Global Logistics (AfterShip labels with your own carrier accounts)
Server Details
Global shipping labels for AI agents via AfterShip with your own carrier accounts.
- Status
- Unhealthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.6/5 across 4 of 4 tools scored.
Each tool has a distinct purpose: quoting rates, creating labels, canceling labels, and a help tool for tracking (which is not supported). No overlap in functionality.
All tool names follow the verb_noun pattern with snake_case, e.g., quote_rates, create_label, cancel_label, query_tracking. Consistent naming convention.
With 4 tools, the server is well-scoped for its purpose of label management via AfterShip. Each tool is essential, and there is no bloat.
The server covers quoting, creating, and canceling labels, but lacks other lifecycle operations like listing or updating labels. query_tracking intentionally not supported, but the absence of label retrieval is a notable gap.
Available Tools
4 toolscancel_labelAIdempotentInspect
Cancel / void a shipping label created via create_label, by its label_id. If the label was never used, the carrier voids it so the merchant is not charged (voidability and windows depend on the carrier). Returns cancel_status: cancelled, pending (carrier still processing) or failed. Idempotent — cancelling an already-cancelled label is safe.
| Name | Required | Description | Default |
|---|---|---|---|
| label_id | Yes | The label_id returned by create_label (AfterShip label id). |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses return states (cancelled, pending, failed), carrier-dependent voidability, and idempotency, adding significant context beyond annotations.
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?
Three concise sentences, front-loaded with action and resource, no unnecessary words.
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 low complexity (1 param, no output schema), description covers usage, returns, and caveats comprehensively.
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?
Only one parameter with schema coverage at 100%; description adds context linking label_id to create_label, but not extensive enough to rate higher.
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 action (cancel/void) and resource (shipping label) with specificity, distinguishes from siblings like create_label and query_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?
Provides context on when to use (after creation, if label unused) and notes idempotency for safety, though no explicit when-not-to-use or alternatives are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
create_labelAInspect
Buy a shipping label for a chosen service_type through the merchant's AfterShip shipper account, and return the printable label file url + tracking_number. First call quote_rates to see available service_type values, then pass that service_type here with the SAME shipper_account_id, addresses and parcel. Before purchasing, this server re-quotes the exact charge and applies the owner policy guardrails (x-agentpay-max-amount / x-agentpay-approval-above) — over the approval threshold returns an unsigned draft and buys nothing. Default env is sandbox (x-aftership-env), which generates real labels at ZERO cost; send x-aftership-env: production to buy real postage. The cost lands on the merchant's own carrier contract, not this server.
| Name | Required | Description | Default |
|---|---|---|---|
| depth | No | Parcel depth / length. | |
| items | No | Optional line items for customs (required for most INTERNATIONAL shipments). Each: {description, quantity, price_amount, price_currency, origin_country (alpha-3), weight_value, weight_unit, sku, hs_code}. | |
| width | No | Parcel width. Provide width+height+depth together (with dimension_unit), or omit all three. | |
| height | No | Parcel height. | |
| to_city | Yes | Recipient city. | |
| to_name | Yes | Recipient contact full name. | |
| to_type | No | Optional address type: "residential" or "business" (default residential). | |
| box_type | No | Parcel box type. Default "custom" (uses your dimensions). Some carriers accept named flat-rate boxes. | |
| to_email | No | Optional Recipient email. | |
| to_phone | No | Optional Recipient phone (some carriers/services require it). | |
| to_state | No | Optional Recipient state / province / region. | |
| from_city | Yes | Sender city. | |
| from_name | Yes | Sender contact full name. | |
| from_type | No | Optional address type: "residential" or "business" (default residential). | |
| from_email | No | Optional Sender email. | |
| from_phone | No | Optional Sender phone (some carriers/services require it). | |
| from_state | No | Optional Sender state / province / region. | |
| paper_size | No | Optional label paper size: default | 4x6 | a4 | a5 ... Default "default". | |
| to_company | No | Optional Recipient company name. | |
| to_country | Yes | Recipient country as an ISO 3166-1 ALPHA-3 code (3 letters, e.g. USA, GBR, JPN, SGP, HKG). Required. | |
