# io.carrierscore/carrierscore

> FMCSA motor-carrier risk scores, monitoring, and carrier-selection evidence reports for AI agents.

- name: io.carrierscore/carrierscore
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 92/100
- quality: 88/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.carrierscore%2Fcarrierscore
- tools: https://api.protogrid.dev/v1/servers/io.carrierscore%2Fcarrierscore/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "carrierscore": {
      "type": "http",
      "url": "https://mcp.carrierscore.io/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 97
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-93% ~updated-65d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 88/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 6 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 8 of 8 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 4,044 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 8, about 4,044 tokens to load them all
- tool set hash: abd5efd5cfa0a9bc26f86c5b594c344f
- badge: [![protogrid quality](https://protogrid.dev/badge/io.carrierscore/carrierscore.svg)](https://protogrid.dev/servers/io.carrierscore/carrierscore)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.carrierscore.io/mcp (streamable-http, auth none, reachable true, uptime30d 0.9263158)

## Packages

_none_

## Tools (8)

- `audit_entries`: List the immutable audit-archive entries for the caller's API key: every Montgomery evidence report the key generated (text or json), newest first, each with its entry id, generation timestamp, DOT number, scoring date, methodology version and the SHA-256 of the archived report text. Requires a paid CarrierScore API key.

Use it to answer "which carriers did we generate evidence for, and when?" and to find the entry id to cite or verify for a given carrier and date. Monitor keys see the last 90 days; Compliance keys see everything ever archived.

Args:
  - dot_number (optional): only entries for this US DOT number
  - since (optional): YYYY-MM-DD; only entries generated on/after this date (UTC)
  - limit (optional): 1-500, default 50

Returns JSON: { tier, retention_days, total_entries, matched, count, entries: [{ entry_id, generated_at, dot_number, sha256, format_requested, scored_as_of, score_version }] }.

Errors: 403 without a paid key; 400 if since is malformed.
- `carrier_lookup`: Look up an FMCSA-registered motor carrier's identity by US DOT number: legal name, DBA, operating status, FMCSA safety rating, fleet size (power units, drivers), physical address, and registration dates.

Use this first when a booking/dispatch agent needs to confirm WHO a carrier is — that a DOT number is real, active, and matches the company name on a rate confirmation. It does not return risk indices (use carrier_score for those).

Returns JSON: { dot_number, legal_name, dba_name, status_code, safety_rating, power_units, total_drivers, phy_street, phy_city, phy_state, phy_zip, add_date, mcs150_date }.

Errors: 404 if the DOT is not in the FMCSA census (likely a typo or a fraudulent/never-registered carrier — treat as a red flag for booking).
- `carrier_score`: Get the CarrierScore risk indices for a carrier by US DOT number: two first-class, separately validated indices (0-100, HIGHER = RISKIER), each with a full component breakdown.

This is the core "is this carrier safe to book?" signal for AI booking agents. Served methodology v0.5 returns TWO indices, both population-relative and built from point-in-time public FMCSA data:
  - inspection_risk — inspection / compliance risk: violations and out-of-service rates per roadside inspection (24-month chronic, 6-month acute). Historically validated against the carrier's future out-of-service rate (validation block on the index).
  - crash_risk — crash risk: reportable crashes, fatal/injury crashes and tow-away crashes per roadside inspection (24 months). Historically validated against future reportable crashes (validation block on the index).
Present BOTH indices; do not collapse them into one number. Hard flags (active out-of-service order, no active insurance filing, high-confidence reincarnated-carrier link) add explicit surcharges — a carrier with any flag deserves extra scrutiny regardless of index values.

