Easyship vs Firecrawl MCP Server
A side-by-side look at the Easyship and Firecrawl MCP Server MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Easyship for delivery work as a local process; choose Firecrawl MCP Server for search & data extraction as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Easyship when
- You need dedicated capabilities in the Delivery domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
EASYSHIP_API_ACCESS_TOKEN. - You want tools like
get_rates, track_shipment, create_shipment.
Choose Firecrawl MCP Server when
- You need dedicated capabilities in the Search & Data Extraction domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
FIRECRAWL_API_KEY, HTTP_STREAMABLE_SERVER, FIRECRAWL_NO_SEARCH_FEEDBACK, FIRECRAWL_NO_ENDPOINT_FEEDBACK. - You want tools like
firecrawl_scrape, firecrawl_map, firecrawl_search.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Delivery | Search & Data Extraction |
| Quality signal | 53/100 · Good | 90/100 · Excellent |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | API key required |
| Pricing | Not declared | Freemium |
| Required env vars | EASYSHIP_API_ACCESS_TOKEN | FIRECRAWL_API_KEYHTTP_STREAMABLE_SERVERFIRECRAWL_NO_SEARCH_FEEDBACKFIRECRAWL_NO_ENDPOINT_FEEDBACK |
| Verified owner | Community listing | Verified |
| GitHub stars | 0 | 7,642 |
| Directory activity | 2 views 0 installs 0 upvotes | 13 views 0 installs 0 upvotes |
| Tools | 25 | 25 |
| Full listing | View Easyship | View Firecrawl MCP Server |
Tools & capabilities
Easyship tools 25
get_ratesGet available shipping rates (courier options with prices and delivery times) for a parcel. Returns the courier options available for a parcel between two countries, each with its price, estimated delivery time, and ranking fields the caller can sort by. **Before calling:** You must have at minimum the origin country, destination country, and weight. If any of these are missing, ask the user first. **If you use assumed or estimated data** (e.g. generic postal codes, standard dimensions), you MUST tell the user: "These are estimated rates based on standard package dimensions. Exact rates may change with a full address and precise box measurements." Each item should include either `item_category` or `item_hs_code` for accurate customs and duty estimates.track_shipmentTrack a shipment and get its current status plus checkpoint history. At least one of `easyship_shipment_id` or `platform_order_number` is required; omitting both returns an error from this tool. Returns the latest status, estimated delivery date, and a list of tracking checkpoints showing the shipment's journey.create_shipmentCreate a new shipment and optionally buy a label in one call. Required authorization scope: `public.shipment:write` (and `public.label:write` if buying a label). **Before calling:** collect complete address details from the user — contact names, emails, phones, and company name (required for origin). **Parcel line items:** For every object in `parcels[].items[]`, provide at least one of `category` (Easyship product category slug) or `hs_code`. The Easyship API will reject the request if both are missing on any item — do not assume a default; ask the user which category applies or for the HS code. ## When to buy a label vs just create a shipment - **"Ship this" / "Buy a label" / "Create a shipping label"** → Set `buy_label: true` and `buy_label_synchronous: true` in `shipping_settings`. With `format: "url"` in `printing_options`, responses include HTTPS URLs under `shipping_documents`. - **"Create a shipment, don't buy the label yet"** → Omit `buy_label` or set it to `false`. The shipment is created in draft state; the user can buy the label later. ## Choosing a courier - **No courier specified** → Omit `courier_settings.courier_service_id`. The API selects a courier automatically (no separate rates call required). - **User names a specific courier** (e.g. "buy a label with <courier> <service>") → Use `get_rates` to resolve the matching `courier_service_id`, then pass it as `courier_settings.courier_service_id` with `allow_fallback: false`. ## Reading the label from the response When `buy_label: true` and `buy_label_synchronous: true`, the response includes a `shipping_documents` array. Entries use `category` (e.g. `label`, `packing_slip`, `commercial_invoice`) and, when `format` is `url`, an `url` field. Example: ```json "shipping_documents": [ { "category": "label", "format": "url", "url": "https://...", "page_size": "4x6" }, { "category": "packing_slip", "format": "url", "url": "https://...", "page_size": "4x6" }, { "category": "commercial_invoice", ... } ] ``` ## Identity / KYC and labels If the response includes `support_email`, `support_email_link`, or `support_reply_hint`, the payload is noting account or identity verification limits on labels; those fields carry suggested end-user wording from Easyship. ## Payload schema `shipment_data` is a JSON dict with this structure (fields marked * are required): ```json { "destination_address": { "contact_name": "string *", "contact_email": "string *", "contact_phone": "string * (nullable)", "line_1": "string * (max 35)", "city": "string *", "country_alpha2": "string * (ISO 3166-1)", "state": "string (required for AU,CA,CN,ID,MX,MY,TH,US,VN)", "postal_code": "string (required for most countries, null for HK)", "line_2": "string", "company_name": "string" }, "origin_address": { "company_name": "string * (max 27)", "contact_name": "string * (max 22)", "contact_email": "string *", "contact_phone": "string *", "line_1": "string * (max 35)", "city": "string *", "state": "string (required for AU,CA,CN,ID,MX,MY,TH,US,VN)", "postal_code": "string (required for most countries)", "country_alpha2": "string (ISO 3166-1)" }, "parcels": [ { "total_actual_weight": 1.5, "box": { "length": 30, "width": 20, "height": 15 }, "items": [ { "description": "string * (max 200)", "quantity": 1, "actual_weight": 1.5, "dimensions": { "length": 10, "width": 10, "height": 10 }, "declared_currency": "USD", "declared_customs_value": 50.0, "category": "<slug from user — required unless hs_code set>", "sku": "string", "hs_code": "<from user — required unless category set>", "contains_battery_pi966": false, "contains_battery_pi967": false, "contains_liquids": false, "origin_country_alpha2": "US" } ] } ], "incoterms": "DDU or DDP", "insurance": { "is_insured": false }, "courier_settings": { "courier_service_id": "uuid (omit to select a courier automatically)", "apply_shipping_rules": true, "allow_fallback": false }, "shipping_settings": { "buy_label": true, "buy_label_synchronous": true, "units": { "weight": "kg | g | lb | oz", "dimensions": "cm | in" }, "printing_options": { "format": "url", "label": "4x6 | A4 | A5", "commercial_invoice": "4x6 | A4", "packing_slip": "4x6 | A4 | none" } }, "order_data": { "platform_name": "string", "platform_order_number": "string", "buyer_notes": "string", "seller_notes": "string" }, "set_as_residential": true, "metadata": {} } ``` ## Weight and dimensions — three ways 1. Provide `total_actual_weight` + `box` at parcel level. 2. Provide `actual_weight` + `dimensions` per item — total weight and box auto-calculated. 3. Provide `sku` per item — weight and dimensions taken from product catalog. Args: shipment_data: The full shipment payload as a JSON dict. See schema above. At minimum: `destination_address`, `origin_address` (or `origin_address_id`), and `parcels` with at least one item. Returns: The created shipment object including selected courier, rates, and — if `buy_label` was true — `shipping_documents` array with label/packing slip/invoice URLs. If identity verification affects label purchase, the payload may include `support_email`, `support_email_link`, and `support_reply_hint`.update_shipmentUpdate an existing shipment's details. Required authorization scope: `public.shipment:write`. The `shipment_data` dict follows the same schema as `create_shipment` — include only the fields you want to change. See `create_shipment` docstring for the full payload schema. If you include **`parcels`**, each line item should still have `category` or `hs_code` — the Easyship API requires at least one per item. Args: easyship_shipment_id: Easyship Shipment ID, e.g. "ESSG10006001". shipment_data: Partial shipment payload — same schema as create_shipment, include only fields to update. Common updates: destination_address, parcels, courier_settings, shipping_settings, incoterms. Returns: The updated shipment object from the Easyship API. If identity verification affects label purchase, the payload may include `support_email`, `support_email_link`, and `support_reply_hint`.list_shipmentsFind