Click on "Install 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., "@postnord-mcp Where is my package 84971563697SE?"
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.
An MCP (Model Context Protocol) server for PostNord's REST APIs. Lets AI assistants like Claude track shipments, find pickup points, and estimate transit times across the Nordics (Sweden, Norway, Denmark, Finland).
You: Where is my package 84971563697SE?
Claude: → track_shipment("84971563697SE")
Your package left the Oslo terminal this morning and is expected
at your pickup point tomorrow between 08:00 and 16:00.Tool | Description |
| Track a shipment by shipment ID, item ID (parcel number), or customer reference. Returns full event history and estimated delivery. |
| Find the nearest pickup/drop-off points by address or postal code, with opening hours. |
| Same, but by latitude/longitude. |
| Estimate delivery time between two postal codes for a given PostNord service code. |
Related MCP server: Parcel MCP Server
Node.js 18+
A PostNord API key — free. All PostNord API plans are free of charge; the key is emailed to you after you register for a plan. Which registration to use depends on whether you have a company/organization number (see below).
PostNord's developer portal is business-oriented. There is no consumer plan — every option authenticates with an API key sent as the apikey query parameter, but the registration paths differ:
Path | Where | Needs org number? | Real shipment data? | Environment |
Sandbox | No — "Company Name" is free text | No (test data only) |
| |
Customer / Partner Plan | Yes | Yes |
|
Sandbox is the quickest way to verify the server works end to end. The signup form only asks for a name, email, username, and password; set POSTNORD_SANDBOX=true (see Configuration) to point the server at the test host.
Customer Plan vs Partner Plan — both are free. "Customer" is for using the APIs for your own business; "Partner" is for building a platform that serves other PostNord customers. Both require a company name and organization number at signup. If you run a sole proprietorship you already have an org number and can use the Customer Plan.
No company? For real (non-sandbox) tracking without an organization number, email api.support@postnord.com and ask whether the free Customer Plan can be granted to an individual/hobby project.
The Booking API requires a separate business agreement and OAuth2 client credentials, and is not included in this server.
git clone https://github.com/fredrsat/postnord-mcp.git
cd postnord-mcp
npm install
npm run buildAdd to your claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"postnord": {
"command": "node",
"args": ["/path/to/postnord-mcp/dist/index.js"],
"env": {
"POSTNORD_API_KEY": "your-api-key"
}
}
}
}claude mcp add postnord --env POSTNORD_API_KEY=your-api-key -- node /path/to/postnord-mcp/dist/index.jsThe server speaks MCP over stdio. Start it with POSTNORD_API_KEY set:
POSTNORD_API_KEY=your-api-key node dist/index.jsAll configuration is via environment variables:
Variable | Required | Default | Description |
| ✅ | — | Your API key from the developer portal |
|
| Set to | |
|
| Override the API base URL entirely | |
|
| Language for human-readable strings: |
Once connected, try asking your assistant:
"Track package 84971563697SE"
"Where's the nearest PostNord pickup point to Karl Johans gate 1, Oslo?"
"Find service points near postal code 111 20 in Sweden"
"How long does MyPack Collect take from 0150 Oslo to 5003 Bergen?"
PostNord authenticates with the API key as an apikey query parameter on every request.
Tracking uses Track & Trace v5 (/rest/shipment/v5/trackandtrace/findByIdentifier.json); service points use Business Location v5.
The transit time endpoint varies by plan and agreement — if get_transit_time returns a 404, check the exact path in the swagger spec under your account on the developer portal and adjust src/postnord.ts.
Rate limits depend on your plan (Sandbox / Free / Premium). API errors are returned to the model as tool errors with the response body included, so the assistant can explain what went wrong.
npm run dev # tsc --watch
npm run build # compile to dist/The code is small on purpose: src/postnord.ts is a thin API client, src/index.ts registers the MCP tools. Adding a new PostNord endpoint is a method on the client plus a registerTool call.
