Head to head · Shipment tracking · October 2026 research run

Ship24 vs TrackingMore

Ship24 scores 55 (C) on agent readiness against TrackingMore's 41.8 (E), and leads in 5 of 7 scored categories. TrackingMore leads on reliability and transparency & trust. Both do shipment tracking. TrackingMore is cheaper for shipment tracking, $0.03 against $0.045 per transaction.

Best shipping and fulfilment APIs for AI agents · All 45 shipping comparisons

Which one, for what

Ship24 C

Best for An agent that only needs tracking events across many couriers, by webhook or by lookup, from a tracking number alone.

Ahead on

  • Schema & documentation, 81 against 31
  • Agent ergonomics, 68 against 54
  • Security & auth, 37 against 31
  • Payments & pricing, 30 against 23
  • Maintenance & community, 80 against 19

Watch for

No status page was found. status.ship24.com doesn't resolve, and neither the site nor the docs link to one

TrackingMore E

Best for An agent that reports where a parcel is across many carriers from a tracking number, with a cheap per-tracking price.

Ahead on

  • Reliability, 65 against 45
  • Transparency & trust, 57 against 52

Also in its favour

  • Cheaper for shipment tracking, $0.03 against $0.045 per transaction

Watch for

The API reference renders by script and no OpenAPI file, llms.txt or Markdown docs were found

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Maintenance & community Ship24 +61

Ship24 80

The ship24 npm package reached 1.1.0 on 6 October 2026, two days before the check (30). In the 90 days before the check there were five dated releases, the Node SDK 1.0.0 on 14 July and 1.1.0 on 6 October, MCP server 1.0.0 on 16 July and 1.0.1 on 27 August in the official registry, and the AI plugin 1.0.0 on 9 September (20). The service is closed, with no API changelog. Support is a contact form, and the GitHub API shows four open issues on the SDK repository and two on the plugin, which we didn't read (6 of 15). The MCP server is in the official registry under the domain namespace com.ship24/tracking-mcp (15). The SDK has no runtime dependencies, CI that tests Node 20, 22 and 24, and a workflow that reports drift from the OpenAPI spec (9 of 10).

TrackingMore 19

Read as a closed service. No dated API change was found. The SDKs were last pushed between February and December 2024, the support articles are dated 2023 and 2024, and the reference is undated (0 of 30). No releases or dated entries in the last 90 days were found (0). Support by email and chat with a help centre; GitHub issues were not read (6 of 15). Seven official SDKs exist but none has changed since December 2024 (10 of 15). The Node SDK has tests and no CI workflow (3 of 10). 0 + 0 + 6 + 10 + 3 = 19.

Schema & documentation Ship24 +50

Ship24 81

A public OpenAPI 3.1 spec at docs.ship24.com/assets/openapi/ship24-tracking-api.yaml covers 12 operations and two webhooks, and every MCP tool has a typed input and output schema (25). llms.txt and a hosted SKILL.md guide exist, but the docs pages have no Markdown copies and llms.txt truncates its descriptions (8 of 10). The MCP tool descriptions say when to use each tool and which to prefer, such as search_tracking_by_number before a billed lookup, and the docs explain the three ways to fetch results (18 of 20). Inputs are typed with required fields, 12 enums and limits such as 5 to 50 characters for a tracking number and 500 a page, though the Authorization header is modelled as a plain string parameter (12 of 15). The spec has many examples and the errors page lists 12 codes, but most operations document only their success response and the live auth_missing_header code isn't on the list (10 of 15). The path carries v1 and the data format page promises that fields are never removed and lists four deprecated fields with months. No API changelog was found, only the SDK and plugin changelogs (8 of 15).

TrackingMore 31

No OpenAPI or similar file was found in the docs, the SDK repositories or a search, and the reference at trackingmore.com/docs renders by script so its schemas were not read (0 of 25). No llms.txt or Markdown docs (0). The official SDK READMEs give one line per call, and the support centre explains when to pair create with get or a webhook and that the create response carries the result (8 of 20). Field names and the required tracking_number and courier_code appear in the SDK examples, with no types, enums or constraints readable (5 of 15). Examples in seven SDK languages and a table of HTTP and meta codes with messages (12 of 15). v4 in the path with v2 and v3 still served, and the support centre says there is no changelog for switching versions. No dated API changelog was found (6 of 15). 0 + 0 + 8 + 5 + 12 + 6 = 31.

Reliability TrackingMore +20

Ship24 45

Read with the hosted lines and scored on the REST API at api.ship24.com/public/v1, which the hosted MCP server wraps. No status page was found. status.ship24.com doesn't resolve, ship24.statuspage.io is inactive, and neither the site footer nor the docs link to one (0). With no readable incident history the record scores the default (5 of 30). The rate limiter page gives a number for each of 11 endpoints, from 1 request a second on GET /couriers to 10 on most others (15). Responses carry RateLimit-*, X-RateLimit-* and Retry-After headers, which we saw on a live response, the errors page recommends exponential backoff on 429, and tracker creation is documented as idempotent with a 409 request_conflict that can be retried (15). The terms supply the service as is and as available, with no SLA found for any plan (0). The path is /public/v1 and the MCP server reports version 1.0.1, with no beta label (10).