and filter shipments, returning a summary of each one. Unless the user explicitly asks for cancelled shipments, exclude them by passing `shipment_state`. Each result carries the shipment ID, lifecycle states, dates, weight, courier, order reference, and tracking numbers, plus origin and destination country. Street addresses, parcel contents, documents, and rates are not included — call `get_shipment` with an ID for those. **USE THIS TOOL FOR:** - Finding shipments by filter (state, courier, country, date range, order number) - Listing or counting shipments that match criteria - Looking up a shipment's ID or current status before calling a detail tool **DO NOT USE THIS TOOL FOR:** - Full detail on a single shipment -> use `get_shipment` - Analytics queries -> use the analytics tools Required authorization scope: `public.shipment:read` Args: page: Page number to fetch, default: `1` per_page: Number of records per page to fetch, default: `20` label_state: Filter by label status (e.g. "pending", "generated", "failed"). Pass values exactly as returned by the API; the set may change as the platform evolves. pickup_state: Filter by pickup status (e.g. "requested", "completed", "cancelled"). Pass values exactly as returned by the API; the set may change as the platform evolves. created_at_to: Search for shipments created before this date: ISO8601 date format. updated_at_to: Search for shipments updated before this date: ISO8601 date format. delivery_state: Filter by delivery status (e.g. "in_transit_to_customer", "delivered", "exception"). Pass values exactly as returned by the API; the set may change as the platform evolves. shipment_state: Filter by shipment lifecycle state (e.g. "created", "cancelled"). created_at_from: Search for shipments created since this date: ISO8601 date format. updated_at_from: Search for shipments updated since this date: ISO8601 date format. warehouse_state: For eFulfilment only. Filter by warehouse state (e.g. "pending", "packed", "shipped"). Pass values exactly as returned by the API. label_paid_at_to: Search for shipments where the labels were paid for before this date: ISO8601 date format. label_paid_at_from: Search for shipments where the labels were paid for since this date: ISO8601 date format. easyship_shipment_id: Easyship Shipment ID provided when creating the shipment. label_generated_at_to: Search for labels generated before this date: ISO8601 date format. origin_country_alpha2: Search by the shipment origin country code: Alpha-2 format (ISO 3166-1). platform_order_number: Order number on the sales platform. label_generated_at_from: Search for labels generated since this date: ISO8601 date format. destination_country_alpha2: Search by shipment destination country code: Alpha-2 format (ISO 3166-1). return_shipment: Search by shipment whether the shipment is return shipment or not. include_contact_details: Set to true only when the user explicitly asked for the recipient's contact email or phone. Defaults to false, which omits them. Returns: A paginated list of shipment summaries matching the filter criteria.get_shipmentFetch a single shipment by Easyship ID, including parcel data and, on request, its documents. Returns the shipment's state, dates, courier, addresses, and parcel contents. Documents are **not** included by default — set `include_documents: true` when the user asked for the label, commercial invoice, or packing slip. The remaining parameters below only shape those documents and have no effect unless `include_documents` is set. Required authorization scope: `public.shipment:read` > All shipment documents are customisable. You can set: > > - Document format: URL, PDF or PNG > - Label page size: A4, A5 or 4x6 > - Commercial invoice page size: A4 or 4x6 > - Packing slip page size: A4 or 4x6 Args: easyship_shipment_id: The Easyship shipment ID, e.g. "ESSG10006001". label: Label page size: A4, A5, or 4x6. format: Document format: URL, PDF, or PNG. packing_slip: Packing slip page size: none, A4, or 4x6. commercial_invoice: Commercial invoice page size: A4 or 4x6. include_contact_details: Set to true only when the user explicitly asked for the recipient's contact email or phone. Defaults to false, which omits them. include_documents: Set to true only when the user asked for a label or document. Defaults to false, which omits the