@belal-elsabbagh-apex/copilot-mcp
Enables EHR Copilot operations such as order cloning, queue building, and execution trace analysis over stdio.
README
@belal-elsabbagh-apex/copilot-mcp
MCP server exposing EHR Copilot operations over stdio. Built with Bun
(bun build bundles src/ → a node-runnable dist/server.js), so it runs under either
bunx or npx. Published as a private package on GitHub Packages.
Tools
| Tool | What it does |
|---|---|
clone_order |
Mirror PROD order(s) into PRE-PROD as fresh orders (clone-only by default; submit is opt-in). |
find_clone_candidates |
List recent PROD orders that will actually clone to forReview. |
delete_preprod_order |
Delete order(s) from PRE-PROD (never touches prod). |
build_queue_item |
Build a UiPath AddQueueItem request (payload + curl) from an order. BUILD ONLY — IsApproved is always false. |
analyze_order_execution |
Trace an order to its UiPath Orchestrator job(s) and diagnose the run. READ-ONLY. |
Configuration
The server reads one validated config holding both the Copilot BE creds and the UiPath args. Two ways to provide it:
- Single file (preferred): set
COPILOT_MCP_CONFIGto a JSON file shaped likeconfig.example.json. - Split legacy files: set
COPILOT_MCP_LOCAL_DIRto a directory containingorder-copy-credentials.json+uipath-config.json(+ optionaloverrides.json).
The uipath.noteBucket / queueUrl / addQueueItemPath / serverUrlByEnv fields are only
required by build_queue_item. overrides (per-prodUid clone remaps) is optional.
Other env vars: COPILOT_MCP_DEBUG_DIR (where clone_order dumps the extracted prod
order JSON; defaults to the OS temp dir).
Local development
bun install
bun run typecheck
bun run build # bundle src -> dist/server.js (node-runnable, what npx/bunx execute)
bun run start # run from source via bun (no build needed)
bun run dev # watch mode
Installing from GitHub Packages (private)
The package is private, so installing requires a GitHub token with read:packages.
Add to the consumer repo's .npmrc:
@belal-elsabbagh-apex:registry=https://npm.pkg.github.com
//npm.pkg.github.com/:_authToken=${NODE_AUTH_TOKEN}
Then export NODE_AUTH_TOKEN=<your PAT> and install:
bun add -d @belal-elsabbagh-apex/copilot-mcp
Wire into .mcp.json
{
"mcpServers": {
"copilot": {
"command": "npx",
"args": ["-y", "@belal-elsabbagh-apex/copilot-mcp"],
"env": {
"COPILOT_MCP_CONFIG": "/abs/path/to/config.local.json"
}
}
}
}
npx and bunx are interchangeable here (the published bin, dist/server.js, is a
plain node ESM entry). Use COPILOT_MCP_LOCAL_DIR instead of COPILOT_MCP_CONFIG for
the split legacy files.
Publishing
Publishing is tag-driven. Bump version in package.json, commit, then push a matching
vX.Y.Z tag:
git tag v1.2.0
git push origin v1.2.0
That one tag push fans out to two workflows (both keyed off the tag, because a
GITHUB_TOKEN-created release does not trigger other workflows):
- Release on tag (
release.yml) — creates a GitHub Release with auto-generated notes. - Publish (
publish.yml) — typechecks, builds, and runsbun publish --access restrictedusing the repo'sGITHUB_TOKEN(packages: write), keeping the package private. Also runnable manually via workflow_dispatch.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.