What is Logchef Mcp

Logchef MCP Server is a connectivity layer that allows AI assistants to interact with the Logchef log management platform. It leverages the Model Context Protocol (MCP) to facilitate natural language queries and interactions with log data stored in ClickHouse, making log analysis simpler and more intuitive for users.

Use cases

Users can utilize this MCP server for various log-related tasks, such as exploring log sources and team memberships, executing complex ClickHouse SQL queries to troubleshoot issues, generating histograms and time series data for trend analysis, and managing saved queries for repetitive tasks. Admin users can also oversee team memberships and source configurations.

How to use

To use the Logchef MCP Server, you need to install it via Docker or as a binary on your local machine. After setting up the server with your Logchef instance’s URL and API token, you can configure your AI assistant to interact with the MCP Server. You can issue natural language queries, create or manage saved queries, and retrieve data using the available tools.

Key features

Key features of the Logchef MCP Server include profile and metadata management, source management for exploring log schemas, log analysis capabilities including SQL query execution and histogram generation, and administrative functions for user and team management. The server supports selective enabling of these tools based on user needs.

Where to use

The Logchef MCP Server is ideal for environments requiring efficient log analysis and monitoring. It’s particularly useful in software development, IT operations, security analysis, and any field where log data needs to be monitored and analyzed for performance, troubleshooting, and security incident detection.

Logchef MCP Server

A Model Context Protocol (MCP) server that connects AI assistants to your Logchef instance.

Logchef is a powerful log management platform that stores logs in ClickHouse, providing fast querying and analysis capabilities. This MCP server enables AI assistants to interact with your Logchef deployment, making log analysis and troubleshooting more accessible through natural conversation.

What You Can Do

With this MCP server, you can ask AI assistants to help you:

• Explore your log infrastructure: See what teams you belong to and what log sources are available
• Query logs effectively: Execute ClickHouse SQL queries to find specific log entries, errors, or patterns
• Understand your data: Get schema information to know what fields are available in your logs
• Analyze log patterns: Generate histograms and time-series data for trend analysis
• Manage saved queries: Create and organize collections of frequently-used queries
• Administer teams and users: Handle team membership, user management, and source configuration (admin users)

Tool Categories

The server provides tools organized into logical categories that can be enabled or disabled as needed:

Profile & Metadata

Core user and server information including team memberships and server version details.

Source Management

Access to log sources across your teams, including schema exploration and source listing.

Log Analysis

The core querying capabilities including SQL execution, histogram generation, and saved query management.

Administration

Team management, user administration, source configuration, and API token management (requires admin privileges).

Use the --disable-<category> flag to turn off tool categories you don’t need. For example, --disable-admin removes all administrative tools.

Tools

Tool	Category	Description
get_profile	Profile	Get the current user profile information
get_teams	Profile	Get teams that the current user belongs to
get_meta	Profile	Get server metadata including version information
get_sources	Sources	Get all sources accessible to the user across all team memberships
get_team_sources	Sources	Get sources that belong to a specific team
query_logs	Logs	Execute ClickHouse SQL queries against log sources to retrieve log entries
get_source_schema	Logs	Get the ClickHouse table schema (column names and types) for a specific source
get_log_histogram	Logs	Generate histogram data for logs with customizable time windows and grouping
get_collections	Logs	List saved query collections for a specific team and source
create_collection	Logs	Create a new saved query collection
get_collection	Logs	Get details of a specific saved query collection
update_collection	Logs	Update an existing saved query collection
delete_collection	Logs	Delete a saved query collection
list_all_teams	Admin	List all teams in the system (admin only)
get_team	Admin	Get detailed information about a specific team
create_team	Admin	Create a new team (admin only)
update_team	Admin	Update an existing team’s information
delete_team	Admin	Delete a team permanently (admin only)
list_team_members	Admin	List all members of a specific team
add_team_member	Admin	Add a user to a team with a specific role
remove_team_member	Admin	Remove a user from a team
link_source_to_team	Admin	Link a log source to a team
unlink_source_from_team	Admin	Remove a log source from a team
list_all_users	Admin	List all users in the system (admin only)
get_user	Admin	Get detailed information about a specific user (admin only)
create_user	Admin	Create a new user in the system (admin only)
update_user	Admin	Update an existing user’s information (admin only)
delete_user	Admin	Delete a user from the system (admin only)
list_api_tokens	Admin	List all API tokens for the current user
create_api_token	Admin	Create a new API token for the current user
delete_api_token	Admin	Delete an API token
list_all_sources	Admin	List all log sources in the system (admin only)
create_source	Admin	Create a new log source (admin only)
validate_source_connection	Admin	Validate ClickHouse connection details (admin only)
delete_source	Admin	Delete a log source (admin only)
get_admin_source_stats	Admin	Get detailed statistics for a log source (admin only)

Getting Started

Prerequisites

You’ll need:

• A running Logchef instance (learn more at logchef.app)
• A valid Logchef API token with appropriate permissions

Generating an API Token

1. Log into your Logchef instance
2. Navigate to your profile settings
3. Create a new API token with the permissions you need
4. Copy the token for use in the MCP server configuration

Installation

Choose one of the following installation methods:

• Docker image: Use the pre-built Docker image.

  Important: The Docker image’s entrypoint is configured to run the MCP server in SSE mode by default, but most users will want to use STDIO mode for direct integration with AI assistants like Claude Desktop:

  1. STDIO Mode: For stdio mode you must explicitly override the default with -t stdio and include the -i flag to keep stdin open:

  docker pull ghcr.io/mr-karan/logchef-mcp:latest
  docker run --rm -i -e LOGCHEF_URL=http://localhost:5173 -e LOGCHEF_API_KEY=<your_api_token> ghcr.io/mr-karan/logchef-mcp:latest -t stdio
  

  2. SSE Mode: In this mode, the server runs as an HTTP server that clients connect to. You must expose port 8000 using the -p flag:

  docker pull ghcr.io/mr-karan/logchef-mcp:latest
  docker run --rm -p 8000:8000 -e LOGCHEF_URL=http://localhost:5173 -e LOGCHEF_API_KEY=<your_api_token> ghcr.io/mr-karan/logchef-mcp:latest
  

  3. Streamable HTTP Mode: In this mode, the server operates as an independent process that can handle multiple client connections. You must expose port 8000 using the -p flag:

  docker pull ghcr.io/mr-karan/logchef-mcp:latest
  docker run --rm -p 8000:8000 -e LOGCHEF_URL=http://localhost:5173 -e LOGCHEF_API_KEY=<your_api_token> ghcr.io/mr-karan/logchef-mcp:latest -t streamable-http
  

• Download binary: Download the latest release of logchef-mcp from the releases page and place it in your $PATH.

• Build from source: If you have a Go toolchain installed you can also build and install it from source:

  just build
  

  Or manually:

  go build -o logchef-mcp.bin ./cmd/logchef-mcp
  

3. Add the server configuration to your client configuration file. For example, for Claude Desktop:

   If using the binary:

   {
     "mcpServers": {
       "logchef": {
         "command": "logchef-mcp.bin",
         "args": [],
         "env": {
           "LOGCHEF_URL": "http://localhost:5173",
           "LOGCHEF_API_KEY": "<your_api_token>"
         }
       }
     }
   }
   

Note: if you see Error: spawn logchef-mcp.bin ENOENT in Claude Desktop, you need to specify the full path to logchef-mcp.bin.

If using Docker:

{
  "mcpServers": {
    "logchef": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "LOGCHEF_URL",