Kuaidi100 launched China's first MCP-protocol-compatible logistics information service platform. The core API services of Kuaidi100's Baidiy
Nothing to run from here
Extensiv MCP by usefulapi is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
16
tools declared
remote
at its publisher
—
calls last 7d
What it does
Read Extensiv warehouse records, create outbound orders and cancel eligible orders.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http extensiv-mcp-by-usefulapi https://extensiv.usefulapi.io/mcp
# 2 — ask your agent for something these tools do
# extensiv_list_facilities, extensiv_list_carriers, extensiv_list_customers and 13 more
Extensiv MCP by usefulapi costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
USAll 449 servers
usefulapi449 servers
24 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http extensiv-mcp-by-usefulapi https://extensiv.usefulapi.io/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
16 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
List the warehouse's facilities with their ids and properties (facility ids are needed for orders, stock details and receivers). GET /properties/facilities.
No parameter schema on file.
List the carriers with their shipment services (modes) and billing codes, the values an order's routingInfo and billingCode must use. GET /properties/carriers.
No parameter schema on file.
List the warehouse's customers (the companies whose goods it stores), with their customer ids. GET /customers.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rql | string | no | Optional RQL filter, for example ReadOnly.CustomerIdentifier.id==1 or readonly.processDate=gt=2026-10-01T00:00:00;readonly.processDate=lt=2026-10-02T00:00:00 (';' = and). |
| sort | string | no | Optional sort expression, for example ReadOnly.CreationDate. |
| pgsiz | integer | no | Page size (default 100, max 500). |
| pgnum | integer | no | Page number, from 1 (default 1). Use totalResults and _links.next of the previous reply. |
One customer by customer id: company info, contacts and settings. GET /customers/{customer_id}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| customer_id | string | yes | The customer id (from extensiv_list_customers). |
List the items (SKUs) of one customer, with item ids, descriptions and units. Filter with rql, for example sku==ABC-1. GET /customers/{customer_id}/items.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| customer_id | string | yes | The customer id (from extensiv_list_customers). |
| rql | string | no | Optional RQL filter, for example ReadOnly.CustomerIdentifier.id==1 or readonly.processDate=gt=2026-10-01T00:00:00;readonly.processDate=lt=2026-10-02T00:00:00 (';' = and). |
| sort | string | no | Optional sort expression, for example ReadOnly.CreationDate. |
| pgsiz | integer | no | Page size (default 100, max 500). |
| pgnum | integer | no | Page number, from 1 (default 1). Use totalResults and _links.next of the previous reply. |
List outbound orders matching an RQL filter, for example ReadOnly.CustomerIdentifier.id==1 or readonly.processDate=gt=2026-10-01T00:00:00 (orders closed after that time). Use detail=OrderItems to include the line items. Orders carry the ship-to name, address and contact details (personal data). GET /orders.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rql | string | no | Optional RQL filter, for example ReadOnly.CustomerIdentifier.id==1 or readonly.processDate=gt=2026-10-01T00:00:00;readonly.processDate=lt=2026-10-02T00:00:00 (';' = and). |
| detail | string | no | Order-level detail, comma-delimited: None (default), OrderItems, BillingDetails, SavedElements, Packages, Contacts, ProposedBilling, OutboundSerialNumbers, SmallParcel, All. |
| itemdetail | string | no | Item-level detail, comma-delimited: None (default), SavedElements, Allocations, AllocationsWithDetail, All. |
| sort | string | no | Optional sort expression, for example ReadOnly.CreationDate. |
| pgsiz | integer | no | Page size (default 100, max 500). |
| pgnum | integer | no | Page number, from 1 (default 1). Use totalResults and _links.next of the previous reply. |
One order by its transaction id (the order id from extensiv_list_orders): status, ship-to, routing, and with detail=OrderItems the lines. GET /orders/{transaction_id}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| order_id | string | yes | The order's transaction id. |
| detail | string | no | Order-level detail, comma-delimited: None (default), OrderItems, BillingDetails, SavedElements, Packages, Contacts, ProposedBilling, OutboundSerialNumbers, SmallParcel, All. |
| itemdetail | string | no | Item-level detail, comma-delimited: None (default), SavedElements, Allocations, AllocationsWithDetail, All. |
Inventory totals per item and facility (on hand, allocated, available). Filter with rql, for example ItemId==123 or a customer filter. GET /inventory/stocksummaries.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rql | string | no | Optional RQL filter, for example ReadOnly.CustomerIdentifier.id==1 or readonly.processDate=gt=2026-10-01T00:00:00;readonly.processDate=lt=2026-10-02T00:00:00 (';' = and). |
| pgsiz | integer | no | Page size (default 100, max 500). |
| pgnum | integer | no | Page number, from 1 (default 1). Use totalResults and _links.next of the previous reply. |
Inventory detail lines (location, lot, quantities). Filter with rql, for example itemIdentifier.sku==SF-Box-DG. GET /inventory.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rql | string | no | Optional RQL filter, for example ReadOnly.CustomerIdentifier.id==1 or readonly.processDate=gt=2026-10-01T00:00:00;readonly.processDate=lt=2026-10-02T00:00:00 (';' = and). |
| pgsiz | integer | no | Page size (default 100, max 500). |
| pgnum | integer | no | Page number, from 1 (default 1). Use totalResults and _links.next of the previous reply. |
All inventory of one customer in one facility, broken out by receive item (lot number, serial number and other track-by values). Both ids are required. GET /inventory/stockdetails.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| customer_id | string | yes | The customer id. |
