Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the lemlist 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%2Flemlist.com%2Flemlist" | 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%2Flemlist.com%2Flemlist" | 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 lemlist API.
Create, update, pause, and start campaigns
Build and edit sequence steps and their branches
Add, update, and remove leads on a campaign
Mark leads interested or not interested and pause or review them
Read campaign reports and start or fetch lead exports
GET STARTED
Manage schedules, message templates, snippets, and team members
Patterns agents use lemlist API for, with concrete tasks.
★ Lead sync into outreach
An AI agent adds and updates leads on a lemlist campaign as they arrive from a CRM or form, setting personalization variables so each contact enters the right sequence without manual CSV imports.
Add a lead with the given email and company to campaign CAMP123 and set the firstName variable
Campaign control
An agent creates a campaign, starts it, and pauses it on demand, letting an operator run sending workflows conversationally instead of clicking through the lemlist dashboard.
Create a campaign named 'Q4 Outbound', then start it
Reply triage
An agent marks leads as interested or not interested based on reply signals and reads campaign reports, keeping pipeline status current across active campaigns.
Mark the lead with email jane@acme.com as interested on campaign CAMP123 and return the campaign report
164 endpoints — the lemlist api runs cold-outreach campaigns: it creates and manages campaigns and their sequences, adds and updates leads, marks leads as interested or not interested, and reads campaign reports and exports.
METHOD
PATH
DESCRIPTION
/campaigns
List campaigns on the account
/campaigns
Create a campaign
/campaigns/{campaignId}/start
Start a campaign so sending begins
/campaigns/{campaignId}/pause
Pause a running campaign
/campaigns/{campaignId}/leads/
Add a lead to a campaign
/campaigns/reports
Read campaign reports
/campaigns
List campaigns on the account
/campaigns
Create a campaign
/campaigns/{campaignId}/start
Start a campaign so sending begins
/campaigns/{campaignId}/pause
Pause a running campaign
/campaigns/{campaignId}/leads/
Add a lead to a campaign
/campaigns/reports
Read campaign reports
What agents get from Jentic-routed access to this vendor.
Setup
Wiring lemlist by hand means holding an API key, sending it as HTTP Basic on every request, and paging through campaigns, leads, and sequences across 164 operations yourself. Through Jentic you install once, import the lemlist API from the Directory, store the key once, and your agent calls it.
Permission scoping
Campaign, lead, and sequence ids are path parameters, so scope by operation and by resource: allow reading campaigns, leads, and reports while withholding start, pause, and delete operations, or restrict the agent to one campaign.
Credential isolation
Your lemlist API key credential 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 'add a lead to a campaign' or 'start an outreach campaign', and Jentic returns the matching lemlist API operation with its input schema so the agent calls the right endpoint without reading the reference docs by hand.
Alternatives and complements available in the Jentic catalogue.
Specific to using lemlist API through Jentic.
What can an AI agent do with the lemlist API?
An agent can create and control campaigns, build sequences, add and update leads, mark lead interest, read reports and exports, and manage schedules and templates across the sending workflow.
How do I connect the lemlist API to an AI agent with Jentic?
Import the lemlist API from the Jentic API Directory, store your API key once, and your agent calls the operations it needs. To get started, install the self-hosted Jentic One runtime from its GitHub repository and import the lemlist API from the Jentic API Directory.
What authentication does the lemlist API use?
The lemlist API uses HTTP Basic authentication with your API key. Jentic One stores that key encrypted in your own instance and applies it at execution time.
Can I limit what my agent is allowed to do with the lemlist API?
Yes. Campaign, lead, and sequence ids are path parameters, so you can scope the agent by operation and by resource: permit reading campaigns and reports while withholding start, pause, and lead-removal operations, or confine it to a single campaign.
Does the lemlist API send email directly for me?
It manages campaigns, sequences, leads, and schedules that drive lemlist's own sending; it does not act as a raw SMTP relay for arbitrary messages outside a campaign.
For Agents
Create and manage campaigns and sequences, add and update leads, mark lead interest, read reports and exports, and manage schedules and templates across 164 endpoints.
Use for: create a new outreach campaign, add a lead to a campaign, pause a running campaign, start a campaign so sending begins
Not supported: Manages campaigns, sequences, leads, schedules, and templates that drive lemlist sending. Does not act as a general SMTP relay or handle billing.
The lemlist API runs cold-outreach campaigns: it creates and manages campaigns and their sequences, adds and updates leads, marks leads as interested or not interested, and reads campaign reports and exports. It also manages schedules, message templates, snippets, and team membership. With 164 operations it covers the full sending workflow, authenticated with HTTP Basic using an API key, so an agent can build and drive multichannel outreach programmatically.
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>