Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Reverse Contact 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%2Freversecontact.com%2Freversecontact" | 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%2Freversecontact.com%2Freversecontact" | 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 Reverse Contact API.
Enrich a person from email, or from firstName, lastName, and companyDomain, via POST /v2/enrich/persons
Enrich a company from its domain via POST /v2/enrich/companies, optionally with fullProfile
Search and count people by currentPositionTitle, currentSeniority, skills, location, and changedJobsWithinDays
Run a natural-language people search from a single prompt via POST /v2/search/people/prompt
GET STARTED
Find lookalike profiles for a given person profile URL or id
Find a contact's work email or phone number from a profile URL or name plus companyDomain
Poll async live-fetch and resolve jobs by webhookId and check remaining credits via GET /v2/usage
Patterns agents use Reverse Contact API for, with concrete tasks.
★ AI prospecting agent with scoped enrichment
A developer's sales agent needs to turn a list of signups into qualified leads without pasting an API key into its prompt. Through Jentic the agent searches by intent, gets the Reverse Contact enrichPerson operation with its input schema, and calls it with the bearer key injected at execution time. It enriches each email with title and company, then enriches the company domain, and only the enrichment operations the developer allowed can run.
For the signup jane@acme.com, call POST /v2/enrich/persons with email 'jane@acme.com', then call POST /v2/enrich/companies with domain 'acme.com' and summarise her title and the company's industry
Building a targeted prospect list
A founder wants a list of decision makers who recently changed roles, a common buying trigger. POST /v2/search/people/count sizes the audience first, POST /v2/search/people returns the matching profiles with cursor pagination, and filters such as currentSeniority, currentFunction, location, and changedJobsWithinDays narrow the results. GET /v2/search/people/available-fields lists the accepted filter values.
Call POST /v2/search/people/count with currentSeniority set to a director-level value, location 'Berlin', and changedJobsWithinDays 90, then page POST /v2/search/people with the same filters and perPage 25
Finding contact details for a known person
A recruiter has a candidate's profile URL but no way to reach them. POST /v2/contact/email and POST /v2/contact/phone look up a work email or phone number from a profile url, or from a name plus companyDomain, and accept a webhookUrl when the lookup runs asynchronously. The recruiter's agent polls GET /v2/webhooks/{webhookId} for the result.
Call POST /v2/contact/email with firstName 'Sam', lastName 'Lee', and companyDomain 'example.com', then poll GET /v2/webhooks/{webhookId} with the returned webhookId until the email result is ready
Natural-language and lookalike search
Writing exact filters is slow when the target is easy to describe in a sentence. POST /v2/search/people/prompt takes a required prompt such as 'product managers at Series B fintech startups in London' and returns matching people, while POST /v2/search/people/lookalike starts from one profile url or id and finds similar people. Both use cursor and perPage for pagination.
Call POST /v2/search/people/prompt with prompt 'product managers at fintech startups in London' and perPage 20, then take the top result and call POST /v2/search/people/lookalike with its url
22 endpoints — the reverse contact api enriches people and companies from an email address, a name plus company, a domain, or a profile url, and returns the person or company record in a consistent response envelope with quotas and metadata.
METHOD
PATH
DESCRIPTION
/v2/enrich/persons
Enrich a person
/v2/enrich/companies
Enrich a company from its domain
/v2/search/people
Search people with filters
/v2/search/people/prompt
Search people from a natural-language prompt
/v2/contact/email
Find a contact's email
/v2/fetch/persons/live
Fetch a live person profile
/v2/webhooks/{webhookId}
Poll an async job
/v2/usage
Read account usage
/v2/enrich/persons
Enrich a person
/v2/enrich/companies
Enrich a company from its domain
/v2/search/people
Search people with filters
/v2/search/people/prompt
Search people from a natural-language prompt
/v2/contact/email
Find a contact's email
/v2/fetch/persons/live
Fetch a live person profile
/v2/webhooks/{webhookId}
Poll an async job
/v2/usage
Read account usage
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Reverse Contact by hand means sending a bearer key on each call, unwrapping its success, data, and quotas envelope, and polling webhookId for async live and resolve jobs. Through Jentic you install once, import Reverse Contact from the API Directory, store the key once, and your agent calls it.
Permission scoping
Reverse Contact carries the person, company, or search filters in the request body, so rules bound which operations your agent may call, not which people it looks up. Limit it to the operations it needs, such as enriching a person or a company, so credit-spending lookups like contact email or phone search are not included unless you add them.
Credential isolation
Your Reverse Contact API 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 'enrich a person from an email' or 'find people who changed jobs', and Jentic returns the matching Reverse Contact operation with its input schema so the agent fills the right filters without reading the docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Reverse Contact API through Jentic.
What authentication does the Reverse Contact API use?
The Reverse Contact API authenticates with HTTP bearer auth per its OpenAPI spec: you pass an API key from the developer dashboard as Authorization: Bearer followed by a key that starts with rc_. Through Jentic the key is stored by your own Jentic One instance and attached to each call, so it never appears in the agent's context.
How do asynchronous lookups work in the Reverse Contact API?
Live fetch, resolve, and contact lookups such as POST /v2/fetch/persons/live and POST /v2/resolve/persons/email acknowledge the request with a webhookId in the response data. Poll GET /v2/webhooks/{webhookId} until the job finishes, or pass a webhookUrl in the request body to receive the result at your own endpoint.
What are the rate limits for the Reverse Contact API?
The OpenAPI spec does not state numeric rate limits. Every response carries a quotas object, and GET /v2/usage reports account usage, so an agent can check its remaining allowance before a large batch. See https://reversecontact.com for plan limits.
Is there a Reverse Contact MCP server?
You don't need an MCP server to give your agent Reverse Contact. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls enrichment and search operations on demand without loading another server's tool definitions into its context.
How do I enrich an email address through Jentic?
Search Jentic for 'enrich a person from an email', load the enrichPerson operation, and execute POST /v2/enrich/persons with the email in the request body. The person record comes back under data.person, and you can follow with POST /v2/enrich/companies using the company domain. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Reverse Contact API?
Yes. If the agent only qualifies inbound signups, write a rule that allows POST /v2/enrich/persons and POST /v2/enrich/companies. It can enrich the emails and domains you hand it, but it cannot run open-ended people searches or contact lookups that spend credits, and every call is logged.
Can I count matching people before running a search?
Yes. POST /v2/search/people/count accepts the same filters as POST /v2/search/people, such as currentPositionTitle, currentSeniority, skills, and location, and returns how many profiles match. Sizing the audience first lets an agent tighten filters before paging through results.
For Agents
Enrich a person from an email or a company from a domain, search and count people by role, seniority, and skills, and find a contact's email or phone, with async jobs polled by webhookId.
Use for: Enrich this email address with the person's name, title, and company, Get the company profile for the domain acme.com, Find all heads of engineering in Berlin who changed jobs in the last 90 days, Count how many people match this search before I pull the results
Not supported: Does not send emails, run outreach sequences, or store leads in a CRM. Use for enriching, searching, and finding contact details for people and companies only.
The Reverse Contact API enriches people and companies from an email address, a name plus company, a domain, or a profile URL, and returns the person or company record in a consistent response envelope with quotas and metadata. It searches people by filters such as currentPositionTitle, currentSeniority, skills, location, and changedJobsWithinDays, runs a natural-language prompt search, and finds lookalike profiles. It also finds a contact's work email or phone, fetches cached or live person and company profiles, and resolves identities asynchronously, with long-running jobs acknowledged by a webhookId that you poll until the result is ready.
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>