{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_cgg73xpt7gr3","handle":"mcp-jadwal-dokter","url":"https://wellknown.network/agents/mcp-jadwal-dokter","links":{"self":"https://wellknown.network/agents/mcp-jadwal-dokter/record.json","html":"https://wellknown.network/agents/mcp-jadwal-dokter","markdown":"https://wellknown.network/agents/mcp-jadwal-dokter/record.md","api":"https://wellknown.network/api/v1/agents/mcp-jadwal-dokter","status":"https://wellknown.network/api/v1/agents/mcp-jadwal-dokter/status","claim":"https://wellknown.network/agents/mcp-jadwal-dokter/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-jadwal-dokter/claim.json","badge":"https://wellknown.network/agents/mcp-jadwal-dokter/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-jadwal-dokter/history","tools":"https://wellknown.network/api/v1/agents/mcp-jadwal-dokter/tools"},"ard":{"identifier":"urn:air::server:mcp-jadwal-dokter","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-jadwal-dokter","summary":"MCP server exposing dummy Indonesian hospital doctor-scheduling tools","description":"# mcp-jadwal-dokter \n \nAn MCP (Model Context Protocol) server that exposes dummy hospital doctor-scheduling \ntools: search doctors, read a schedule, check open slots, and make a booking. It is \nbuilt to be driven by an LLM agent, and it ships as a pip package that runs over stdio \nwith one command. \n \nThe server is deterministic: data plus tools, no model and no API key. That is the \npoint. An MCP server is the tool layer; the model lives in the client. A separate \nStreamlit demo (in `demo/`) lets an LLM drive these tools in an agentic chat, for \nexample to find a pediatrician free on Thursday afternoon and book the slot. \n \nThis is a portfolio project (project 11 of a larger set). `PLAN.md` is the full build \nplan and design record. \n \n## Architecture \n \n```mermaid \nflowchart LR \n    User -->|chat| Streamlit \n    Streamlit -->|asyncio.run per turn| Agent[Agent loop] \n    Agent <-->|prompt plus tools / tool calls| LLM[LLM provider<br/>Anthropic or OpenRouter] \n    Agent <-->|stdio MCP| Server[jadwal-dokter MCP server] \n    Server --> Tools[search_doctors / get_schedule<br/>check_slot / create_booking] \n    Tools --> Seed[(doctors.json, read-only)] \n    Tools --> DB[(SQLite bookings)] \n``` \n \nEverything from the MCP server rightward is the published package and needs no key. \nThe LLM and the Streamlit client are the demo, and only they read an API key. Each user \nturn opens one stdio session to the server, runs the tool-calling loop, and closes it. \n \n## Tools \n \nEight tools, plus resources and a prompt: \n \n| Tool | What it does | \n|------|--------------| \n| `get_today()` | The server's date and weekday, so an agent resolves relative phrases (\"next Thursday\") against the server clock. | \n| `search_doctors(specialization?, name?, day?)` | Find doctors by specialization, name substring, and/or practice day. Filters are optional and combine with AND. | \n| `get_schedule(doctor_id)` | A doctor's weekly practice blocks and any leave periods. | \n| `check_slot(doctor_id, da…","publisher":{"name":"Christian Miracle Rumawung","url":null},"homepage":"https://mirecodex.my.id","repository":null,"version":"0.2.0","license":"MIT","protocols":["mcp"],"tags":["mcp","model-context-protocol","healthcare","scheduling","llm","tools","agent"],"pricing":null,"endpoints":[{"url":"pypi:mcp-jadwal-dokter","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"productivity.calendar","name":"Calendar & Scheduling","confidence":1,"provenance":"declared"},{"slug":"ai.model-access","name":"Model Access","confidence":0.894,"provenance":"derived"}],"categories":["ai","productivity"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-jadwal-dokter","registry":"pypi","observedAt":"2026-11-03T14:23:44.664Z","publishedAt":"2026-07-08T14:31:08.017901Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-jadwal-dokter","url":"https://pypi.org/project/mcp-jadwal-dokter/","firstSeenAt":"2026-09-10T02:22:58.826Z","fetchedAt":"2026-11-03T14:21:33.709Z","normalizedAt":"2026-11-03T14:21:33.709Z"}]},"firstSeenAt":"2026-09-10T02:22:58.826Z","updatedAt":"2026-11-03T14:23:44.664Z"}