What does this server simulate?
It simulates FHIR operations by returning the HTTP request that would have been made (e.g., `GET https://fhir.example.com/Patient/123` or a POST with body) instead of actually calling a FHIR API.
@mike-holcomb
基本情報
An implementation of Model Context Protocol server for use with MedAgentBench (FHIR request generation)
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
A Python-based MCP server that simulates FHIR API interactions for the MedAgentBench environment. Instead of making real HTTP requests, it returns a textual representation of the HTTP request that would have been made, enabling testing of MedAgentBench agents without a live FHIR endpoint.
Install with Poetry (requires Python >= 3.10). Set the FHIR_BASE_URL environment variable to your desired FHIR server base URL. Run fhir-mcp-server-medagentbench to start the server, which listens for MCP requests over standard input/output.
It simulates FHIR operations by returning the HTTP request that would have been made (e.g., `GET https://fhir.example.com/Patient/123` or a POST with body) instead of actually calling a FHIR API.
You need Python >= 3.10 and Poetry. The server depends on the `mcp-server` library and requires the `FHIR_BASE_URL` environment variable to be set.
No external data is fetched. The server only returns textual request representations based on the configured `FHIR_BASE_URL`. There is no actual FHIR resource storage.
The server communicates over standard input/output for MCP. No authentication or specific transport options are mentioned.
Currently the simulated resources only include `CapabilityStatement`; the server does not make real network requests and only returns request strings.
A search tool helps dev to solve the naming things problem.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
A curated list of references for MLOps
コメント