Install Jentic One Beta

Connect the Klipy API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Klipy 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%2Fklipy.ai%2Fklipy" | sh

Step 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%2Fklipy.ai%2Fklipy" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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.

Capabilities

What an agent can do with Klipy API.

Upsert a person by email with firstName, lastName, title, phone, linkedin, and altEmails in one call

Query people by email, phone, companyId, or owner with cursor pagination up to 100 per page

Create a company from its domain and name, then update or delete it by companyId

Log an interaction such as EMAIL, MEETING, MEMO, or VOICE_NOTE with a direction and title against a contact

GET STARTED

Start building with Klipy API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Klipy API for, with concrete tasks.

★ AI agent CRM upkeep through Jentic

An assistant that reads your inbox keeps Klipy current without you copying details by hand. Through Jentic the agent searches for 'upsert a contact', loads the Klipy upsert operation with its input schema, and writes the person by email with the name, title, and phone it found. Your own Jentic One instance injects the klipy_api_ key at call time, so the agent never holds it.

Call PUT /people with email 'ana@globex.com', firstName 'Ana', lastName 'Ruiz', and title 'Head of Ops', then log a MEETING interaction with POST /interactions using mainContactEmail 'ana@globex.com'

Interaction logging after calls and meetings

After a call or meeting, the notes go into Klipy as an interaction with a type such as MEETING or VOICE_NOTE, a direction such as OUTBOUND, a title, an optional summary, and the interactionDate as a Unix timestamp in milliseconds. Each interaction names its contact by mainContact or mainContactEmail.

Call POST /interactions with type 'MEETING', direction 'OUTBOUND', title 'Renewal check-in', a summary, and mainContactEmail for the attendee

Account history before a call

Before a call, an agent pulls the people at a company with a companyId filter and then queries interactions for that company, giving a quick history of who was contacted and what was discussed.

Call POST /people/query with filter companyId 'cmp_123', then POST /interactions/query with filter companyId 'cmp_123' and summarise the latest interactions

Key Endpoints

14 endpoints — the klipy api reads and writes the core records in a klipy crm: people, companies, and the interactions logged against them.

METHOD

PATH

DESCRIPTION

PUT

/people

Upsert a person

POST

/people/query

Query people

PATCH

/people/{personId}

Update a person

POST

/companies

Create a company

GET

/companies/{companyId}

Get a company by ID

POST

/interactions

Create an interaction

POST

/interactions/query

Query interactions

PUT

/people

Upsert a person

POST

/people/query

Query people

PATCH

/people/{personId}

Update a person

POST

/companies

Create a company

GET

/companies/{companyId}

Get a company by ID

POST

/interactions

Create an interaction

POST

/interactions/query

Query interactions

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring Klipy by hand means choosing between its X-Klipy-Api-Key header and bearer auth, issuing a key with the right scopes, and unwrapping its object, data, and meta envelopes. Through Jentic you install once, import Klipy from the API Directory, store the key once, and your agent calls it.

Permission scoping

Klipy puts the person, company, and interaction ids in the URL path (/people/{personId}, /companies/{companyId}), so a rule can pin your agent to one record and the operations you pick. You choose the operations it may call, so destructive ones like deleting a person or a company are not included unless you add them.

Credential isolation

Your Klipy 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 'upsert a contact' or 'log a meeting', and Jentic returns the matching Klipy operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Klipy API through Jentic.

What authentication does the Klipy API use?

Per its OpenAPI spec, the Klipy API accepts an API key in the format klipy_api_<id>, sent either in the X-Klipy-Api-Key header or as a bearer token in the Authorization header. Each endpoint also requires a scope on the key, such as people:read, companies:write, or interactions:write. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time.

What are the rate limits for the Klipy API?

Per the Klipy OpenAPI spec, rate limiting is enforced per API key at 200 requests per minute and per organization at 1000 requests per minute. Successful responses include X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset, and throttled responses include Retry-After.

What is the difference between creating and upserting a person in Klipy?

POST /people creates a person from a type of email, an identifier, and a firstName. PUT /people upserts by email and accepts more fields, including phone, personalPhone, linkedin, twitter, altEmails, and remarks, so it is the safer choice when the person may already exist.

Is there a Klipy MCP server?

You don't need an MCP server to give your agent the Klipy API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the people, company, and interaction operations on demand without loading another server's tool definitions into its context.

Can I limit what my agent is allowed to do with the Klipy API?

Yes. For example, write a rule that allows only POST /people/query, POST /interactions/query, and POST /interactions, so the agent can look people up and log interactions but cannot delete people or companies. Every call it makes through your instance is logged, and you can also issue the key with narrow Klipy scopes.

How do I log a meeting in Klipy through Jentic?

Search Jentic for 'log a meeting in the CRM', load the Klipy create interaction operation, and call POST /interactions with type MEETING, a direction, a title, and mainContactEmail. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Klipy API

AI ReadinessAI-Aware (B-)63/100

See full scorecard

Official vendor OpenAPI document · agent-readyCRMContact ManagementapiKey, bearer14 EndpointsREST

For Agents

Create, upsert, query, and update people and companies in Klipy CRM, and log or query interactions such as emails, meetings, and memos against them.

Use for: Add a new contact to Klipy from an email signature, Find the person in Klipy with this email address, Log the meeting I just had with a customer, List all interactions with a company

Not supported: Does not handle deal pipelines, email sending, or support tickets. Use for Klipy people, company, and interaction records only.

The Klipy API reads and writes the core records in a Klipy CRM: people, companies, and the interactions logged against them. You can create a person by email, upsert one with phone, social handles, and alternate emails, query people by email, phone, companyId, or owner, and create or remove companies by domain. Interactions such as emails, meetings, memos, voice notes, and bookings are logged with a direction and title and can be queried by contact or company, with each endpoint gated by a scope such as people:read or companies:remove.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: BSignals: 4

95%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

60%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: B+Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

75%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: D+Signals: 4

41%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

93%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

58%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: CSignals: 1

55%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: BSignals: 1

66%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Klipy API to your agent

Capabilities

Start building with Klipy API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Klipy API

Jentic AI Readiness Score

Klipy API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness