Cross-references internal Firestore unit listings and securely saves digital signature PNGs to Firebase Storage for parcel management.
Processes incoming parcel label scans using Google Cloud Vision OCR to extract and parse label text.
Schedules and sends automated email alerts for incoming parcels via SendGrid.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Trackkr MCP Server Log an Amazon package for unit 4B and notify the resident."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol server that enables AI agents to autonomously manage incoming packages, log parcels, cross-reference unit directories, and track pick-up signatures without physical locker hardware.
Website: https://trackkr.app
Glama MCP Endpoint: https://glama.ai/endpoints/xuvltpe45j/mcp
Direct MCP Endpoint: https://trackkr.app/mcp
Repository: https://github.com/DTLA-Professional-Services-LLC/trackkr-mcp
License: MIT
get_pending_parcels: Fetches the current ledger of uncollected packages, highlights aging stats (5+ days), and returns structured JSON context.
log_incoming_parcel: Accepts parsed text from Google Cloud Vision OCR label scans and/or external photoUrl links (automatically downloaded and hosted on Firebase Storage), cross-references internal Firestore unit listings, and schedules automated email alerts via SendGrid and US (+1) SMS alerts via the Quo Phone API.
release_parcel_with_signature: Updates parcel state to Picked Up, records the timestamp, and securely saves the digital signature PNG layout to Firebase Storage.
Related MCP server: Property MCP Server
Variable | Required | Description |
| Yes | Path to your authorized Firebase service account credentials (or stringified JSON). |
| No | Set to |
npxFIREBASE_CONFIG_JSON="./service-account.json" \
USE_MOCK_OCR="true" \
npx -y github:DTLA-Professional-Services-LLC/trackkr-mcpclaude_desktop_config.json{
"mcpServers": {
"trackkr-mcp": {
"command": "npx",
"args": ["-y", "github:DTLA-Professional-Services-LLC/trackkr-mcp"],
"env": {
"FIREBASE_CONFIG_JSON": "/path/to/service-account.json",
"USE_MOCK_OCR": "true"
}
}
}
}Fetches the current ledger of uncollected packages, highlights aging stats (5+ days), enriches each with occupant contact preferences and notification/telemetry history, and returns structured JSON context.
Inputs: businessId, maxResults, emitTelemetry, thresholdDays.
Accepts parsed text from Google Cloud Vision OCR label scans and/or a trusted Firebase Storage photoUrl, cross-references internal Firestore unit listings, enforces a 4-hour idempotent lock on (trackingNumber + unitId), and schedules automated email alerts via SendGrid.
Inputs: businessId (required), qty, notes, unitId, +9 more.
Updates parcel state to Picked Up, records the pickup timestamp and recipient name, securely saves the digital signature PNG layout to Firebase Storage, and emits a PARCEL_RELEASED telemetry event.
Inputs: parcelId (required), businessId (required), pickedUpBy (required), datePickedUp, +4 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool targets a distinct parcel lifecycle stage: viewing pending parcels, logging incoming parcels, and releasing parcels with signature. There is no meaningful overlap in purpose or resource, so an agent can easily select the right tool.
All tool names use snake_case with a leading verb and a parcel-related noun (get_pending_parcels, log_incoming_parcel, release_parcel_with_signature). The pattern is predictable, and the third tool's modifier does not disrupt readability.
Three tools is lean but reasonable for a focused intake-to-release workflow. It is slightly under-scoped for a parcel-tracking domain that likely benefits from additional query and update operations.
The core lifecycle is covered: log incoming, list pending, and release with signature. However, there are notable gaps such as getting a parcel by ID, listing full history/all parcels, updating parcel details, canceling/deleting, and managing notifications or units.
AI open-house assistant for agents: sign-in kiosk + automated, consent-aware follow-ups.
Verified location-bound retail evidence for AI agents, delivered by human field workers.
Email inboxes for AI agents. Send, receive, and read email with a trust report on every message.
Give AI agents secure access to your email via private aliases with dedicated mailbox storage.
