# GBG Loqate - Reach

> Verify addresses, email addresses, and phone numbers with confidence scores.

- name: io.github.gbgplc/lqt
- version: 0.6.2
- connection class: R0 (autonomous)
- trust: 90/100
- quality: 85/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.gbgplc%2Flqt
- tools: https://api.protogrid.dev/v1/servers/io.github.gbgplc%2Flqt/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "lqt": {
      "type": "http",
      "url": "https://reach.prod.fabric.gbgplatforms.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 65
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% ~updated-166d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 85/100 (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: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 11 of 11 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: verify_address_batch (destructiveHint, idempotentHint); verify_contact (destructiveHint, idempotentHint); verify_email_batch (destructiveHint, idempotentHint); …
- pass `tools.token_cost`: about 7,442 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: 11, about 7,442 tokens to load them all
- tool set hash: 56064229d7a63210474a8cef02da7acc
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.gbgplc/lqt.svg)](https://protogrid.dev/servers/io.github.gbgplc/lqt)
- 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://reach.prod.fabric.gbgplatforms.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (11)

- `list_policies`: List available decisioning policies (strict, shipping, standard, permissive) with their thresholds.
- `retrieve_address`: Resolve a suggestion id from address.suggestions into its full cleansed address components (organisation, sub-building, number, street, city, province, postcode, country). Use this when you need the address itself — to fill a form or show a confirmation — rather than a decision; to verify a chosen suggestion instead, pass 'suggestion_id' to verify_address. CONSUMES A LOQATE CREDIT per call, so resolve only the one suggestion the user chose. The result is reference data, NOT a verification. Requires a Loqate API key.
- `show_policy`: Show full details for a specific decisioning policy.
- `verify_address`: Verify an address against Loqate's global reference data. Returns a confidence score (0-1), verification status, and a policy-driven accept/review/reject recommendation. Set 'suggest' to also get alternative addresses suggested by Loqate whenever the address does not clear the policy; offer them to the user and verify the chosen one in a second call before treating it as good. Suggestions require a separately licensed Loqate feature enabled on the account — without it, verification still succeeds and the problem is reported in suggestions.error. Requires a Loqate API key — pass it via the 'key' field (get one at account.loqate.com).
- `verify_address_batch`: Verify up to 100 addresses in one call. Up to 100 records per call; the results array is in submission order and each entry carries its input index, so results can be zipped back onto rows without relying on order. One bad record fails only itself — it carries an error while the rest are verified. Suggestions are not available in batch. Records are grouped by country before being sent, as Loqate recommends, so the cost is one upstream call per distinct country in the batch rather than one per call. Set detect_country to guess the country of records that do not supply one — detection runs per record, before grouping, so a mixed batch still sends each group with the right default. Requires a Loqate API key — pass it via the 'key' field.
- `verify_contact`: Verify address, email, and/or phone together. Returns individual results plus an overall recommendation (most conservative of all provided fields). Set 'suggest' to also get alternative addresses suggested by Loqate whenever the address does not clear the policy; offer them to the user and verify the chosen one in a second call before treating it as good. Suggestions require a separately licensed Loqate feature enabled on the account — without it, verification still succeeds and the problem is reported in suggestions.error. Requires a Loqate API key — pass it via the 'key' field.
- `verify_contact_batch`: Verify up to 100 contacts in one call, each with any combination of address, email and phone, returning an overall recommendation per contact. Results are in submission order and each carries its input index. One bad record fails only itself, and a field that cannot be verified does not remove the contact — the overall recommendation is drawn from whichever fields were checked. The three types run concurrently, so a full batch is paced by email at roughly 7 seconds per 100. Requires a Loqate API key — pass it via the 'key' field.
- `verify_email`: Verify an email address via Loqate. Returns confidence, risk level, and accept/review/reject recommendation. Requires a Loqate API key — pass it via the 'key' field.
- `verify_email_batch`: Verify up to 100 email addresses in one call. Up to 100 records per call; the results array is in submission order and each entry carries its input index, so results can be zipped back onto rows without relying on order. One bad record fails only itself — it carries an error while the rest are verified. Suggestions are not available in batch. The batch endpoint returns less detail than single verification: risk, complainer and reason are absent, though the accept/review/reject recommendation and the disposable-mailbox flag are identical. Requires a Loqate API key — pass it via the 'key' field.
- `verify_phone`: Verify a phone number via Loqate. Returns confidence, number type, carrier, and accept/review/reject recommendation. Requires a Loqate API key — pass it via the 'key' field.
- `verify_phone_batch`: Verify up to 100 phone numbers in one call. Up to 100 records per call; the results array is in submission order and each entry carries its input index, so results can be zipped back onto rows without relying on order. One bad record fails only itself — it carries an error while the rest are verified. Suggestions are not available in batch. Phone validation has no bulk endpoint, so numbers are checked concurrently against a shared limit. Measured at around 2.6s for 100 numbers, which is the fastest of the three batch types — email is the slowest, at roughly 7s for 100, because it probes mail servers. Requires a Loqate API key — pass it via the 'key' field.