Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the ListPlus agent 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%2Flistplus.ai%2Flistplus" | 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%2Flistplus.ai%2Flistplus" | 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 ListPlus agent API.
Check contact and company records for errors such as email-domain typos, role mailboxes, and near-duplicates with check_records
Find a person by name and company, LinkedIn URL, work email, or a natural-language query with find_person
Fill missing email, phone, job_title, linkedin_profile_url, or company fields on records with enrich_records, priced first with estimate
Verify whether email addresses are deliverable, returning valid, invalid, catch_all, or unknown
GET STARTED
Count companies that match filters such as countries and naics codes, broken down by one dimension
Search people by job_titles, seniorities, departments, locations, and company_domains, and load matching companies into a list
Clean a workspace list with check_list and fix_list, then send its records to a HubSpot, Slack, or lemlist pipeline
Patterns agents use ListPlus agent API for, with concrete tasks.
★ AI sales assistant cleaning and enriching a lead list
A sales assistant agent given a pasted CRM export can tell the user what is wrong and what it would cost to fix. Through Jentic the agent searches for 'check contact records for errors', calls check_records on the rows, then calls enrich_records with estimate: true for the missing email and phone fields and relays the price before running it. The agent key is injected by Jentic, and each response's tell_your_user text gives the agent a plain summary to pass on.
POST /a/v1/check_records with the user's records, then POST /a/v1/enrich_records with fields ['email', 'phone'] and estimate true, report the price, and rerun without estimate once the user approves
Market sizing before a campaign
Before committing to a segment, a founder wants to know how many companies fit it. count_companies returns the number of companies matching filters such as countries and naics codes for free, and with the by option and a key it breaks the total down by a dimension such as industries, employees, or revenue. search_options returns the exact filter values to use.
POST /a/v1/search_options to get the naics value for apparel manufacturing, then POST /a/v1/count_companies with filters countries ['IT'] and naics ['315'] and by 'employees'
Prospect search and list building
Outbound teams build lists of decision-makers that match a profile. search_people filters by job_titles, seniorities, departments, locations, industries, headcount, and company_domains, with has_email and has_mobile flags, and can write results into a list_id. load_companies does the same for company records, accepts max_credits as a ceiling, and supports estimate for the price first.
POST /a/v1/search_people with job_titles ['Head of Marketing'], locations ['Germany'], has_email true, and a list_id, then POST /a/v1/describe_list to confirm the records landed
Email deliverability checks before sending
Sending to bad addresses hurts sender reputation. verify_email checks whether each address is deliverable and labels it valid, invalid, catch_all, or unknown, at 0.3 credits per address according to the spec, with addresses checked in the last 7 days at no charge.
POST /a/v1/verify_email with a list of 50 addresses and drop any marked invalid before passing the rest to the sequencer
26 endpoints — the listplus agent api checks b2b contact and company records for errors, sizes markets, finds people and leads, and fills missing fields such as work email, mobile number, job title, and linkedin profile.
METHOD
PATH
DESCRIPTION
/a/v1/check_records
Check records for errors
/a/v1/find_person
Find a person
/a/v1/enrich_records
Enrich records with missing fields
/a/v1/verify_email
Verify email deliverability
/a/v1/search_people
Search people by role and company
/a/v1/count_companies
Count companies matching filters
/a/v1/get_job
Get job status
/a/v1/send_to_pipeline
Send records to a pipeline
/a/v1/check_records
Check records for errors
/a/v1/find_person
Find a person
/a/v1/enrich_records
Enrich records with missing fields
/a/v1/verify_email
Verify email deliverability
/a/v1/search_people
Search people by role and company
/a/v1/count_companies
Count companies matching filters
/a/v1/get_job
Get job status
/a/v1/send_to_pipeline
Send records to a pipeline
What agents get from Jentic-routed access to this vendor.
Setup
Wiring ListPlus by hand means handling a bearer agent key, tracking which operations run anonymously and which need the key, calling estimate before paid actions, and polling get_job for long runs. Through Jentic you install once, import ListPlus from the API Directory, store the agent key once, and your agent calls it.
Permission scoping
ListPlus exposes each action as its own POST path and carries the list_id and records in the request body, so rules bound which operations your agent may call, not which list it works on. You choose the operations it may call, so credit-spending or destructive ones like enrich_records or remove_column are not included unless you add them.
Credential isolation
Your ListPlus agent 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 contacts for errors' or 'find a person at a company', and Jentic returns the matching ListPlus operation with its input schema so the agent calls the right action without reading the manual.
Alternatives and complements available in the Jentic catalogue.
Specific to using ListPlus agent API through Jentic.
What authentication does the ListPlus agent API use?
The OpenAPI spec declares agentKey, an HTTP bearer scheme that carries a workspace agent key beginning with lpk_, issued from the agents page of a ListPlus workspace. A few operations also accept anonymous calls, including what_can_you_do, search_options, count_companies, and check_records for up to 25 records, while enrichment, people search, email verification, and list work need the key.
How much does enrichment cost with the ListPlus agent API?
Per the enrich_records description, filling a work email from a name and company costs about 2.39 credits per record and at most 9, a mobile about 3.84 and at most 12, and a job title about 1.41 and at most 13.5, charged per hit for email and phone. verify_email costs 0.3 credits per address. Sending estimate: true on a paid action returns its exact price without running it.
What are the rate limits for the ListPlus agent API?
The OpenAPI spec notes that find_person is rate-limited but does not state numeric limits. Check the ListPlus agent manual at https://listplus.ai/a for current limits.
Is there a ListPlus MCP server?
You don't need an MCP server to give your agent ListPlus. Jentic connects it directly from the API Directory: import it, store your agent key once, and your agent calls the check, find, and enrich operations it needs, discovered on demand rather than preloaded into its context.
Can I limit what my agent is allowed to do with ListPlus?
Yes. For example, write a rule that allows only check_records, count_companies, and find_person, so the agent can audit records, size markets, and look people up but cannot spend credits through enrich_records or verify_email, or change a list with update_records. Every call it makes is logged.
How do I enrich records through Jentic?
Add ListPlus to your Jentic One instance from the directory and store your lpk_ agent key. Your agent searches for 'fill missing work emails', loads the enrich_records operation, and posts the records with fields such as email and phone, first with estimate: true to get the price, then polls get_job with the returned job_id for larger runs. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Check B2B contact records for errors, find people by name or role, search and count companies, enrich missing emails and phone numbers, verify emails, and manage workspace lists.
Use for: Check this CSV of contacts for typos and duplicates, Find the CFO of a specific company, I need to fill in missing work emails for a list of leads, Verify whether these email addresses can receive mail
Not supported: Does not handle email sending, campaign sequencing, or CRM deal tracking itself. Use for checking, finding, enriching, and organising B2B contact and company records only.
The ListPlus agent API checks B2B contact and company records for errors, sizes markets, finds people and leads, and fills missing fields such as work email, mobile number, job title, and LinkedIn profile. Its record checks run more than 100 tests covering email-domain typos, role mailboxes, duplicates, and phone codes that do not fit the country, and are free for up to 25 records without a key. Beyond one-off lookups, it works on a workspace's lists: query, add, update, tag, deduplicate, derive columns, set trigger rules, and hand records to a pipeline such as HubSpot, Slack, or lemlist. Every paid action accepts estimate: true to return its price without running, and every response carries options with next steps and their prices.
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>