- Explore MCP Servers
- jaeger-mcp-server
Jaeger Mcp Server
What is Jaeger Mcp Server
jaeger-mcp-server is a specialized MCP Server designed for integration with Jaeger, a popular open-source distributed tracing system. It facilitates the collection and management of trace data in a microservices architecture.
Use cases
Use cases for jaeger-mcp-server include monitoring microservices performance, troubleshooting latency issues in distributed systems, and visualizing trace data for better observability.
How to use
To use jaeger-mcp-server, you need to install it in your environment, configure it to connect with your Jaeger instance, and then start the server. Detailed instructions can typically be found in the project’s README or documentation.
Key features
Key features of jaeger-mcp-server include seamless integration with Jaeger, support for high-throughput trace data processing, and the ability to manage microservices tracing efficiently.
Where to use
jaeger-mcp-server is primarily used in environments that utilize microservices architecture, particularly in applications requiring distributed tracing for performance monitoring and debugging.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Jaeger Mcp Server
jaeger-mcp-server is a specialized MCP Server designed for integration with Jaeger, a popular open-source distributed tracing system. It facilitates the collection and management of trace data in a microservices architecture.
Use cases
Use cases for jaeger-mcp-server include monitoring microservices performance, troubleshooting latency issues in distributed systems, and visualizing trace data for better observability.
How to use
To use jaeger-mcp-server, you need to install it in your environment, configure it to connect with your Jaeger instance, and then start the server. Detailed instructions can typically be found in the project’s README or documentation.
Key features
Key features of jaeger-mcp-server include seamless integration with Jaeger, support for high-throughput trace data processing, and the ability to manage microservices tracing efficiently.
Where to use
jaeger-mcp-server is primarily used in environments that utilize microservices architecture, particularly in applications requiring distributed tracing for performance monitoring and debugging.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
Jaeger MCP Server
MCP Server for Jaeger.
Prerequisites
- Node.js 18+
Quick Start
This MCP server (using STDIO transport) can be added to any MCP Client
like VS Code, Claude, Cursor, Windsurf Github Copilot via the jaeger-mcp-server NPM package.
VS Code
{
"servers": {
"jaeger-mcp-server": {
"command": "npx",
"args": [
"-y",
"jaeger-mcp-server"
],
"envFile": "${workspaceFolder}/.env"
}
}
}
Claude Desktop
{
"mcpServers": {
"jaeger-mcp-server": {
"command": "npx",
"args": [
"-y",
"jaeger-mcp-server"
],
"env": {
"JAEGER_URL": "<YOUR_JAEGER_HTTP_OR_GRPC_API_URL>"
}
}
}
}
Configuration
Environment Variables
JAEGER_URL: HTTP API (HTTP JSON(/api/v3/*)) or the gRPC API (gRPC/Protobuf(jaeger.api_v3.QueryService)) URL of the Jaeger instance to access.JAEGER_PORT: HTTP or gRPC API port of the Jaeger instance to access. The default value is16685for the gRPC API and16686for the HTTP API.JAEGER_AUTHORIZATION_HEADER:AuthorizationHTTP header to be added into the requests for querying traces over Jaeger API (for ex.Basic <Basic Auth Header>)JAEGER_PROTOCOL: API protocol of the Jaeger instance to access. Valid values areGRPCandHTTP. The default value isGRPC. Valid
Components
Tools
get-operations: Gets the operations as JSON array of object withnameandspanKindproperties.
Supports the following input parameters:service:Mandatory:trueType:stringDescription: Filters operations by service name
spanKind:Mandatory:falseType:stringDescription: Filters operations by OpenTelemetry span kind (server,client,producer,consumer,internal)
get-services: Gets the service names as JSON array of string.
No input parameter supported.get-trace: Gets the spans by the given trace by ID as JSON array of object in the OpenTelemetry resource spans format.traceId:Mandatory:trueType:stringDescription: Filters spans by OpenTelemetry compatible trace id in 32-character hexadecimal string format
startTime:Mandatory:falseType:stringDescription: The start time to filter spans in the RFC 3339, section 5.6 format, (e.g.,2017-07-21T17:32:28Z)
endTime:Mandatory:falseType:stringDescription: The end time to filter spans in the RFC 3339, section 5.6 format, (e.g.,2017-07-21T17:32:28Z)
find-traces: Searches the spans as JSON array of object in the OpenTelemetry resource spans format.serviceName:Mandatory:trueType:stringDescription: Filters spans by OpenTelemetry compatible trace id in 32-character hexadecimal string format
operationName:Mandatory:falseType:stringDescription: The start time to filter spans in the RFC 3339, section 5.6 format, (e.g.,2017-07-21T17:32:28Z)
attributes:-
Mandatory:false -
Type:map<string, string | number | boolean> -
Description: Filters spans by span attributes. Attributes can be passed in key/value format in JSON where
keys can be string and values can be string, number (integer or double) or boolean.
For example
-
startTimeMin:Mandatory:trueType:stringDescription: Start of the time interval (inclusive) in the RFC 3339, section 5.6 format, (e.g.,2017-07-21T17:32:28Z) for the query.
Only traces with spans that started on or after this time will be returned.
startTimeMax:Mandatory:trueType:stringDescription: End of the time interval (exclusive) in the RFC 3339, section 5.6 format, (e.g.,2017-07-21T17:32:28Z) for the query.
Only traces with spans that started before this time will be returned.
durationMin:Mandatory:falseType:stringDescription: Minimum duration of a span in milliseconds in the trace.
Only traces with spans that lasted at least this long will be returned.
durationMax:Mandatory:falseType:stringDescription: Maximum duration of a span in milliseconds in the trace.
Only traces with spans that lasted at most this long will be returned.
searchDepth:Mandatory:falseType:numberDescription: Defines the maximum search depth.
Depending on the backend storage implementation, this may behave like an SQLLIMITclause.
However, some implementations might not support precise limits
and a larger value generally results in more traces being returned.
Resources
N/A
Roadmap
- Support
HTTP Streamtransport protocol (SSEtransport protocol is deprecated in favor of it) to be able to use the MCP server from remote. - Support more tools which are not directly available over Jaeger API (orchestrating and pipelining multiple API endpoints)
Issues and Feedback
Please use GitHub Issues for any bug report, feature request and support.
Contribution
If you would like to contribute, please
- Fork the repository on GitHub and clone your fork.
- Create a branch for your changes and make your changes on it.
- Send a pull request by explaining clearly what is your contribution.
Tip:
Please check the existing pull requests for similar contributions and
consider submit an issue to discuss the proposed feature before writing code.
License
Licensed under MIT.
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.