TrackingMore 65

Read with the hosted lines and scored on the REST API v4 at api.trackingmore.com. status.trackingmore.com is a hosted status page with uptime and a status update history (20). Its figures and history render by script, so the 90 days could not be read; the static text says there were no updates in the last 7 days (5). Rate limits are published per endpoint, 3 requests a second on trackings/create and 10 a second elsewhere, per account (15). The support centre says a 429 means the application should stop and wait 120 seconds, and a repeated create answers meta code 4101 rather than creating a duplicate. No Retry-After and no idempotency key (10 of 15). No SLA document was found. The Enterprise plan lists 99.99 per cent API uptime as a feature and the API page claims 99.9 per cent uptime, which is marketing rather than a published SLA (5 of 10). v4 is the current version and not marked beta (10). 20 + 5 + 15 + 10 + 5 + 10 = 65.

Agent ergonomics Ship24 +14

Ship24 68

Scored on the REST API and the MCP server together. The MCP server has 12 tools, registered by plan, but its tools/list answer is about 61 KB because every tool carries an output schema, and the REST API has no field selection, so a results call returns every event (13 of 25). GET /trackers pages by page and limit (default 100, maximum 500) with a sort order. No filter appears in the spec for that call, and GET /couriers returns the full list unpaged (12 of 20). Errors are a JSON errors array with a stable code and a message that says what to fix, with 12 documented codes (16 of 20). POST /trackers and POST /trackers/track are idempotent for an identical payload, clientTrackerId is validated as unique, the bulk call is documented as not fully idempotent, and all 12 MCP tools carry readOnlyHint or destructiveHint and idempotentHint annotations (18 of 20). Only trackingNumber is required and the courier is detected automatically. One official SDK exists, for Node.js and TypeScript, so the two-language line isn't met (9 of 15).

TrackingMore 54

trackings/get filters by tracking numbers, courier and created date range, and batch create takes 40 at once. No field selection was found, and the unread reference may document more (10 of 25). Date and courier filters exist; pagination parameters were not found in what was read (8 of 20). Every response carries an HTTP code and a meta code with a message, such as 4121 for an undetected courier and 4190 for a reached quota (14 of 20). No idempotency key. A repeated create is rejected with 4101, so the write is safe to retry, and delete and retrack take ids (10 of 20). Create needs only tracking_number and courier_code, detect is free, and official SDKs cover seven languages (12 of 15). 10 + 8 + 14 + 10 + 12 = 54.

Payments & pricing Ship24 +7

Ship24 30

Read with the hosted rubric. No x402, MPP or L402 was found in the docs, the spec or the pricing page (0). The pricing page lists both billing models without a login, per shipment from $39 a month for 1,000 with $0.045 for each extra shipment, and per call from $99 a month for 10,000 with $0.015 for each extra call, with every tier and overage rate in a table (20). The Tracking API has a free plan of 10 shipments a month. Whether signup asks for a card wasn't established, because the dashboard needs a login we didn't create (10 of 20). A person signs up and picks a plan in the dashboard, and API key creation isn't available through the API or the MCP server (0).

TrackingMore 23

Read with the hosted rubric. No x402, MPP or L402 (0). The API page gives a from price of $0.03 a tracked order and three unlabelled figures, and the pricing page's plan prices render by script, so per-unit pricing is partly public (8 of 20). A Free plan and a 14-day trial are offered, and whether a card is asked for was not established (15 of 20). A person signs up in a browser and generates the key there (0). 0 + 8 + 15 + 0 = 23.

Security & auth Ship24 +6

Ship24 37

API keys are sent as a Bearer token in the Authorization header. An account can hold up to 20, managed in the dashboard, and the plugin's security note advises a dedicated key so it can be revoked alone. Keys have no scopes and no secret travels in a query string (20 of 30). No read-only key or approval step was found. The API has no delete operation, the MCP server registers tools by plan and marks resend_webhooks as destructive, and that is the only least-privilege control (5 of 20). Results carry courier event text, which is untrusted, and no prompt-injection guidance was found in the docs or the plugin (3 of 15). GET /trackers/:trackerId/webhook-history/download returns every webhook push with its response, but no log of API calls or key use was found (4 of 15). SECURITY.md in the plugin repository gives contact@ship24.com for reports on the API and MCP server. No security.txt, bug bounty, SOC 2 or ISO 27001 statement was found, and webhooks are checked by a static shared secret with no signature (5 of 20).