Returns JSON: { dot_number, legal_name, inspection_risk: { label, description, score, base, surcharge, percentile_basis, band, band_note, data_sufficiency, components: { <name>: { label, value, percentile, weight } }, validation: { auc_holdout, label, holdout_origins, post_selection_origin, source, text } }, crash_risk: { ...same shape... }, legacy_composite: { score, base_score, surcharge, rule, rule_text, validated: false, note }, carrier_score (backward-compatible: == legacy_composite.score under v0.5), base_score, surcharge, score_version ("0.5"), methodology_note, components (flat, backward-compatible), flags: string[], data_sufficiency (0-1, share of the components resting on observed vs neutral-imputed data), scored_as_of, disclaimer }. Older opt-in methodologies keep their shapes: v0 (six components), v0.3 (sub_indices), v0.4 (indices + composite).

Interpreting for booking decisions: treat the indices as documented decision-support evidence, not an approve/deny verdict. legacy_composite / carrier_score is NOT validated and is kept only so older integrations keep working — never present it as the carrier's risk score. Low data_sufficiency means limited inspection history — common for new carriers, itself a risk signal. Always relay each index's validation text and the disclaimer when presenting the result.

Errors: 404 if the DOT is not in the scored population; 503 if scores have not been computed yet.
- `list_alerts`: Retrieve the alert history for a saved carrier list (see save_carrier_list), newest first. Requires the same paid API key that saved the list.

Each alert records one change detected between consecutive daily scoring runs for one carrier: type (oos_order_activated, authority_lost, insurance_lapsed, status_changed, inspection_risk_jump, crash_risk_jump, score_jump, reincarnation_link), severity (critical / high / medium / low), the field that changed with its before/after values, the DOT and legal name, and the scoring dates compared. inspection_risk_jump / crash_risk_jump (index base up >= 10 points, medium) are the primary deterioration signals; score_jump on the legacy composite is emitted at low severity for backward compatibility. Use it to answer "did anything change on my carrier list?" — critical alerts (new OOS order, authority lost) mean the carrier should not be dispatched until verified; follow up with carrier_score or montgomery_file for the full picture.

Args:
  - list_id: the lst_... id returned by save_carrier_list
  - since (optional): YYYY-MM-DD; only alerts from scoring runs on/after this date

Returns JSON: { list_id, since, count, alerts: [{ ts, as_of, prev_as_of, list_id, list_name, dot, legal_name, type, severity, field, before, after }] }. An empty alerts array means no monitored change since the given date (alerts only exist once two daily scoring runs have happened).

Errors: 403 without a paid key; 404 if the list id is unknown for this key; 400 if since is not YYYY-MM-DD.
- `monitor_carriers`: Batch risk check for a list of carriers by US DOT number (max 100 per call): score summary and hard flags for each.

Use when an agent is screening multiple candidate carriers for a load, or re-checking a broker's active carrier roster ("did any of my carriers pick up an out-of-service order or drop insurance?"). For a full breakdown of any single carrier that looks risky here, follow up with carrier_score or montgomery_file.

Args:
  - dot_numbers: array of DOT number strings, 1-100 entries

Returns JSON: { scored_as_of, requested, found, carriers: [{ dot_number, legal_name, inspection_risk (0-100 inspection / compliance risk index, higher = riskier), crash_risk (0-100 crash risk index), carrier_score (legacy composite under v0.5 — backward compatibility only; use the two indices), data_sufficiency, flags: string[] }], not_found: string[], disclaimer }. DOTs in not_found are absent from the scored population — verify them with carrier_lookup; an unknown DOT on your roster is itself a red flag.

Errors: 400 if the list is empty or exceeds 100 (split into batches); 503 if scores are not computed yet.
- `montgomery_file`: Generate a timestamped Montgomery file — a carrier-selection evidence report — for a carrier by US DOT number.

Since Montgomery v. Caribe Transport II (SCOTUS, May 2026), freight brokers are exposed to state-law negligent-selection claims and need documented, timestamped, safety-data-based carrier selection. This report is that artifact: the two risk indices (inspection / compliance risk and crash risk, each with its components, percentiles, activity-band context and its own historical-validation line), the legacy composite (labelled backward-compatibility only), hard flags, FMCSA safety rating, and the methodology disclaimer, dated as of the scoring run. A booking agent should generate and retain this file at the moment a carrier is selected for a load.

