Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the CarrierScrub API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fcarrierscrub.com%2Fcarrierscrub" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fcarrierscrub.com%2Fcarrierscrub" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with CarrierScrub API.
Check one carrier by USDOT or MC number for a GO, CAUTION, or STOP verdict
Return dated reason codes that each cite a published FMCSA fact
Check a list of carriers in batch from a CSV or XLSX file
Read every dated grant, suspension, revocation, and reinstatement of a carrier's operating authority
Report how many carriers' FMCSA authority, insurance, and contact records changed in a day or week
GET STARTED
Patterns agents use CarrierScrub API for, with concrete tasks.
★ Agent-Run Carrier Vetting
Before a brokerage agent tenders a load, it checks the carrier by USDOT or MC number through Jentic and reads the GO, CAUTION, or STOP verdict with its dated FMCSA reason codes. Each reason names the FMCSA record it used and that record's date, so the agent acts on published facts, not inferences. A rule can keep the agent on the carrier-check operations and nothing else.
Check a carrier by its MC number and block the load tender if the verdict is STOP, logging the reason codes.
Bulk Carrier Screening
An operations team screens a whole carrier list at once by uploading a CSV or XLSX file to the batch endpoint, getting a verdict and dated reasons for each row. CarrierScrub dates every result and names the FMCSA record it drew from, so a bulk run is reproducible. Teams use this to re-screen their approved carrier base on a schedule.
Upload a CSV of 500 carriers to the batch endpoint and flag every row returning CAUTION or STOP.
Authority and Activity Monitoring
A compliance workflow reads a carrier's full authority history, every dated grant, suspension, revocation, and reinstatement, and tracks how many carriers' FMCSA authority, insurance, and contact records changed over a day or week. Both of these endpoints are open and need no key, so monitoring runs without credentials. This surfaces carriers whose authority recently lapsed.
Pull the authority history for a carrier and alert if a revocation is dated in the last 30 days.
4 endpoints — the carrierscrub api vets motor carriers for freight brokerages using fmcsa records.
METHOD
PATH
DESCRIPTION
/v1/lookup
Check one carrier by USDOT or MC number
/v1/batch
Check a list of carriers from a CSV or XLSX file
/v1/authority-history
Read a carrier's dated operating-authority history
/v1/fmcsa-activity
Count carriers whose FMCSA records changed in a day or week
/v1/lookup
Check one carrier by USDOT or MC number
/v1/batch
Check a list of carriers from a CSV or XLSX file
/v1/authority-history
Read a carrier's dated operating-authority history
/v1/fmcsa-activity
Count carriers whose FMCSA records changed in a day or week
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the CarrierScrub API by hand means creating an Agency-plan key, sending it as a bearer token, and remembering the FMCSA activity and authority-history endpoints are open while the lookup and batch calls are not. Through Jentic you install once, import CarrierScrub from the API Directory, store the key once, and your agent calls it.
Permission scoping
CarrierScrub exposes four read endpoints and no write operations, so a rule bounds your agent to the single carrier lookup, the batch check, the authority history, or the FMCSA activity feed. You choose which of those it may call, and nothing it can reach changes a record.
Credential isolation
Your CarrierScrub key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'check a carrier by USDOT number', and Jentic returns the matching CarrierScrub operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using CarrierScrub API through Jentic.
What authentication does the CarrierScrub API use?
The CarrierScrub API authenticates with a bearer token in the Authorization header, per its OpenAPI spec, using keys that start with cs_live_. An owner or admin of an Agency-plan brokerage creates the key, and a key unused for 60 days stops working. The FMCSA activity and authority-history endpoints are open and need no key. Through Jentic the token is stored encrypted by your own Jentic One instance and injected only at call time.
Can I check a carrier's FMCSA status with the CarrierScrub API?
Yes. A single lookup takes a USDOT or MC number and returns a GO, CAUTION, or STOP verdict with dated reason codes, and a batch call checks a list from a CSV or XLSX file. You can also read a carrier's full operating-authority history and weekly FMCSA record-change counts.
What are the rate limits for the CarrierScrub API?
The OpenAPI spec does not specify rate limits for the CarrierScrub API. Check the vendor's documentation at https://carrierscrub.com/auth.md for current limits and plan details.
Can I limit what my agent is allowed to do with the CarrierScrub API?
Yes. Write a rule that allows only the single carrier lookup, or add the batch check and the open history and activity reads, so the agent can vet carriers and nothing more. There are no write operations in this API, and every call it makes is logged.
Is there a CarrierScrub MCP server?
You don't need an MCP server to give your agent the CarrierScrub API. Jentic connects it directly from the API Directory: import it, store your Agency-plan key once, and your agent calls the carrier lookup and history operations. You skip loading another server's tool definitions into the agent's context.
How do I vet a carrier through Jentic?
Add the CarrierScrub API from the Jentic API Directory and store your Agency-plan key once. Your agent then searches by intent such as 'check a carrier by MC number' and Jentic returns the matching operation with its input schema, so it can read the verdict and reason codes. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Check a motor carrier by USDOT or MC number for a GO, CAUTION, or STOP verdict with dated FMCSA reason codes, in single or batch form. Read authority history and weekly FMCSA record-change activity without a key.
Use for: Check whether a carrier is safe to onboard by its MC number, Look up a carrier's verdict and reason codes by USDOT number, Review the operating-authority history for a motor carrier, Run a batch carrier check from a spreadsheet
Not supported: Does not book loads, track shipments, or set carrier rates. Use for FMCSA-based carrier vetting, authority history, and record-change activity only.
The CarrierScrub API vets motor carriers for freight brokerages using FMCSA records. A single lookup takes a carrier's USDOT or MC number and returns a GO, CAUTION, or STOP verdict with dated reason codes, and a batch call checks a list of carriers from a CSV or XLSX file. Two open endpoints report how many carriers' FMCSA authority, insurance, and contact records changed over a day or week and give the full dated history of a carrier's operating authority. Every result names the FMCSA record it used and that record's date, and each reason states a published fact rather than a conclusion about the company.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>