What is the PBS API rate limit?
The PBS Public API is rate-limited to one request per 20 seconds. This limit is shared among all users of the public API.
@matthewdcage
Basic information
Australian Pharmaceutical Benefits Scheme PBS API Server using Anthropic MCP with natural language LLM integration
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A standalone Model Context Protocol (MCP) server that allows AI models to access the Australian Pharmaceutical Benefits Scheme (PBS) API, which contains information about medicines, pricing, and availability in Australia. It is built for the public PBS API but can be adapted to the private API if developer access has been granted.
Clone the repository, install dependencies with npm install, and build with npm run build. Run the server in stdio mode (npm start), HTTP/SSE mode (npm run start:http), or as a command-line tool (npm run cli -- <command>). Configure an MCP client (e.g., Claude Desktop) by providing the path to the built server and your PBS API subscription key in the client’s mcpServers configuration.
The PBS Public API is rate-limited to one request per 20 seconds. This limit is shared among all users of the public API.
Yes. The tool uses a subscription key for accessing the PBS API. You can obtain a key by registering on the PBS Data API Portal at https://data-api-portal.health.gov.au/ and subscribing to the PBS Public API v3 product.
Only the current schedule and those published in the past 12 months are available via the Public API. Some endpoints require specific parameters, and the API structure may change over time.
Yes. The project is built for the public API but can easily be adapted to the private API if you have been granted developer access.
The server supports both stdio and HTTP/SSE transport layers. It can run as a standard MCP server in stdio mode or as an HTTP server with Server-Sent Events for real-time tool events.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
Comments