Mezmo MCP
Mezmo's remote MCP server connects AI assistants to Mezmo's Observability platform so you can run advanced root-cause analysis, discover pipelines, and export logs without hosting anything yourself.
Mezmo MCP Server (Model Context Protocol)
Mezmo MCP is a remote Model Context Protocol (MCP) server that lets AI assistants and IDE chat agents interact with the Mezmo observability platform via the Model Context Protocol. Use it for streamlined observability, log analysis, and root-cause analysis in your favorite tools.
Add Mezmo MCP and you can:
- 🕵️ Run advanced Root-cause analysis over recent logs
- 📦 List and describe Pipelines
- 📤 Export and filter Logs with powerful query syntax
Table of Contents
Overview
Mezmo MCP is a remote MCP server that connects AI assistants and IDE chat to Mezmo so you can run advanced root-cause analysis, discover pipelines, and export logs without hosting anything yourself. It’s built for observability use cases and works across many popular MCP clients.
Available Tools & Examples
- analyze_logs_for_root_cause_relative_time: analyze logs over a relative window
- Example:
analyze my logs from the last 30 minutes and determine root cause for any issues that you find
- Example:
- analyze_logs_for_root_cause_time_range: analyze logs between specific timestamps
- Example:
analyze errors between 2025-01-01T10:00:00Z and 2025-01-01T11:00:00Z
- Example:
- deduplicate_logs_relative_time: deduplicate similar logs over a relative window
- Example:
deduplicate error logs from the last hour for app "checkout-service"
- Example:
- deduplicate_logs_time_range: deduplicate similar logs between specific timestamps
- Example:
deduplicate logs from 2025-01-01T10:00:00Z to 2025-01-01T11:00:00Z
- Example:
- export_logs_relative_time: export raw logs over a relative window
- Example:
export error logs from the last 30 minutes for app "my-app-frontend"
- Example:
- export_logs_time_range: export raw logs between specific timestamps
- Example:
export logs from 2025-01-01T10:00:00Z to 2025-01-01T11:00:00Z with level error
- Example:
- list_pipelines: list all pipelines
- Example:
list all my pipelines
- Example:
- get_pipeline: get details for a pipeline by ID
- Example:
show me details for pipeline <pipeline id>
- Example:
Best Practices
- Start broad for root-cause analysis
- If the query is too narrow, our RCA can't do its thing. Cast a wide net, and if needed, specify app/service/level in subsequent queries.
- Prefer analyze_logs_for_root_cause or deduplicate_log tools for insights
- These tools deduplicate and groups similar logs for better summaries, allowing the results to fit into finite LLM context windows.
- Use relative time ranges
- Prefer values like
last_15_minutes,last_hourwhen supported.
- Prefer values like
- Keep prompts simple; add filters gradually
- Add
app,host,level, andqueryfilters step by step.
- Add
- Use export_logs for raw data only
- For dashboards or offline analysis, use
export_logs; otherwise prefer RCA.
- For dashboards or offline analysis, use
Installation
Requirements
- A Mezmo Service Key (generate one in your Mezmo dashboard under Settings > API Keys; see Mezmo docs for details)
- Node.js ≥ 18 (only needed for clients that use the
mcp-remotebridge) - One of the supported MCP clients below
For every client we follow a simple rule:
- Supports remote URL? → configure it with a
urlthat points tohttps://mcp.mezmo.com/mcpand include theAuthorizationheader. - StdIO-only client? → use the
mcp-remotebridge:
AUTH_HEADER="Bearer <SERVICE KEY>" npx mcp-remote https://mcp.mezmo.com/mcp \
--header "Authorization:${AUTH_HEADER}"
Client Configurations
Expand a section below to see setup instructions for your preferred editor or tool.
Cursor natively supports remote MCP servers, so you only need a remote configuration.
Clicking the Install MCP Server badge opens Cursor and automatically adds the mezmo entry to your ~/.cursor/mcp.json with a placeholder for the Service Key. After it’s created, edit the file and replace <SERVICE KEY> with your actual Mezmo service key. Restart Cursor for changes to take effect. The final configuration should look like the example below.
{
"mcpServers": {
"mezmo": {
"url": "https://mcp.mezmo.com/mcp",
"headers": {
"Authorization": "Bearer <SERVICE KEY>"
}
}
}
}
Windsurf also supports remote servers via the serverUrl field.
{
"mcpServers": {
"mezmo": {
"serverUrl": "https://mcp.mezmo.com/mcp",
"headers": {
"Authorization": "Bearer <SERVICE KEY>"
}
}
}
}
{
"mcpServers": {
"mezmo": {
"url": "https://mcp.mezmo.com/mcp",
"headers": {
"Authorization": "Bearer <SERVICE KEY>"
}
}
}
}
VS Code’s Copilot Chat supports remote MCP servers with HTTP transport.
"mcp": {
"servers": {
"mezmo": {
"type": "http",
"url": "https://mcp.mezmo.com/mcp",
"headers": {
"Authorization": "Bearer <SERVICE KEY>"
}
}
}
}
{
"mcp": {
"servers": {
"mezmo": {
"type": "http",
"url": "https://mcp.mezmo.com/mcp",
"headers": {
"Authorization": "Bearer <SERVICE KEY>"
}
}
}
}
}
Zed does not support remote URLs yet, so use the mcp-remote bridge.
