Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the EmailFig 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%2Femailfig.com%2Femailfig" | 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%2Femailfig.com%2Femailfig" | 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 EmailFig API.
Create or update a contact and read it back
Add contacts to a list and remove them from it
Tag and untag contacts
Define and update custom fields for contacts
Read forms and campaign performance
GET STARTED
Register, test, and manage webhook endpoints
Patterns agents use EmailFig API for, with concrete tasks.
★ Agent-synced contacts
An AI agent keeps a mailing audience in step with your app. Through Jentic the agent creates or updates a contact, subscribes it to the right list, and sets custom fields, so a new signup in your product becomes a managed contact without a manual export. Contacts come back in cursor-paginated pages the agent can walk.
Create or update a contact, add it to a named list, and set a custom field on it
List and tag hygiene
A workflow keeps segments clean. The API tags and untags contacts, adds and removes them from lists, and unsubscribes an address, so an agent can re-segment an audience or honor an opt-out across the account. Tags are returned in pages so large audiences can be processed in batches.
Tag every contact on a list, then unsubscribe any address that opted out
Campaign performance read
A reporting agent summarizes how email went. The API lists campaigns and reads a single campaign, and reads the forms that collect signups, so an agent can pull performance for a digest without opening the dashboard. Forms tie new contacts back to where they came from.
List recent campaigns, read one campaign's performance, and summarize it for a weekly report
30 endpoints — the emailfig api keeps contacts, lists, tags, and custom fields in sync between your app and your email program, and reads how your campaigns performed.
METHOD
PATH
DESCRIPTION
/contacts
Create or update a contact
/contacts
List contacts
/lists/{list_id}/contacts
Add a contact to a list
/contacts/{contact_id}/tags
Tag a contact
/campaigns
List campaigns
/custom_fields
Create a custom field
/webhooks
Create a webhook endpoint
/forms
List forms
/contacts
Create or update a contact
/contacts
List contacts
/lists/{list_id}/contacts
Add a contact to a list
/contacts/{contact_id}/tags
Tag a contact
/campaigns
List campaigns
/custom_fields
Create a custom field
/webhooks
Create a webhook endpoint
/forms
List forms
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the EmailFig API by hand means handling its bearer key, following cursor pagination through contacts and campaigns, and keeping custom fields in step with your own schema. Through Jentic you install once, import EmailFig from the API Directory, store the key once, and your agent calls it.
Permission scoping
EmailFig puts the list and contact id in the URL path (/lists/{list_id}/contacts and /contacts/{id}), so a rule can pin your agent to the operations it needs, such as adding contacts to one list and reading campaigns. Erasing a contact is not included unless you add it.
Credential isolation
Your EmailFig 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 'add a contact to a list' or 'read a campaign's performance', and Jentic returns the matching EmailFig operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using EmailFig API through Jentic.
What authentication does the EmailFig API use?
The EmailFig API authenticates with a bearer API key per its OpenAPI spec: you create a key under Settings and send it as `Authorization: Bearer emf_live_...`, and an account call confirms the key works. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's context.
Is there an EmailFig MCP server?
You don't need an MCP server to give your agent the EmailFig API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the contact, list, and campaign operations on demand without loading another server's tool definitions into its context.
Can I sync contacts with the EmailFig API?
Yes. A single operation creates or updates a contact, and others add it to or remove it from a list, tag or untag it, set custom fields, and read it back. Contacts are returned in cursor-paginated pages, and you keep the same filters as you page through them.
What are the rate limits for the EmailFig API?
The OpenAPI spec does not state specific rate limits, though contacts, tags, and campaigns are paged at up to 100 per request. Check the provider's documentation at https://emailfig.com for the current limits on your plan.
Can I limit what my agent is allowed to do with the EmailFig API?
Yes. EmailFig puts the list and contact id in the URL path, so write a rule that lets your agent add contacts to one list and read campaigns while erasing a contact stays out of its reach. Every call it makes is logged.
How do I add a contact to a list with the EmailFig API through Jentic?
Search Jentic for 'add a contact to a list' and it returns the operation with its input schema; your agent creates the contact and subscribes it to the list you name. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Sync contacts, lists, tags, and custom fields with your email program, read campaign and form data, and manage webhook endpoints, all through one bearer-authenticated API.
Use for: Add a new contact to my EmailFig account, Subscribe a contact to a specific list, Tag everyone who filled out a form, Check how a campaign performed
Not supported: Does not send transactional email, manage SMS, or run paid ads. Use for managing contacts, lists, tags, custom fields, and reading campaigns only.
The EmailFig API keeps contacts, lists, tags, and custom fields in sync between your app and your email program, and reads how your campaigns performed. It creates or updates contacts, adds and removes them from lists, tags and untags them, manages custom fields, reads forms and campaigns, and delivers events through webhook endpoints you can test. Contacts, tags, and campaigns come back in cursor-paginated pages you can carry filters across.
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>