This module provides APIs for building MCP (Model Context Protocol) clients and servers in Ballerina.
MCP is an open standard that enables seamless integration between Large Language Models (LLMs) and external data sources, tools, and services. It facilitates structured communication through JSON-RPC 2.0 over HTTP transport, allowing AI applications to access and interact with external capabilities in a standardized way.
The Ballerina MCP library implements both client and server-side functionality, supporting automatic tool discovery, type-safe schema generation, flexible session management (STATEFUL, STATELESS, AUTO modes), and streamable HTTP transport with Server-Sent Events (SSE) for bidirectional communication.
Issues and Projects tabs are disabled for this repository as this is part of the Ballerina Library. To report bugs, request new features, start new discussions, view project boards, etc., go to the Ballerina Library parent repository. This repository only contains the source code for the module.
-
Download and install Java SE Development Kit (JDK) version 21 (from one of the following locations).
-
Generate a GitHub access token with read package permissions, then set the following
envvariables:export packageUser=<Your GitHub Username> export packagePAT=<GitHub Personal Access Token>
Execute the commands below to build from the source.
-
To build the package:
./gradlew clean build
-
To run the tests:
./gradlew clean test -
To run a group of tests
./gradlew clean test -Pgroups=<test_group_names>
-
To build the without the tests:
./gradlew clean build -x test -
To debug the package with a remote debugger:
./gradlew clean build -Pdebug=<port>
-
To debug with Ballerina language:
./gradlew clean build -PbalJavaDebug=<port>
-
Publish the generated artifacts to the local Ballerina central repository:
./gradlew clean build -PpublishToLocalCentral=true
-
Publish the generated artifacts to the Ballerina central repository:
./gradlew clean build -PpublishToCentral=true
As an open-source project, Ballerina welcomes contributions from the community.
For more information, go to the contribution guidelines.
All the contributors are encouraged to read the Ballerina Code of Conduct.
- For more information go to the
mcplibrary. - Chat live with us via our Discord server.
- Post all technical questions on Stack Overflow with the #ballerina tag.