| to_street1 | Yes | Recipient street address line 1. | |
| to_street2 | No | Optional Recipient street address line 2. | |
| is_document | No | Optional: true for documents-only shipments. Default false. | |
| weight_unit | No | Weight unit: kg | lb | oz | g. Default kg. | |
| from_company | No | Optional Sender company name. | |
| from_country | Yes | Sender country as an ISO 3166-1 ALPHA-3 code (3 letters, e.g. USA, GBR, JPN, SGP, HKG). Required. | |
| from_street1 | Yes | Sender street address line 1. | |
| from_street2 | No | Optional Sender street address line 2. | |
| service_type | Yes | The carrier service to buy — a service_type value returned by quote_rates (e.g. "fedex_international_priority"). | |
| weight_value | Yes | Parcel weight value. Required. Pair with weight_unit. | |
| dimension_unit | No | Dimension unit: cm | in | m. Default cm. | |
| to_postal_code | No | Recipient postal / ZIP code (required by most carriers). | |
| customs_purpose | No | Optional customs purpose for international parcels: gift | merchandise | sample | return | repair. Sent as customs.purpose when provided. | |
| from_postal_code | No | Sender postal / ZIP code (required by most carriers). | |
| parcel_description | No | Optional human description of the parcel contents. | |
| shipper_account_id | Yes | The MERCHANT'S AfterShip shipper-account id (same one used in quote_rates). |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses re-quoting of charge, application of owner policy guardrails, behavior when over threshold (returns unsigned draft), sandbox vs production environment effects, and cost responsibility. This goes well beyond the annotations which only indicate non-readonly and non-destructive.
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?
Description is moderately long but each sentence adds value. It is well-structured with clear progression: purpose, prerequisite, behavior, environment, cost. Could be slightly more concise but remains effective.
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 36 parameters and no output schema, the description covers overall workflow, return values (URL and tracking number), environment handling, and policy guardrails. It addresses the complexity adequately.
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 coverage is 100% with detailed descriptions for each parameter. Description adds context for service_type and shipper_account_id by referencing quote_rates, but does not substantially enhance meaning beyond the schema.
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?
Description explicitly states 'Buy a shipping label for a chosen service_type' and returns 'printable label file url + tracking_number'. It clearly distinguishes from sibling tools like quote_rates (rates), cancel_label (cancellation), and query_tracking (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?
Provides explicit workflow: first call quote_rates to get service_type, then use same parameters. Mentions policy guardrails and environment selection. Does not explicitly state when not to use, but the prerequisite step is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
query_trackingARead-onlyInspect
NOT SUPPORTED by this server. AfterShip's Shipping (Postmen) API — which powers this server's rate/label/cancel tools — has no parcel-tracking endpoint. Live parcel tracking is a SEPARATE AfterShip product: the AfterShip Tracking API (https://www.aftership.com/docs/tracking). To follow a parcel, use the carrier's own tracking or the AfterShip Tracking API with the tracking_number that create_label returned. This tool returns a structured not_supported result explaining that (it never errors).
| Name | Required | Description | Default |
|---|---|---|---|
| tracking_number | No | Optional tracking number (echoed back with guidance). Tracking itself is not served here. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint, openWorldHint), the description adds that the tool returns a structured not_supported result, never errors, and explains the underlying server limitation.
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 front-loaded with 'NOT SUPPORTED' and every sentence serves a purpose, efficiently explaining the limitation and alternatives.
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?
For a tool that solely returns a not-supported result, the description fully covers why, what to use instead, and what the response looks like. No output schema needed.
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 coverage is 100% with a clear description of the single parameter. The description does not add further detail beyond what is already in the schema.
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 returns a 'not_supported' result and explains why. It distinguishes from siblings by explicitly mentioning tracking is not available here and referencing create_label.
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?