{
"context_servers": {
"Mezmo": {
"command": {
"path": "npx",
"args": [
"mcp-remote",
"https://mcp.mezmo.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer <SERVICE KEY>"
}
},
"settings": {}
}
}
}
{
"mcpServers": {
"mezmo": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.mezmo.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer <SERVICE KEY>"
}
}
}
}
Claude Code supports remote URLs:
claude mcp add --transport http mezmo https://mcp.mezmo.com/mcp \
--header "Authorization: Bearer <SERVICE KEY>"
{
"mcpServers": {
"Mezmo": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.mezmo.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer <SERVICE KEY>"
}
}
}
}
{
"mcpServers": {
"mezmo": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.mezmo.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer <SERVICE KEY>"
}
}
}
}
{
"mcpServers": {
"mezmo": {
"command": "cmd",
"args": [
"/c",
"npx",
"mcp-remote",
"https://mcp.mezmo.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer <SERVICE KEY>"
}
}
}
}
Add a new MCP and enter:
AUTH_HEADER="Bearer <SERVICE KEY>" npx mcp-remote https://mcp.mezmo.com/mcp \
--header "Authorization:${AUTH_HEADER}"
Roo Code supports remote URLs:
{
"mcpServers": {
"mezmo": {
"type": "streamable-http",
"url": "https://mcp.mezmo.com/mcp",
"headers": {
"Authorization": "Bearer <SERVICE KEY>"
}
}
}
}
{
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.mezmo.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer <SERVICE KEY>"
}
}
{
"mcpServers": {
"mezmo": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.mezmo.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer <SERVICE KEY>"
}
}
}
}
Qodo Gen supports remote URLs:
{
"mcpServers": {
"mezmo": {
"url": "https://mcp.mezmo.com/mcp",
"headers": {
"Authorization": "Bearer <SERVICE KEY>"
}
}
}
}
{
"mcpServers": {
"mezmo": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.mezmo.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer <SERVICE KEY>"
}
}
}
}
{
"Mezmo": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.mezmo.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer <SERVICE KEY>"
},
"working_directory": null,
"start_on_launch": true
}
}
Opencode supports remote URLs:
"mcp": {
"mezmo": {
"type": "remote",
"url": "https://mcp.mezmo.com/mcp",
"headers": {
"Authorization": "Bearer <SERVICE KEY>"
},
"enabled": true
}
}
Add to ~/.codex/config.toml:
[mcp_servers.mezmo]
command = "npx"
args = [
"mcp-remote",
"https://mcp.mezmo.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}",
]
env = { AUTH_HEADER = "Bearer <SERVICE KEY>" }
Codex defaults to being sandboxed, so you'll also need to give it network access. If you want to run in a sandbox mode of workspace-write for example, add this:
[sandbox_workspace_write]
network_access = true
You can either start with a flag like codex --sandbox workspace-write or set a default mode with:
sandbox_mode = "workspace-write"
Troubleshooting
1. npx argument-escaping bug
Some clients pass command-line arguments to npx without quoting spaces. This can split the Authorization header (e.g. Bearer and the token become separate arguments) and cause authentication failures.
Work-around: store the header in an environment variable and pass it without spaces:
{
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.mezmo.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer <SERVICE KEY>"
}
}
2. Lost connection to the Mezmo MCP server
If your client shows an error such as “server disconnected” or stops responding to MCP commands:
- Disable or remove the Mezmo MCP entry in your client settings.
- Re-enable (or re-add) the same entry, or simply restart the client.
This forces the client to establish a fresh connection to the Mezmo MCP backend.
3. 401/403 authentication errors
- Verify the
Authorizationheader is present and formatted asBearer <SERVICE KEY>. - If using
npx mcp-remote, prefer the environment variable approach to avoid splitting the header. - Regenerate your Service Key in Mezmo and try again if issues persist.
Next Steps
Once your client is configured you can immediately run natural-language commands such as
analyze my logs from the last 30 minutes and determine root cause for any issues that you findlist all my pipelinesshow me details for pipeline <pipeline title>export error logs from the last 30 minutes for app "my-app-frontend"
Enjoy streamlined observability with Mezmo + AI! 🎉
Related Servers
Claude Code Exporter
Export and organize Claude Code conversations with powerful filtering. Supports CLI and MCP server integration for Claude Desktop.
MicroShift Test Analyzer
Analyzes MicroShift test failures from Google Sheets to correlate them with specific MicroShift versions.
WinCC Unified MCP XT
An MCP server for interfacing with SIEMENS WinCC Unified SCADA systems via their GraphQL API.
EVM MCP Server
Provides blockchain services for over 30 EVM-compatible networks through a unified interface.
Kontxt
Indexes local code repositories to provide codebase context to AI clients.
Universal MCP Server
A universal MCP server with a modular plugin architecture.
MCP API Bridge
A server that bridges Google Sheets, Azure AI, and MQTT APIs.
Projet MCP Server-Client
An implementation of the Model Context Protocol (MCP) for communication between AI models and external tools, featuring server and client examples in Python and Spring Boot.
MediaWiki MCP Server
Enables LLM clients to interact with any MediaWiki wiki using the Model Context Protocol.
Code Runner MCP
Execute JavaScript and Python code in a secure sandbox. Supports Deno for JS/TS and Pyodide for Python, with configurable permissions.