You can test the server manually with the MCP Inspector:
POSTNORD_API_KEY=your-api-key npx @modelcontextprotocol/inspector node dist/index.jsBooking API support (requires a PostNord business agreement + OAuth2 client credentials)
Publish to npm for npx postnord-mcp usage
Response trimming — return curated fields instead of raw API JSON to save tokens
Contributions welcome — open an issue or PR.
This is an unofficial, community-built integration. It is not affiliated with or endorsed by PostNord AB. Use of the PostNord APIs is subject to their terms of service.
Find the nearest PostNord service points (pickup/drop-off locations) by address or postal code. Returns names, addresses, opening hours, and coordinates.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | City name, e.g. Oslo | |
| limit | No | Max number of service points to return (default: 5) | |
| postalCode | No | Postal code, e.g. 0150 | |
| streetName | No | Street name | |
| countryCode | Yes | Country to search in | |
| streetNumber | No | Street number |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions the return fields (names, addresses, opening hours, coordinates), providing some transparency, but it does not explicitly state read-only behavior, side effects, or any limitations. For a search operation, this is acceptable but not fully transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, concise and well-structured. It conveys the essential information without unnecessary detail, making it easy for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given there is no output schema, the description appropriately mentions the return fields. It explains the input method and the result content. It lacks examples or edge cases, but for a straightforward search tool, it provides sufficient context for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers 100% of parameters with descriptions. The tool description adds context by explaining 'by address or postal code' and 'nearest', which clarifies the purpose of city, streetName, streetNumber, and postalCode parameters. This goes slightly beyond the basic schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: finding nearest PostNord service points by address or postal code. It uses a specific verb ('Find'), identifies the resource ('PostNord service points'), and distinguishes from the coordinate-based sibling tool by specifying the search method.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this tool is for address/postal code searches but does not explicitly mention when to use it versus the coordinate-based alternative (find_service_points_by_coordinates). It lacks a direct statement about alternatives, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find the nearest PostNord service points (pickup/drop-off locations) by geographic coordinates (WGS84 latitude/longitude).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max number of service points to return (default: 5) | |
| latitude | Yes | Latitude in decimal degrees | |
| longitude | Yes | Longitude in decimal degrees | |
| countryCode | Yes | Country to search in |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It accurately describes a read-only lookup but does not explicitly state there are no side effects, rate limits, or special behaviors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, focused sentence that conveys the purpose without unnecessary detail or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema is provided, and the description does not mention what the result contains (e.g., distance, address, opening hours), leaving some ambiguity for a lookup tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers all parameters with descriptions, and the tool description adds important context like WGS84 coordinate system and PostNord service points. Parameter descriptions are clear and meaningful.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it finds the nearest PostNord service points by geographic coordinates, distinguishing it from sibling tools like track_shipment and find_service_points.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when coordinates are available, but does not explicitly contrast with the generic find_service_points tool or state when to choose one over the other.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Estimate PostNord transit time between two postal codes for a given service code. Service codes depend on your PostNord agreement (e.g. 19 for MyPack Collect).