Args:
  - dot_number: US DOT number, digits only
  - format: "text" (default; the filing-ready plain-text report, available on the free tier) or "json" (structured fields; requires an API key on the monitor or compliance tier)

Returns: format="text" gives the plain-text report (structured field report_text); format="json" gives structured fields { report, generated, dot_number, legal_name, dba_name, safety_rating, status_code, power_units, inspection_risk, crash_risk, legacy_composite (v0.5), carrier_score (backward-compatible), components, flags, data_sufficiency, score_version, scored_as_of, disclaimer } (v0.4 parquets return indices + composite instead). Every report embeds the disclaimer verbatim — keep it when storing or quoting the report.

Audit archive (paid tiers): every report generated with an API key is stored immutably server-side and the result carries audit_entry_id + sha256 (SHA-256 of the plain-text report). Quote both when citing the report; later, verify_evidence(entry_id) proves the archived copy is unchanged and audit_entries lists what was generated. Monitor keys can retrieve the last 90 days (2,000 reports/month); Compliance keys have unlimited retention and reports.

Errors: 403 if format=json without an API key; 404 unknown DOT; 429 if a Monitor key has used its 2,000 reports this month (upgrade hint in the message); 503 if scores are not computed yet.
- `save_carrier_list`: Save a named list of carriers (by US DOT number) for continuous monitoring. Requires a paid CarrierScore API key (Monitor or Compliance tier) — connect with your key via OAuth (or set CARRIERSCORE_API_KEY on a self-hosted server); the free tier gets a 403 with an upgrade link.

Once saved, CarrierScore diffs every carrier on the list against the previous day's scoring run after each daily run and records alerts: new out-of-service order (critical), operating authority lost (critical), insurance filing lapsed (high), operating status leaving Active (high), risk score up 10+ points (medium), high-confidence reincarnated-carrier link appearing (medium). Alerts are always retrievable with list_alerts; optionally they are also pushed to a webhook (JSON POST, HMAC-signed via the X-CarrierScore-Signature header with the per-key secret from GET /v1/lists) and/or summarized in one daily digest email.

Use this when a broker asks to "watch" or "keep an eye on" their carrier roster. Caps: 500 DOTs total across all lists on the Monitor tier, 5000 on Compliance; up to 50 lists per key. Saving the same DOT twice in one list is deduped.

Args:
  - name: short label for the list (1-100 chars)
  - dot_numbers: array of DOT number strings (1-8 digits each)
  - webhook_url (optional): https URL to POST new alerts to
  - email (optional): address for the daily digest

Returns JSON: { list_id, name, dots, created, updated, webhook_url?, email? }. Keep list_id — list_alerts needs it.

Errors: 403 without a paid key; 400 on invalid DOTs, empty list, or exceeding the tier cap (message says which); 401 bad key.
- `verify_evidence`: Verify an archived Montgomery evidence report by its audit entry id: CarrierScore re-reads the immutable stored copy, recomputes its SHA-256 and reports whether it matches the hash recorded at generation time (and, optionally, a hash the caller supplies — e.g. the sha256 printed on a broker's filed copy). Requires the same paid API key that generated the report.

Use it when a broker or auditor needs to prove that a filed evidence report is exactly what CarrierScore produced on the stated date. match=true means the archived report is byte-identical to what was served; match_supplied compares against the caller's own hash. Follow up with the audit_entries list to find ids, or with montgomery_file to generate a fresh report.

Args:
  - entry_id: the audit_entry_id returned by montgomery_file (also listed by audit_entries)
  - sha256 (optional): a 64-hex SHA-256 to compare against the archived report (text or canonical json)

Returns JSON: { entry_id, dot_number, generated_at, scored_as_of, score_version, format_requested, sha256_stored, sha256_computed, match, sha256_json_stored, sha256_json_computed, match_json, sha256_supplied?, match_supplied? }.

Errors: 403 without a paid key, or (Monitor tier) if the entry is older than the 90-day retrieval window; 404 if the entry id is unknown for this key.