| facility_id | string | yes | The facility id (from extensiv_list_facilities). |
| pgsiz | integer | no | Page size (default 100, max 500). |
| pgnum | integer | no | Page number, from 1 (default 1). Use totalResults and _links.next of the previous reply. |
List inbound receivers (receipts of goods), for example ReadOnly.CustomerIdentifier.id==1. Use detail=ReceiveItems for the lines. GET /inventory/receivers.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rql | string | no | Optional RQL filter, for example ReadOnly.CustomerIdentifier.id==1 or readonly.processDate=gt=2026-10-01T00:00:00;readonly.processDate=lt=2026-10-02T00:00:00 (';' = and). |
| detail | string | no | Receiver-level detail, comma-delimited: None (default), ReceiveItems, BillingDetails, SavedElements, ProposedBilling, All. |
| itemdetail | string | no | Item-level detail, comma-delimited: None (default), SavedElements, All. |
| pgsiz | integer | no | Page size (default 100, max 500). |
| pgnum | integer | no | Page number, from 1 (default 1). Use totalResults and _links.next of the previous reply. |
One receiver by its transaction id. GET /inventory/receivers/{transaction_id}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| receiver_id | string | yes | The receiver's transaction id (from extensiv_list_receivers). |
The line items of one receiver, with item details. GET /inventory/receivers/{transaction_id}/items.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| receiver_id | string | yes | The receiver's transaction id (from extensiv_list_receivers). |
| detail | string | no | Detail level, comma-delimited: None (default), SavedElements, All. |
List inbound purchase orders per customer. Filter with rql, sort with sort. GET /inventory/pos.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rql | string | no | Optional RQL filter, for example ReadOnly.CustomerIdentifier.id==1 or readonly.processDate=gt=2026-10-01T00:00:00;readonly.processDate=lt=2026-10-02T00:00:00 (';' = and). |
| sort | string | no | Optional sort expression, for example ReadOnly.CreationDate. |
| pgsiz | integer | no | Page size (default 100, max 500). |
| pgnum | integer | no | Page number, from 1 (default 1). Use totalResults and _links.next of the previous reply. |
WRITE: submit a new outbound order for a customer and facility (the warehouse will pick and ship it). Not idempotent: calling twice creates two orders, so check extensiv_list_orders for the reference_num first. Needs ids from extensiv_list_customers, extensiv_list_facilities and SKUs from extensiv_list_items; billing_code, carrier and mode are required by Extensiv and must come from extensiv_list_
| Parameter | Type | Required | Notes |
|---|---|---|---|
| customer_id | string | yes | The customer id the order is for. |
| facility_id | string | yes | The facility id that fulfils it. |
| reference_num | string | yes | Your reference number for the order (for example a PO or web-shop order number). |
| ship_to | object | yes | The ship-to address. |
| items | array | yes | The order lines. |
| notes | string | no | Warehouse instructions. |
| shipping_notes | string | no | Carrier-specific shipping instructions. |
| billing_code | string | yes | Freight billing code as listed for the carrier by extensiv_list_carriers (billingCodes), for example Prepaid or BillThirdParty. |
| carrier | string | yes | Carrier name, for example UPS (from extensiv_list_carriers). |
| mode | string | yes | The carrier's service mode code (from extensiv_list_carriers). |
| account | string | no | The shipper account number for third-party or collect billing. |
WRITE: cancel one order by transaction id, with a reason and an optional cancellation fee. This cannot be undone; the order must be in a state the warehouse can still cancel (otherwise Extensiv answers with an error). The tool first reads the order to get the ETag Extensiv requires (If-Match). POST /orders/{transaction_id}/canceler.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| order_id | string | yes | The order's transaction id (from extensiv_list_orders). |
| reason | string | yes | Why the order is cancelled. |
| charge | number | no | Cancellation fee to bill, 0 (default) if none. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Extensiv MCP by usefulapi or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.4.0 · scanned 1 Nov 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digestc074c961f95c79b03d19631b35a307c3ee394cd64d3ce70d6f22466b2e24e50c
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| extensiv_list_facilities | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_list_carriers | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_list_customers | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_get_customer | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_list_items | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_list_orders | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_get_order | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_list_stock_summaries | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_list_inventory | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_list_stock_details | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_list_receivers | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_get_receiver | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_list_receiver_items | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_list_purchase_orders | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| extensiv_create_order | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| extensiv_cancel_order | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestc074c961f95c79b0
Scanned2026-11-01
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.4.0.
1.4.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Extensiv MCP by usefulapi can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.