Explicitly tells when to use this tool (when tracking parcels) and when not to use it, directing to the AfterShip Tracking API. Also clarifies that the tool never errors.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
quote_ratesARead-onlyInspect
Compare live shipping rates across the carriers bound to a merchant AfterShip shipper account (UPS / USPS / FedEx / DHL / Ninja Van / J&T and more). IMPORTANT: shipper_account_id is the MERCHANT'S OWN carrier account (their own contract/rates), which they bound inside AfterShip / admin.postmen.com — this server never owns carrier accounts. Pass a to/from address and a parcel (weight + optional dimensions); returns a list of available service_type values with each total_charge (amount + currency), delivery_date and transit_time. Feed the service_type you want into create_label. Bring-your-own key via header x-aftership-key; x-aftership-env sandbox (default, free) or production. This call never buys anything.
| Name | Required | Description | Default |
|---|---|---|---|
| depth | No | Parcel depth / length. | |
| items | No | Optional line items for customs (required for most INTERNATIONAL shipments). Each: {description, quantity, price_amount, price_currency, origin_country (alpha-3), weight_value, weight_unit, sku, hs_code}. | |
| width | No | Parcel width. Provide width+height+depth together (with dimension_unit), or omit all three. | |
| height | No | Parcel height. | |
| to_city | Yes | Recipient city. | |
| to_name | Yes | Recipient contact full name. | |
| to_type | No | Optional address type: "residential" or "business" (default residential). | |
| box_type | No | Parcel box type. Default "custom" (uses your dimensions). Some carriers accept named flat-rate boxes. | |
| to_email | No | Optional Recipient email. | |
| to_phone | No | Optional Recipient phone (some carriers/services require it). | |
| to_state | No | Optional Recipient state / province / region. | |
| from_city | Yes | Sender city. | |
| from_name | Yes | Sender contact full name. | |
| from_type | No | Optional address type: "residential" or "business" (default residential). | |
| from_email | No | Optional Sender email. | |
| from_phone | No | Optional Sender phone (some carriers/services require it). | |
| from_state | No | Optional Sender state / province / region. | |
| to_company | No | Optional Recipient company name. | |
| to_country | Yes | Recipient country as an ISO 3166-1 ALPHA-3 code (3 letters, e.g. USA, GBR, JPN, SGP, HKG). Required. | |
| to_street1 | Yes | Recipient street address line 1. | |
| to_street2 | No | Optional Recipient street address line 2. | |
| is_document | No | Optional: true if the shipment is documents only (no customs value). Default false. | |
| weight_unit | No | Weight unit: kg | lb | oz | g. Default kg. | |
| from_company | No | Optional Sender company name. | |
| from_country | Yes | Sender country as an ISO 3166-1 ALPHA-3 code (3 letters, e.g. USA, GBR, JPN, SGP, HKG). Required. | |
| from_street1 | Yes | Sender street address line 1. | |
| from_street2 | No | Optional Sender street address line 2. | |
| weight_value | Yes | Parcel weight value. Required. Pair with weight_unit. | |
| dimension_unit | No | Dimension unit: cm | in | m. Default cm. | |
| to_postal_code | No | Recipient postal / ZIP code (required by most carriers). | |
| from_postal_code | No | Sender postal / ZIP code (required by most carriers). | |
| parcel_description | No | Optional human description of the parcel contents. | |
| shipper_account_id | Yes | The MERCHANT'S AfterShip shipper-account id — the carrier account (UPS/FedEx/DHL/Ninja Van...) THEY bound in AfterShip, with their own contract & rates. Not owned by this server. List them via AfterShip / admin.postmen.com shipper accounts. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond readOnlyHint=true and openWorldHint=true, description explicitly states 'This call never buys anything' and clarifies that the server never owns carrier accounts, increasing transparency about safety and ownership.
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?
Description is concise but comprehensive, front-loading the purpose, then important clarifications, then usage steps. Every sentence adds value 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 33 parameters (10 required) and no output schema, description covers the essential flow: rates are returned with service_type, charges, etc. It explains authentication, safety, and links to create_label. It could detail return structure more, but overall complete for a read-only quote 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?
Schema description coverage is 100%, so baseline 3. Description adds key semantics for shipper_account_id (explaining it's the merchant's own account) and outlines main parameters (to/from address, parcel weight/dimensions). It also explains return fields, though schema already describes parameters well.
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?
Description clearly states it compares live shipping rates from merchant's carrier accounts. It distinguishes itself from siblings by mentioning the output can be fed into create_label, and it is a read-only rate comparison tool, unlike cancel_label, create_label, and query_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?
Description explains when to use: to get rates before creating a label. It mentions passing to/from address and parcel. It implicitly guides to use this before create_label. It also clarifies authentication and environment. It does not explicitly state when not to use, but the context is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!