Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Version 2 Voice LI-ELS, 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%2Flumen.com%2Flumen-version-2-voice-li-els" | 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%2Flumen.com%2Flumen-version-2-voice-li-els" | 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 Version 2 Voice LI-ELS API.
Validate a service address against Lumen systems via POST /Voice/v1/Numbers/serviceAddress
Return the address split into USPS fielded format: streetNumber, preDirectional, streetName, streetSuffix, city, state, and zipCode
Normalise directionals to values such as N, NE, E, or SW and states to two-letter codes
Surface an errorMessage when Lumen cannot validate the address, before an order is attempted
GET STARTED
Patterns agents use Version 2 Voice LI-ELS API for, with concrete tasks.
★ Address check by a provisioning agent through Jentic
Before a provisioning agent orders voice numbers, it confirms the customer's site address with Lumen. It searches Jentic for 'validate a Lumen service address', receives POST /Voice/v1/Numbers/serviceAddress with its fielded address schema, and passes the standardised result on to the ordering step, stopping early if Lumen returns an errorMessage.
Call POST /Voice/v1/Numbers/serviceAddress with streetNumber 200, preDirectional E, streetName COLFAX, streetSuffix AVE, city DENVER, state CO, zipCode 80203, country US, and report the returned address or errorMessage
Order form address clean-up
A sales or onboarding form collects a free-form address. Sending its parts to the Lumen validation operation returns the address split into USPS fields, with directionals and the state code normalised, so downstream Lumen voice orders carry an address Lumen already accepts.
Call POST /Voice/v1/Numbers/serviceAddress with the address parts from the form and write the returned streetNumber, streetName, streetSuffix, city, state, and zipCode back to the order record
Bulk site list verification
When a business moves several offices onto Lumen voice service, checking each site address first catches the ones Lumen cannot place. Running each address through the validation operation in turn yields a list of accepted addresses and those with an errorMessage to fix before ordering.
For each office address in the list, call POST /Voice/v1/Numbers/serviceAddress and produce a table of addresses that validated and those that returned an errorMessage
1 endpoints — the lumen version 2 voice li-els api validates a service address against lumen systems and returns it in usps fielded format, the address check that precedes ordering lumen voice numbers.
METHOD
PATH
DESCRIPTION
/Voice/v1/Numbers/serviceAddress
Validate a service address
/Voice/v1/Numbers/serviceAddress
Validate a service address
What agents get from Jentic-routed access to this vendor.
Setup
Wiring this Lumen API by hand means running the OAuth2 client-credentials exchange, sending your BusOrg in the x-customer-number header, and mapping addresses into USPS fields with enumerated directionals and state codes. Through Jentic you install once, import it from the API Directory, store your client credentials once, and your agent calls it.
Permission scoping
The address travels in the request body, so rules bound which operations your agent may call, not which address. With a single operation here, allowing it gives the agent address validation and nothing else.
Credential isolation
Your Lumen client credentials are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'validate a Lumen service address', and Jentic returns POST /Voice/v1/Numbers/serviceAddress with its input schema, including the directional and state enums, so the agent sends a well-formed request without reading the developer portal.
Alternatives and complements available in the Jentic catalogue.
Specific to using Version 2 Voice LI-ELS API through Jentic.
What authentication does the Lumen Version 2 Voice LI-ELS API use?
Per its OpenAPI spec, it uses OAuth2 with the client credentials flow, with a token URL of /oauth/token on Lumen's test host. The request also carries the required x-customer-number header, your Lumen-defined customer ID, also known as the BusOrg number. Through Jentic, your client credentials are stored encrypted by your own Jentic One instance and the token is attached at execution time.
What does the Lumen address validation return?
POST /Voice/v1/Numbers/serviceAddress returns the service address in USPS fielded format: streetNumber, streetNumberSuffix, preDirectional, streetName, postDirectional, streetSuffix, city, state, and zipCode. When Lumen cannot validate the address, the response carries an errorMessage.
What are the rate limits for the Lumen Version 2 Voice LI-ELS API?
The OpenAPI spec does not specify rate limits. Check https://developer.lumen.com/contact-us/ for current limits on your account.
How do I validate a service address with Lumen through Jentic?
Install Jentic One, add the Lumen Version 2 Voice LI-ELS API from the Jentic directory, and store your OAuth2 client credentials. Your agent searches for 'validate a Lumen service address', receives POST /Voice/v1/Numbers/serviceAddress with its address schema, and sends the address parts. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a Lumen address validation MCP server?
You don't need an MCP server to give your agent this Lumen API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the address validation operation by intent.
Can I limit what my agent is allowed to do with the Lumen Version 2 Voice LI-ELS API?
Yes. This spec exposes only the address validation operation, so a rule allowing POST /Voice/v1/Numbers/serviceAddress gives the agent exactly that and nothing more. If you also import Lumen's ordering API, keep its ordering and disconnect operations out of the same rule, and the agent's calls are logged for review.
Know of an official OpenAPI document? Contribute it →
For Agents
Validate a US service address against Lumen systems and get it back in USPS fielded format before ordering voice numbers. Uses OAuth2 client credentials and an x-customer-number header.
Use for: Validate this street address before ordering Lumen voice service, Check whether Lumen recognises 200 E Colfax Ave, Denver, Get this address in USPS fielded format, I need to confirm a customer's service address with Lumen
Not supported: Does not order, port, or disconnect telephone numbers, and does not geocode addresses. Use for validating service addresses against Lumen systems only.
The Lumen Version 2 Voice LI-ELS API validates a service address against Lumen systems and returns it in USPS fielded format, the address check that precedes ordering Lumen voice numbers. A single operation takes the street number, directionals, street name and suffix, city, state, zip code, and country, and responds with the standardised fields or an errorMessage. Calls use an OAuth 2.0 client-credentials token and carry the customer's Lumen BusOrg ID in the x-customer-number header; the spec's server is Lumen's test environment.
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>