff887fdd93ea9cb6abdfc1
BLAKE2b-256 d003a5b4bcca7884527758b961b3ae0b9788cccd542ca378378df4628849664a

See more details on using hashes here.

File details

Details for the file awslabs_kinesis_mcp_server-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for awslabs_kinesis_mcp_server-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 876d681f79ea2a2c488e88a322e121fb0bdcbcc1065fdc40346b20ea21c72dbd
MD5 d8c9074e8b1578cb1a0215a8b5391eee
BLAKE2b-256 8192a98e781042cc2ca50b80e14ff2e0b30292d3e51aabdbbb5d4f4a4bf1f87b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page