Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Cavyro 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%2Fcavyro.com%2Fcavyro" | 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%2Fcavyro.com%2Fcavyro" | 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 Cavyro API.
Create and update contacts and companies with custom fields
Move deals through configurable pipeline stages
Build pipelines and configure their stages
Manage projects, tasks, and task lists
Run saved reports and dashboards over workspace data
GET STARTED
Search across contacts, companies, deals, and projects
Subscribe to webhook event types for record changes
Patterns agents use Cavyro API for, with concrete tasks.
★ AI Agent Deal Updates
An AI agent connected through Jentic can keep a sales pipeline current: it creates a contact, opens a deal for them in a pipeline, and moves the deal to the next stage as it progresses. Cavyro handles stage order and feed events so the agent records the change rather than clicking through the board.
Create a contact, add a deal for them to a pipeline, and move the deal to the next stage
Pipeline Configuration
Set up how opportunities flow by creating pipelines and defining their stages. Cavyro lets you add, update, and reorder stages so the CRM reflects a team's real sales process.
Create a new pipeline and add an ordered set of stages for it
Project and Task Management
Coordinate delivery work alongside sales by creating projects, task lists, and tasks with owners and due dates. Cavyro supports bulk task actions and subtasks so the agent can keep execution in step with the deal.
Create a project, add a task list, and add a task with an owner and due date
Workspace Reporting
Measure pipeline health by running saved reports and reading dashboards over workspace data. Cavyro exposes deal reports by type and dashboard widgets for recurring views.
Run a saved report on deals closed this quarter and return the summary figures
374 endpoints — the cavyro api runs a workspace crm that tracks contacts, companies, and deals and moves them through configurable pipeline stages.
METHOD
PATH
DESCRIPTION
/api/v1/contacts
Create a contact
/api/v1/deals
List deals
/api/v1/companies
Create a company
/api/v1/pipelines
Create a pipeline
/api/v1/projects
Create a project
/api/v1/campaigns
Create a campaign
/api/v1/search
Search the workspace
/api/v1/contacts
Create a contact
/api/v1/deals
List deals
/api/v1/companies
Create a company
/api/v1/pipelines
Create a pipeline
/api/v1/projects
Create a project
/api/v1/campaigns
Create a campaign
/api/v1/search
Search the workspace
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Cavyro by hand means handling its bearer-token auth, passing an X-Workspace-Id header on workspace-scoped calls, and tracking paths for contacts, deals, pipelines, and tasks yourself. Through Jentic you install once, import Cavyro from the API Directory, store the token once, and your agent calls it.
Permission scoping
You choose which Cavyro operations the agent may call, such as creating contacts and moving deals, so bulk-delete and recycle-bin purge operations are not included unless you add them.
Credential isolation
Your Cavyro bearer token 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 'create a contact' or 'move a deal stage', and Jentic returns the matching Cavyro operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Cavyro API through Jentic.
What authentication does the Cavyro API use?
The Cavyro API authenticates with a bearer token sent in the Authorization header, and workspace-scoped operations additionally require an `X-Workspace-Id` header naming the workspace, per its OpenAPI spec. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it stays out of the agent's prompt and logs.
Can I move deals through pipeline stages with the Cavyro API?
Yes. You can create pipelines, define their stages, add deals to a pipeline, and move a deal from one stage to the next. Bulk operations let you reassign, re-stage, or update the status of many deals at once.
Can I manage projects and tasks with the Cavyro API?
Yes. The API creates projects, folders, task lists, tasks, and subtasks, with owners, due dates, and bulk actions. This lets the agent keep delivery work in step with the sales pipeline in the same workspace.
Is there a Cavyro MCP server?
You do not need an MCP server to give your agent the Cavyro API. Jentic connects it directly from the API Directory: import Cavyro, store your token once, and your agent updates contacts and deals through the operations the API already exposes. Operations are discovered on demand, so no extra tool definitions are loaded into the agent's context.
Can I limit what my agent is allowed to do with the Cavyro API?
Yes. Write a rule that allows only the operations the agent needs, for example creating contacts and moving deals, and leave out bulk-delete and recycle-bin purge operations. The agent keeps the pipeline current within those bounds, and every call it makes is logged.
How do I update a deal through Jentic with the Cavyro API?
Search Jentic for 'move a deal stage', which returns the Cavyro operation with its input schema, then supply the deal and target stage and the agent runs it. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Create contacts and companies, move deals through pipeline stages, run projects and tasks, and search the workspace through the Cavyro CRM API.
Use for: Create a new contact in my workspace, Move a deal to the next pipeline stage, List the deals in my pipeline, Build a new sales pipeline with stages
Not supported: Does not handle payment processing, email campaign sending, or accounting ledgers. Use for CRM contacts, deals, pipelines, and project tasks only.
The Cavyro API runs a workspace CRM that tracks contacts, companies, and deals and moves them through configurable pipeline stages. It manages projects, tasks, docs, calendar events, and dashboards in the same workspace, with custom fields, bulk actions, and a recycle bin across records. Webhook subscriptions, saved reports, and workspace-wide search round out the surface.
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>