download links. Returns: Shipment details, including `shipping_documents` when `include_documents` is true.delete_shipmentDelete a shipment that has not yet been shipped. Required authorization scope: `public.shipment:write` Args: easyship_shipment_id: The Easyship shipment ID, e.g. "ESSG10006001". Returns: Confirmation of the deleted shipment, or an error.cancel_shipmentCancel a shipment that has been shipped. Required authorization scope: `public.shipment:write` > You can cancel your shipment after it has been shipped only if its label failed to be generated or if the label is already generated, but the shipment is not yet in transit. Args: easyship_shipment_id: The Easyship shipment ID, e.g. "ESSG10006001". Returns: Confirmation of the cancelled shipment, or an error.create_labelCreate a label for an existing shipment and retrieve it synchronously. Buys a label for a shipment that already exists. This is a dedicated endpoint that finalizes the shipment, books it with the courier, and returns the label and shipping documents in one synchronous call. `update_shipment` with `buy_label` performs the same purchase as part of a wider update. Required authorization scope: `public.label:write` **Typical use:** Buying or regenerating a label for an existing shipment ID where `label_state` is `not_created` or similar. Successful responses include `shipping_documents` with `category` values such as `label`, `packing_slip`, and `commercial_invoice`; with `format` `url`, entries include `url` fields. If the response includes `support_reply_hint`, `support_email`, or `support_email_link`, the API is noting verification limits on labels—those fields contain Easyship-provided support guidance. Args: easyship_shipment_id: The Easyship shipment ID, e.g. "ESUS323672208". courier_service_id: UUID of the courier service to use. Omit to keep the shipment's current courier or let Easyship select a courier automatically. format: Document format. One of: "url", "pdf", "png", "zpl". Default "url" (returns clickable links). label: Label page size. One of: "4x6", "A4", "A5". Default "4x6". commercial_invoice: Commercial invoice page size. One of: "4x6", "A4". Default "A4". packing_slip: Packing slip page size. One of: "4x6", "A4", "none". Default "4x6". remarks: Custom commercial invoice remarks (max 70 chars). Overrides company-level remarks. Returns: The full shipment object with `shipping_documents` containing label/invoice/packing slip URLs. If identity verification affects label purchase, the payload may include `support_email`, `support_email_link`, and `support_reply_hint`.get_shipment_documentsRequest a commercial invoice document for a shipment from the API. The MCP transport cannot return raw PDF bytes; the implementation responds with content-type and size metadata only. Downloadable HTTPS URLs for documents are available via `get_shipment` when document `format` is `url`. Required authorization scope: `public.shipment_document:read` Args: easyship_shipment_id: The Easyship shipment ID, e.g. "ESSG10006001". page_size: Page size for the document: "4x6" or "A4". Default: "A4". Returns: Metadata only (content type and size). For downloadable URLs, use `get_shipment` with format="URL".list_pickupsRetrieve a list of pickups. Required authorization scope: `public.pickup:read` Args: page: Page number to fetch, minimum: 1. per_page: Number of records per page to fetch, minimum: 1, maximum: 100. courier: Filter by courier name (e.g. "DHL Express", "USPS"). Pass the courier name exactly as returned by the API; the available set changes as couriers are added or removed. pickup_date: Filter by pickup date in YYYY-MM-DD format. shipment_id: Filter by shipment ID. pickup_state: Filter by pickup state (e.g. "requested", "completed", "cancelled"). Pass the state string exactly as returned by the API. include_contact_details: Set to true only when the user explicitly asked for the recipient's contact email or phone. Defaults to false, which omits them. Returns: A paginated list of pickup objects matching the filter criteria.get_pickupRetrieve details of a specific pickup. Required authorization scope: `public.pickup:write` (note: the API requires write scope even for this read operation). Args: easyship_pickup_id: The Easyship pickup ID. include_contact_details: Set to true only when the user explicitly asked for the recipient's contact email or phone. Defaults to false, which omits them. Returns: Full pickup details, or an error.- +13 more on the listing page
