Read-only Medplum chart search and patient context for MCP clients.
Read-only Medplum chart search and patient context for MCP clients.
Five FHIR backends sit behind one interface. This repository is the reference implementation: bring your own FHIR backend and model key for a real agent (Medplum for the authenticated path, or any verified adapter for synthetic evaluation), or start with the zero-key local synthetic walkthrough.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"last-ehr": {
"command": "npx",
"args": ["-y", "@lastehr/agent-write-conformance"],
"env": {
"OPENAI_API_KEY": "your-value",
"ANTHROPIC_API_KEY": "your-value",
"MODEL_ID": "your-value",
"NEXT_PUBLIC_MEDPLUM_BASE_URL": "your-value",
"MEDPLUM_BASE_URL": "your-value",
"MEDPLUM_CLIENT_ID": "your-value",
"MEDPLUM_CLIENT_SECRET": "your-value",
"NEXT_PUBLIC_MEDPLUM_GOOGLE_CLIENT_ID": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
| ANTHROPIC_API_KEY | Credential the server authenticates with. | Yes |
| MODEL_ID | Configuration value read at startup. | Optional |
| NEXT_PUBLIC_MEDPLUM_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| MEDPLUM_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| MEDPLUM_CLIENT_ID | Configuration value read at startup. | Optional |
| MEDPLUM_CLIENT_SECRET | Credential the server authenticates with. | Yes |
| NEXT_PUBLIC_MEDPLUM_GOOGLE_CLIENT_ID | Configuration value read at startup. | Optional |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Model Context Protocol server for Anki - enables AI assistants to interact with your Anki flashcards
MCP server for DeepSeek V4 (v4-flash, v4-pro, 1M context): chat, reasoning, function calling, thinking mode, cost tracking. deepseek-chat/reasoner
Your coding assistant writes a mock and calls it done. It invents an SDK call that doesn't exist. It ships an N+1 loop that passes every test and dies under load. Verificate MCP runs the deep review pass on every AI…
mcp-name: io.github.jlucasmcrell/apify-scrapers Apify Public Data MCP: 40 Production Data Tools & Public Records