TrackingMore 31

One API key in the Tracking-Api-Key header, shown once, at most four per account, deleted in the web app. No scopes or expiry (20 of 30). No read-only key or least-privilege mode, and delete is one call (4 of 20). Tracking checkpoints are carrier text returned to the model, and no guidance was found (3 of 15). A webhook notification log exists in the web app; no log of API calls or key use was found (4 of 15). No security.txt (404), no security page on trackingmore.com, no certification, bug bounty or disclosure policy found. The CWILL privacy policy points to a trust site that was not read (0 of 20). 20 + 4 + 3 + 4 + 0 = 31.

Score by category

CategoryWeight this runShip24TrackingMoreEdge
Reliability16%204565TrackingMore +20
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28131Ship24 +50
Agent ergonomics13%16.26854Ship24 +14
Security & auth14%17.53731Ship24 +6
Payments & pricing10%12.53023Ship24 +7
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88019Ship24 +61
Transparency & trust7%8.85257TrackingMore +5
Negative events≤1500
TotalC 55/100E 41.8/100

Facts side by side

FactShip24TrackingMore
KindHTTP APIHTTP API
VendorShip24 LimitedCHANNELWILL CO., LIMITED
Hosted endpointhttps://api.ship24.com/public/v1https://api.trackingmore.com/v4
TransportsHTTPHTTP
AuthAPI keyAPI key
PricingFreemiumFreemium
Price for shipment tracking$0.045 per transaction$0.03 per transaction
x402nono
LicenceProprietary service under Ship24's Terms and Conditions. The Node SDK and the AI plugin on GitHub are MITProprietary hosted service under the CWILL Terms of Service. The seven official SDKs on GitHub are MIT
Tools exposed12none
Read-only variant documentedyesno
llms.txtyesno
MCP registrycom.ship24/tracking-mcpnot listed
Last release2026-10-062024-12-25
Terms last updatedno date givenno date given
Privacy policy last updated2026-08-012026-08-08
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waivernot found in the textnot found in the text
Popularity0 stars, 79 npm/wk6 stars

Verdicts

Ship24

The REST API and the hosted MCP server share one public OpenAPI 3.1 spec, numbered rate limits with Retry-After, and tracker creation that is idempotent by payload. No status page, SLA or security certification was found, API keys carry no scopes, and the API agreement and data processing agreement named in the terms aren't published.

TrackingMore

A small tracking API with published per-endpoint rate limits, meta error codes, a free courier detection call and SDKs in seven languages. The reference docs render by script with no OpenAPI file, plan prices weren't readable, one key has full access, the SDKs date from 2024 and the legal documents belong to the CWILL group.

Before you call either

Ship24

  1. Send Authorization: Bearer apik_... to https://api.ship24.com/public/v1. The same key works on the MCP server, which lists tools without a key but answers 401 on calls
  2. Store the trackerId or set a unique clientTrackerId. Tracking numbers aren't unique, and any changed field on a repeat POST /trackers creates a second tracker that uses quota
  3. Allow up to 60 seconds for the first POST /trackers/track or POST /tracking/search call, since results are fetched from the courier synchronously
  4. Cache GET /couriers. It is limited to one request a second and returns the whole courier list, and courier auto-detection usually makes courierCode unnecessary
  5. Check for quota_limit_reached and no_active_subscription. POST /tracking/search needs a separate per-call plan, and the free plan blocks at 10 shipments a month

TrackingMore

  1. Send the key as Tracking-Api-Key to https://api.trackingmore.com/v4; the v2 header name Trackingmore-Api-Key and the v3 path are the older versions
  2. Call POST /v4/couriers/detect first when the carrier is unknown (free on v4), then POST /v4/trackings/create with tracking_number and courier_code; the create response already carries the tracking result
  3. Create up to 40 shipments at once with POST /v4/trackings/batch and read them with GET /v4/trackings/get, which filters by tracking numbers, courier and created date
  4. Treat meta code 4101 as an existing tracking rather than a failure, and 4190 as a plan quota to raise with the person; after a 429 wait 120 seconds
  5. Stay under 3 creates a second and 10 requests a second on other calls per account, and prefer a webhook (same version as the API) to polling

Questions

Which is better for AI agents, Ship24 or TrackingMore?

Ship24 scores 55 (C) on agent readiness against TrackingMore's 41.8 (E), and leads in 5 of 7 scored categories. TrackingMore leads on reliability and transparency & trust.

Which is cheaper for shipment tracking, Ship24 or TrackingMore?

TrackingMore, at $0.03 per transaction against $0.045 per transaction for Ship24. These are the vendors' published prices for the job.

Do Ship24 and TrackingMore need an API key?

Both need an API key.

Can an agent call Ship24 and TrackingMore without installing anything?

Yes. Ship24 has a hosted endpoint at https://api.ship24.com/public/v1 and TrackingMore at https://api.trackingmore.com/v4.

Other comparisons with Ship24 or TrackingMore

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.