Firecrawl MCP Server tools 25
firecrawl_scrapeRetrieve and extract content from one supplied URL through Firecrawl. Use this when the request identifies a page and needs its content or defined fields. It can return markdown, HTML, links, screenshots, branding data, a targeted answer, or JSON matching a supplied schema; JSON is useful when the requested result has defined fields, while markdown preserves readable page content. This tool operates on a known page. For a set of pages use `firecrawl_crawl`, and to discover page URLs use `firecrawl_map` or `firecrawl_search`. Options include JavaScript render delay, cache age, main-content filtering, PII redaction, and lockdown cache-only retrieval. Browser actions may change the live page when interactive actions are enabled. Firecrawl may reuse recently indexed content instead of refetching the page, and the reuse window varies by domain. Set `maxAge: 0` to force a live fetch, or a smaller `maxAge` to bound how stale reused content may be. A successful response does not by itself confirm that the state it describes is still current. Returns the selected content formats and page metadata.firecrawl_mapEnumerate URLs indexed under one website through Firecrawl without fetching each page's content. Use this when the request asks for a site's URL inventory, when several relevant pages must be located, or when the desired page URL is unknown. An optional `search` term narrows the URL list, while sitemap, subdomain, query-parameter, and result-limit options control coverage. Returns matching URLs rather than page bodies. Retrieve one page with `firecrawl_scrape`; collect content across multiple pages with `firecrawl_crawl`.firecrawl_searchSearch web, news, or image sources and return ranked results. Operators include quoted phrases, `-term`, `site:host`, `inurl:term`, `intitle:term`, and `related:host`; the set is non-exhaustive. `includeDomains` and `excludeDomains` are mutually exclusive hostname filters; categories limit results to GitHub, research, PDF, or developer sources. For a programming question, add `categories: ["developer"]`. It searches an index of GitHub issues, merged pull requests, repository READMEs, and curated documentation sites, and returns the hits in `data.developer` beside the web results. `categories: ["research"]` restricts these web results to research-affiliated websites and returns page snippets. The `firecrawl_research_*` tools are a separate surface that searches paper abstracts and full text across biomedical (PubMed, bioRxiv, medRxiv) and arXiv literature. `scrapeOptions` can attach extracted page content; pages fetched this way use a fixed reuse window and ignore `maxAge`, so use `firecrawl_scrape` when a live fetch is required. Returns source-type result groups and usage metadata. Authenticated responses can include an `id` for optional search feedback.firecrawl_crawlStart a multi-page crawl at a website URL, poll it to a terminal state, and return the final status and collected data. Scope can be bounded with include/exclude paths, depth, page limit, subdomain/external-link controls, sitemap handling, delay, and scrape options. Crawl results can be large; use conservative limits when full-site coverage is unnecessary. Webhooks and interactive scrape actions are unavailable in safe mode. Returns the crawl ID, status, and page data.firecrawl_check_crawl_statusRetrieve the current status, progress, and available results for an existing crawl ID. This only reads Firecrawl job state and does not start or modify the crawl.firecrawl_extractDeprecated compatibility entry point. Use firecrawl_scrape once per known URL with formats: ["json"] and jsonOptions containing the prompt and schema. Use firecrawl_search or firecrawl_agent before Scrape when URLs are not known.firecrawl_agentStart an asynchronous web research job from a prompt, optional seed URLs, and an optional JSON schema. Use this for a requested synthesis across multiple sources when the task can wait for asynchronous completion. The agent can search, navigate, read pages, and assemble a structured result. This call returns only a job ID, not the research result. Read the job with `firecrawl_agent_status` until it reaches `completed` or `failed`; research commonly takes several minutes. If the job cannot finish within the task's available time, `firecrawl_search` and `firecrawl_scrape` can gather evidence synchronously.firecrawl_agent_statusRetrieve progress or final results for a `firecrawl_agent` job ID. A `processing` response is non-terminal and does not contain the final research result. Check again after 15–30 seconds until the status is `completed` or `failed`; complex jobs can take several minutes. If the job cannot finish within the task's available time, use `firecrawl_search` and `firecrawl_scrape` to complete the requested output. Returns job status, progress information, and result data when completed.firecrawl_interactOpen or reuse a live browser session to navigate a page, click controls, fill fields, or run browser code. Provide either `url` or `scrapeId`, and either a natural-language `prompt` or executable `code`; code can run as Bash, Python, or Node with a bounded timeout. This acts on the live site, so actions such as form submission can create persistent external side effects. Returns execution output, stdout/stderr, exit status, and session viewing URLs.firecrawl_interact_stopStop the live interact session associated with a `scrapeId` and release its resources. Returns a success confirmation.firecrawl_parseParse one supported document into markdown, HTML, links, summary, targeted answers, or JSON matching a schema. Supported inputs include common HTML, PDF, Word, RTF, OpenDocument, and spreadsheet files; PDF parsing can be bounded with `pdfOptions.maxPages`. Local MCP reads `filePath` from the server filesystem. Hosted MCP uses two calls: first provide `filePath` to receive upload instructions, upload locally, then call again with the returned `uploadRef`; do not send both fields together. Remote web URLs belong in `firecrawl_scrape`. Set `redactPII` to request redaction of personally identifiable information in the returned content. `zeroDataRetention` requires an eligible authenticated account; omit it for anonymous keyless use. Returns upload instructions for hosted phase one or parsed document content for the final call.firecrawl_monitor_createCreate a recurring scrape, crawl, or search monitor that compares each check with its retained predecessor. The simple form accepts `page`/`pages` or `queries` plus a plain-language `goal`; the advanced `body` form controls targets, schedule, change-tracking formats, judging, retention, webhook, and notifications. In the simple form, a `goal` is required. If `queries` contains one or more non-empty values and is supplied with `page`/`pages`, `queries` create the search target and page targets are ignored. A monitor schedules future network checks and can send configured email or webhook notifications. Returns the created monitor.- +13 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Easyship
{
"mcpServers": {
"easyship-2": {
"command": "uvx",
"args": [
"easyship-mcp"
],
"env": {
"EASYSHIP_API_ACCESS_TOKEN": "YOUR_EASYSHIP_API_ACCESS_TOKEN_HERE"
}
}
}
}
Firecrawl MCP Server
{
"mcpServers": {
"firecrawl-firecrawl-mcp-server": {
"command": "npx",
"args": [
"-y",
"firecrawl-mcp"
],
"env": {
"FIRECRAWL_API_KEY": "YOUR_FIRECRAWL_API_KEY_HERE",
"HTTP_STREAMABLE_SERVER": "YOUR_HTTP_STREAMABLE_SERVER_HERE",
"FIRECRAWL_NO_SEARCH_FEEDBACK": "YOUR_FIRECRAWL_NO_SEARCH_FEEDBACK_HERE",
"FIRECRAWL_NO_ENDPOINT_FEEDBACK": "YOUR_FIRECRAWL_NO_ENDPOINT_FEEDBACK_HERE"
}
}
}
}
Frequently asked questions
Easyship is categorized under Delivery and uses a local stdio subprocess. Firecrawl MCP Server belongs to Search & Data Extraction and uses a local stdio subprocess. Pick Easyship for delivery work and Firecrawl MCP Server for search & data extraction.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Easyship has no declared pricing — check the project's own site. Firecrawl MCP Server is listed as freemium — a free tier with paid plans. Auth: api key required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add easyship-2 and firecrawl-firecrawl-mcp-server as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Easyship has a quality signal of 53/100 (Good) with 2 views, 0 installs and 0 GitHub stars. Firecrawl MCP Server has 90/100 (Excellent) with 13 views, 0 installs and 7,642 GitHub stars.