Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Chainstack Platform 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%2Fchainstack.com%2Fchainstack" | 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%2Fchainstack.com%2Fchainstack" | 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 Chainstack Platform API.
Create and manage blockchain nodes within a project
Create networks and attach nodes to them
Organize resources into projects and list project members
Retrieve application tokens from the marketplace
Request Goerli and Sepolia testnet funds from the faucet
GET STARTED
Read and update organization details
Patterns agents use Chainstack Platform API for, with concrete tasks.
★ AI Agent Node Provisioning
An AI agent connected through Jentic can stand up blockchain infrastructure on request: it creates a project, adds a network, and deploys a node on that network. Chainstack handles the resource hierarchy so the agent provisions the stack instead of clicking through the platform UI.
Create a project, create a network in it, and deploy a node on that network
Project and Access Organization
Keep infrastructure tidy by grouping networks and nodes under projects and reviewing who has access. Chainstack lists project members and lets you create, update, and delete projects so resources map to teams.
Create a project and list its members to confirm access
Testnet Faucet Funding
Fund development wallets without leaving the workflow by requesting testnet tokens from the Goerli and Sepolia faucets. Chainstack exposes faucet operations that dispense funds for integration testing.
Request Sepolia testnet funds from the faucet for a development address
Marketplace Application Tokens
Access deployed marketplace services by retrieving their application tokens. Chainstack returns an application token for a marketplace slug so an integration can call the service it fronts.
Retrieve the application token for a given marketplace application slug
21 endpoints — the chainstack api provisions and manages blockchain infrastructure: it creates nodes, groups them into networks, and organizes those networks under projects.
METHOD
PATH
DESCRIPTION
/v1/nodes/
List all nodes
/v1/nodes/
Create a node
/v1/networks/
List all networks
/v1/networks/
Create a network
/v1/projects/
List all projects
/v1/projects/
Create a project
/v1/organization/
Get organization name and ID
/v1/nodes/
List all nodes
/v1/nodes/
Create a node
/v1/networks/
List all networks
/v1/networks/
Create a network
/v1/projects/
List all projects
/v1/projects/
Create a project
/v1/organization/
Get organization name and ID
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Chainstack by hand means sending your API key as a bearer token in the Authorization header and tracking the project, network, and node paths yourself. Through Jentic you install once, import Chainstack from the API Directory, store the key once, and your agent calls it.
Permission scoping
You choose which Chainstack operations the agent may call, such as listing and creating nodes, so deleting nodes, networks, or projects is not included unless you add it.
Credential isolation
Your Chainstack API 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 'create a blockchain node' or 'list networks', and Jentic returns the matching Chainstack 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 Chainstack Platform API through Jentic.
What authentication does the Chainstack API use?
The Chainstack API authenticates with an API key provided as a bearer token in the Authorization header, per its OpenAPI spec. You create and manage keys in the Chainstack platform, and through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never appears in the agent's prompt or logs.
Can I create and manage blockchain nodes with the Chainstack API?
Yes. You can create nodes, retrieve and update them, and delete them, and group them into networks under a project. The API also lists project members and returns marketplace application tokens for deployed services.
Can I request testnet funds with the Chainstack API?
Yes. The API exposes faucet operations for the Goerli and Sepolia testnets that dispense funds to a development address. This lets an integration top up test wallets without leaving the provisioning workflow.
Is there a Chainstack MCP server?
You do not need an MCP server to give your agent the Chainstack API. Jentic connects it directly from the API Directory: import Chainstack, store your key once, and your agent provisions nodes and networks 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 Chainstack API?
Yes. Write a rule that allows only the operations the agent needs, for example listing and creating nodes, and leave out operations like deleting nodes, networks, or projects. The agent provisions infrastructure within those bounds, and every call it makes is logged.
How do I deploy a node through Jentic with the Chainstack API?
Search Jentic for 'create a blockchain node', which returns the Chainstack operation with its input schema, then supply the project, network, and node configuration and the agent runs it. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Create and manage blockchain nodes, networks, and projects, retrieve marketplace application tokens, and request testnet faucet funds through the Chainstack platform API.
Use for: Create a new blockchain node in my project, List all nodes in my organization, Set up a network and attach a node, Create a new project for my team
Not supported: Does not handle on-chain transactions, smart-contract deployment, or wallet key custody. Use for Chainstack node, network, and project management only.
The Chainstack API provisions and manages blockchain infrastructure: it creates nodes, groups them into networks, and organizes those networks under projects. It reads and updates organization details, lists project members, and retrieves marketplace application tokens for deployed services. Testnet faucet endpoints dispense Goerli and Sepolia funds for development.
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>