About Perfrunner MCP Server
Perfrunner MCP Server is a prototype for querying static perfrunner test and cluster configurations. It is aimed at performance teams working with infrastructure configuration data stored in Couchbase.
Key features
- 01Access test configurations
- 02Access cluster configurations
- 03Store configurations and results in Couchbase
- 04Use full-text search
Use cases
- 01Look up a perfrunner test configuration
- 02Inspect cluster configuration data
- 03Search stored performance configuration records
MCP support
Provides MCP access to perfrunner configuration information, including test and cluster configurations.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEPerfrunner MCP Server
A Model Context Protocol (MCP) that provide info on the perfrunner static configurations. i.e test and cluster configurations.
Overview
Prototype and toy playground for an MCP server to talk with perf team's infrastructure.
Features
- Integrates with Couchbase server for storing test configurations and results
- Backed by Full Text Search (FTS)
- Basic MCP
Configuration
Create a .env file in the project root with necessary configuration (you can copy and modify the provided .env.example file):
cp .env.example .env
# Edit the .env file with your specific configuration
Running the MCP Server
make
Loading Data
scripts/configs_to_server.py is used to load .test and .spec files into your Couchbase server cluster.
To load test files, use:
uv run scripts/configs_to_server.py test path/to/my/test-directory/
And to load cluster spec use:
uv run scripts/configs_to_server.py cluster path/to/my/cluster-spec-directory/
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.