Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the EasyBits 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%2Feasybits.cloud%2Feasybits" | 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%2Feasybits.cloud%2Feasybits" | 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 EasyBits API.
Run a command or inline code inside a Firecracker microVM sandbox
Deploy an app to a managed machine and roll back to an earlier release
Query, batch-execute, or import into a managed SQL database
Store files behind a CDN and search them, with soft-delete and restore
Search, fetch, extract, and crawl web pages for an agent
GET STARTED
Register a custom domain and issue a wildcard certificate
Run persistent assistants and send them turns across channels
Patterns agents use EasyBits API for, with concrete tasks.
★ Execution backend for a coding agent
A coding agent needs somewhere safe to run what it writes. Through Jentic the agent creates a Firecracker microVM sandbox, runs a command synchronously or executes inline code, starts background processes, and reads their logs, so generated code runs in isolation rather than on the host. A sandbox can be snapshotted as a reusable template.
Create a sandbox, run a Python snippet in it, and return the captured output and exit status
One-call app deployment
An agent ships an app without a manual pipeline. EasyBits launches an app on a managed machine in a single call, publishes and lists releases, restarts in place, and rolls back to an earlier release if a deploy misbehaves. Secrets and logs for the machine are reachable through the same surface.
Launch an app on a managed machine, publish a release, and roll back if the new release fails to start
Agent-owned data and web layer
An agent needs to store state and gather information. EasyBits gives it a managed SQL database it can query, batch-execute, or import into, a CDN-backed file store with AI file search and soft-delete, and web operations to search, fetch, extract, and crawl pages. The agent keeps its own data and its own view of the web in one backend.
Create a database, import a dataset, then search the web and store the extracted results as files
101 endpoints — the easybits api runs code inside firecracker microvm sandboxes, deploys and hosts full apps on managed machines, and gives an agent a working backend: sql databases, a cdn-backed file store, documents published as sites, and persistent assistants reachable across channels.
METHOD
PATH
DESCRIPTION
/api/v2/sandboxes/{id}/exec
Run a command synchronously in a sandbox
/api/v2/sandboxes/{id}/run-code
Run inline code in a sandbox
/api/v2/machines/launch
Launch an app on a managed machine in one call
/api/v2/machines/{id}/releases
Publish a release for a machine
/api/v2/databases/{dbId}/query
Query, batch-execute, or import into a database
/api/v2/web/search
Search the web
/api/v2/web/extract
Extract structured data from a page
/api/v2/files
Register a file and get an upload URL
/api/v2/sandboxes/{id}/exec
Run a command synchronously in a sandbox
/api/v2/sandboxes/{id}/run-code
Run inline code in a sandbox
/api/v2/machines/launch
Launch an app on a managed machine in one call
/api/v2/machines/{id}/releases
Publish a release for a machine
/api/v2/databases/{dbId}/query
Query, batch-execute, or import into a database
/api/v2/web/search
Search the web
/api/v2/web/extract
Extract structured data from a page
/api/v2/files
Register a file and get an upload URL
What agents get from Jentic-routed access to this vendor.
Setup
Wiring EasyBits by hand means handling its bearer API key or an OAuth2 flow, learning scopes from READ to ADMIN, and polling async jobs like web extraction yourself. Through Jentic you install once, import EasyBits from the API Directory, store the credential once, and your agent calls it.
Permission scoping
EasyBits puts the machine and sandbox id in the URL path (/sandboxes/{id}/... and /machines/{id}/...), so a rule can pin your agent to one machine or sandbox and the operations you pick, such as running code and reading logs. Destructive ones like destroying a sandbox or releasing a machine are not included unless you add them.
Credential isolation
Your EasyBits 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 'run code in a sandbox' or 'deploy my app', and Jentic returns the matching EasyBits 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 EasyBits API through Jentic.
What authentication does the EasyBits API use?
The EasyBits API accepts a bearer API key sent as `Authorization: Bearer eb_sk_live_...`, and also supports an OAuth2 authorization-code flow with PKCE for interactive clients, per its OpenAPI spec. Keys carry scopes from READ through WRITE, DELETE, and ADMIN. Through Jentic the credential 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 EasyBits MCP server?
You don't need a separate MCP server to give your agent the EasyBits API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls its sandbox, database, and deployment operations on demand without loading another server's tool definitions into its context.
Can I run code in a sandbox with the EasyBits API?
Yes. You create a sandbox, then run a command synchronously or execute inline code inside it, start and manage background processes, and read their logs. Sandboxes are Firecracker microVMs, and you can snapshot one as a reusable template.
What are the rate limits for the EasyBits API?
The OpenAPI spec does not state specific rate limits. Check the EasyBits documentation at https://www.easybits.cloud/docs for current limits before running high-volume sandbox or crawl workloads.
Can I limit what my agent is allowed to do with the EasyBits API?
Yes. Write a rule that allows just the operations your agent needs, such as running code and reading logs on a single machine, and leave out destructive ones like destroying a sandbox or releasing a machine. Every call it makes is logged.
How do I deploy an app with the EasyBits API through Jentic?
Search Jentic for 'deploy my app' and it returns the launch operation with its input schema; your agent publishes a release and can roll back if it fails. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Run code in Firecracker sandboxes, deploy and host apps, query SQL databases, store files on a CDN, and search or crawl the web, all from one backend an agent can call.
Use for: Run this Python snippet in a sandbox and return the output, Deploy my app and roll back if the release fails, Query a SQL database I host on EasyBits, Search the web and extract structured data from a page
Not supported: Does not handle payments, identity providers, or email delivery. Use for sandboxed code execution, app hosting, databases, files, and web access only.
The EasyBits API runs code inside Firecracker microVM sandboxes, deploys and hosts full apps on managed machines, and gives an agent a working backend: SQL databases, a CDN-backed file store, documents published as sites, and persistent assistants reachable across channels. It also searches, fetches, extracts, and crawls the web, registers custom domains with wildcard certificates, and delivers events through webhooks. Every path lives under one versioned base and returns a consistent error envelope.
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>