
Last9 Observability MCP
Seamlessly bring real-time production context—logs, metrics, and traces—into your local environment to auto-fix code faster.
README
Last9 MCP Server
A Model Context Protocol server implementation for Last9 that enables AI agents to seamlessly bring real-time production context — logs, metrics, and traces — into your local environment to auto-fix code faster.
- View demo
- Read our announcement blog post
Status
Works with Claude desktop app, or Cursor, Windsurf, and VSCode (Github Copilot) IDEs. Implements the following MCP tools:
get_exceptions
: Get list of exceptions.get_service_graph
: Get service graph for an endpoint from the exception.get_logs
: Get logs filtered by service name and/or severity level.get_drop_rules
: Get drop rules for logs that determine what logs get filtered out at Last9 Control Planeadd_drop_rule
: Create a drop rule for logs at Last9 Control Plane
Tools Documentation
get_exceptions
Retrieves server-side exceptions over a specified time range.
Parameters:
limit
(integer, optional): Maximum number of exceptions to return. Default: 20.start_time_iso
(string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS).end_time_iso
(string, optional): End time in ISO format (YYYY-MM-DD HH:MM:SS).span_name
(string, optional): Name of the span to filter by.
get_service_graph
Gets the upstream and downstream services for a given span name, along with the throughput for each service.
Parameters:
span_name
(string, required): Name of the span to get dependencies for.lookback_minutes
(integer, optional): Number of minutes to look back. Default: 60.start_time_iso
(string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS).
get_logs
Gets logs filtered by optional service name and/or severity level within a specified time range.
Parameters:
service
(string, optional): Name of the service to get logs for.severity
(string, optional): Severity of the logs to get.start_time_iso
(string, optional): Start time in ISO format (YYYY-MM-DD HH:MM:SS).end_time_iso
(string, optional): End time in ISO format (YYYY-MM-DD HH:MM:SS).limit
(integer, optional): Maximum number of logs to return. Default: 20.
get_drop_rules
Gets drop rules for logs, which determine what logs get filtered out from reaching Last9.
add_drop_rule
Adds a new drop rule to filter out specific logs at Last9 Control Plane
Parameters:
name
(string, required): Name of the drop rule.filters
(array, required): List of filter conditions to apply. Each filter has:key
(string, required): The key to filter on. Only attributes and resource.attributes keys are supported. For resource attributes, use format: resource.attributes[key_name] and for log attributes, use format: attributes[key_name] Double quotes in key names must be escaped.value
(string, required): The value to filter against.operator
(string, required): The operator used for filtering. Valid values:- "equals"
- "not_equals"
conjunction
(string, required): The logical conjunction between filters. Valid values:- "and"
Installation
You can install the Last9 Observability MCP server using either:
Homebrew
# Add the Last9 tap
brew tap last9/tap
# Install the Last9 MCP CLI
brew install last9-mcp
NPM
# Install globally
npm install -g @last9/mcp-server
# Or run directly with npx
npx @last9/mcp-server
Configuration
Environment Variables
The service requires the following environment variables:
-
LAST9_AUTH_TOKEN
: Authentication token for Last9 MCP server (required) -
LAST9_BASE_URL
: Last9 API URL (required) -
LAST9_REFRESH_TOKEN
: Refresh Token with Write permissions. Needed for accessing control plane APIs (required). -
Signup at Last9 and setup one of the integrations.
-
Obtain
LAST9_BASE_URL
andLAST9_AUTH_TOKEN
from here. -
The Write Refresh Token can be obtained from API Access page.
Usage with Claude Desktop
Configure the Claude app to use the MCP server:
- Open the Claude Desktop app
- Go to Settings, then Developer, click Edit Config
- Open the
claude_desktop_config.json
file - Copy and paste the server config to your existing file, then save
- Restart Claude
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"last9": {
"command": "/opt/homebrew/bin/last9-mcp",
"env": {
"LAST9_AUTH_TOKEN": "<your_auth_token>",
"LAST9_BASE_URL": "<last9_otlp_host>",
"LAST9_REFRESH_TOKEN": "<refresh_token_from_last9_dashboard>"
}
}
}
}
Usage with Cursor
Configure Cursor to use the MCP server:
- Navigate to Settings, then Cursor Settings
- Select MCP on the left
- Click Add new global MCP server at the top right
- Copy and paste the server config to your existing file, then save
- Restart Cursor
{
"mcpServers": {
"last9": {
"command": "/opt/homebrew/bin/last9-mcp",
"env": {
"LAST9_AUTH_TOKEN": "<auth_token>",
"LAST9_BASE_URL": "<last9_otlp_host>",
"LAST9_REFRESH_TOKEN": "<write_refresh_token>"
}
}
}
}
Usage with Windsurf
Configure Windsurf to use the MCP server:
- Open Windsurf
- Go to Settings, then Developer
- Click Edit Config
- Open the
windsurf_config.json
file - Copy and paste the server config to your existing file, then save
- Restart Windsurf
{
"mcpServers": {
"last9": {
"command": "/opt/homebrew/bin/last9-mcp",
"env": {
"LAST9_AUTH_TOKEN": "<auth_token>",
"LAST9_BASE_URL": "<last9_otlp_host>",
"LAST9_REFRESH_TOKEN": "<refresh_token>"
}
}
}
}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.