| Name | Required | Description | Default |
|---|---|---|---|
| serviceCode | Yes | PostNord service code, e.g. 19 | |
| dateOfDeparture | No | Departure date as YYYY-MM-DD (default: today) | |
| originPostalCode | Yes | ||
| originCountryCode | Yes | ||
| destinationPostalCode | Yes | ||
| destinationCountryCode | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It hints at non-destructiveness via 'estimate', but does not mention authentication requirements, rate limits, error conditions, or what happens for invalid postal codes. It also does not describe the output format, which is critical since no output schema exists. The only behavioral note is that service codes depend on the agreement, but that is more of a parameter constraint than a behavioral trait.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no fluff. The core purpose is front-loaded, and the note about service codes is placed right after, which is relevant. It is concise and to the point, making it easy for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has six parameters, no output schema, and no annotations, the description is incomplete. It does not describe the return value (e.g., estimated days or a range), does not mention the optional dateOfDeparture parameter, and provides no guidance on error handling or edge cases. An agent would need to infer the output format or risk misinterpreting the result. The description covers the 'what' but not the 'so what'.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 33%, so the description must compensate for undocumented parameters. It provides an example service code (19) and explains that codes depend on the agreement, adding value. However, it does not explain the purpose of dateOfDeparture (though the schema includes its format and default) nor the postal code format. The country codes are self-evident from the enums. Overall, the description adds some meaning beyond the schema but does not fully cover the gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: estimating PostNord transit time between two postal codes for a given service code. It uses a specific verb ('estimate') and resource ('transit time'), and the scope is well-defined. The siblings are about tracking and service points, so no confusion with them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use this tool (when a transit time estimate is needed) and the context that service codes depend on the user's PostNord agreement. However, it does not explicitly state alternatives or exclusions, though the sibling tools are clearly distinct. It gives a practical example (service code 19) that helps an agent understand typical usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Track a PostNord shipment by shipment ID, item ID (parcel number), or customer reference. Returns the full tracking history with status events, estimated delivery time, and delivery details.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Shipment ID, item ID, or reference, e.g. 84971563697SE | |
| locale | No | Language for status descriptions (default: en) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses the output content (tracking history, status events, estimated delivery, details) but does not state whether the operation is read-only, any authentication requirements, rate limits, or error behavior. With no annotations to indicate safety, the description could be more explicit about side effects (e.g., 'does not modify any data').
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, direct, and free of extraneous information. It efficiently covers both the action and the expected output without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema, the description adequately covers what the tool returns (tracking history, status events, estimated delivery, delivery details). It does not detail response format or error cases, but for a tracking tool, the input requirements and high-level output are sufficient for an agent to decide on and invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds value by including a concrete example ('e.g. 84971563697SE') and clarifying that the 'id' parameter accepts multiple identifier types (shipment ID, item ID, or reference). The locale parameter's purpose and default are clearly explained, though the description largely mirrors the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: tracking a PostNord shipment by ID, item, or reference, and enumerates the returned data (tracking history, status events, estimated delivery, delivery details). It is distinct from the sibling tools, which focus on service points and transit time, not shipment status tracking.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly conveys when to use this tool (whenever a shipment's status is required) by listing the exact input types and deliverables. It does not explicitly contrast with alternatives, but the sibling tools address different needs (service points, transit time), making the intended use obvious.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0find_service_pointsfind_service_points_by_coordinatesget_transit_timetrack_shipmenttrack_shipment and get_transit_time are clearly distinct, but find_service_points and find_service_points_by_coordinates perform the same lookup with different input types. The suffix and explicit descriptions prevent serious confusion.
All tool names follow a lowercase verb_noun pattern with consistent snake_case. find_service_points_by_coordinates is longer but still fits the same convention.
Four tools is well within the ideal range and each covers a meaningful PostNord workflow: tracking, service point lookup, and transit time estimation. There is no obvious redundancy.
The set covers the core read-only PostNord use cases well, especially tracking and pickup locations. It lacks a way to enumerate valid service codes or create shipments, but those are minor gaps for typical tracking and collection queries.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Multi-carrier shipping for AI agents: compare rates, buy labels, track packages, validate addresses
Track packages across 1,300+ global carriers with real-time status and AI-powered delivery dates.
India shipping for AI agents: Shiprocket courier serviceability, create orders, track AWB.
Furgonetka MCP Server is an extension for LLMs (such as Claude) that integrates AI assistants with Poland's most popular courier brokerage platform. The server enables models to interact directly with services from various couriers (including InPost, DPD, DHL, UPS, and Poczta Polska) through a single, unified interface. With this integration, your AI stops just "writing about logistics" and starts actually managing it.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/fredrsat/postnord-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
