Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the 9bot Agent and MCP Gateway 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%2F9bot.com.br%2F9bot" | 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%2F9bot.com.br%2F9bot" | 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 9bot Agent and MCP Gateway API.
Exchange JSON-RPC tool messages with the 9bot gateway
Discover the tools a tenant has enabled after authorization
Read OAuth protected-resource and authorization-server metadata
Fetch the gateway discovery document and server manifest
Check the gateway's health status
GET STARTED
Patterns agents use 9bot Agent and MCP Gateway API for, with concrete tasks.
★ Agent Tool Access Through One Gateway
An agent needs to call whatever tools a given tenant has enabled without integrating each one separately. The 9bot gateway exposes a single JSON-RPC exchange endpoint behind OAuth, and the available tools are discovered dynamically after authorization, so the agent reaches a tenant's full enabled tool set through one authenticated surface.
Authorize against the 9bot gateway and exchange a JSON-RPC message to list and call an enabled tool
OAuth Discovery and Bootstrapping
A client needs to bootstrap its OAuth flow against the 9bot gateway before it can call any tool. The gateway serves protected-resource and authorization-server metadata plus a discovery document, so an agent can read the metadata, complete authorization, and learn where to send tool messages without hard-coded configuration.
Read the OAuth protected-resource and authorization-server metadata from the gateway to bootstrap an authorization flow
Gateway Health Monitoring
An operations agent watches whether the 9bot gateway is reachable before routing agent traffic to it. The health endpoint returns the gateway's status without a credential, so a monitor can poll it on a schedule and alert when the gateway is unavailable.
Poll the gateway health endpoint and raise an alert if it reports an unhealthy status
6 endpoints — the 9bot gateway api is the public http surface of the 9bot agent tool gateway: it exchanges json-rpc tool messages, serves oauth and discovery metadata, and reports gateway health.
METHOD
PATH
DESCRIPTION
/mcp
Exchange a JSON-RPC tool message
/mcp/health
Get the gateway health status
/.well-known/mcp
Get gateway discovery metadata
/.well-known/oauth-protected-resource
Get OAuth protected-resource metadata
/.well-known/oauth-authorization-server
Get OAuth authorization-server metadata
/server.json
Get the gateway server manifest
/mcp
Exchange a JSON-RPC tool message
/mcp/health
Get the gateway health status
/.well-known/mcp
Get gateway discovery metadata
/.well-known/oauth-protected-resource
Get OAuth protected-resource metadata
/.well-known/oauth-authorization-server
Get OAuth authorization-server metadata
/server.json
Get the gateway server manifest
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the 9bot gateway by hand means completing its OAuth bearer flow and handling JSON-RPC tool envelopes yourself. Through Jentic you install once, import it from the API Directory, store the token once, and your agent calls the gateway.
Permission scoping
You choose which 9bot operations your agent may call, so it can exchange tool messages and read discovery metadata while nothing else is reachable unless you add it.
Credential isolation
Your 9bot 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 'reach the 9bot tool gateway', and Jentic returns the matching 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 9bot Agent and MCP Gateway API through Jentic.
What authentication does the 9bot gateway API use?
The 9bot gateway authenticates the tool-exchange endpoint with an OAuth bearer token in the Authorization header, per its OpenAPI spec. The discovery and health endpoints are open and need no credential. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it never reaches the agent's context.
Can my agent discover which tools a tenant has enabled?
Yes. After OAuth authorization, the gateway exposes its available tools dynamically through the JSON-RPC exchange endpoint, and the set depends on the application scopes, authorized groups, and tenant configuration. An agent reads the discovery metadata, authorizes, and then lists and calls the enabled tools through the one exchange endpoint.
What are the rate limits for the 9bot gateway API?
The OpenAPI spec does not define rate limits. Check the 9bot documentation at https://9bot.com.br for the current limits that apply to the gateway.
How do I reach the 9bot gateway through Jentic?
Import the 9bot gateway API from the Jentic directory and give your agent an intent such as 'reach the 9bot tool gateway'. Jentic returns the exchange operation with its input schema, your agent completes authorization and sends tool messages, and your stored token is injected at execution time. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the 9bot gateway API?
Yes. Write a rule that allows only the tool-exchange and discovery-read operations, so your agent can reach enabled tools and read metadata but nothing beyond that surface, and every call it makes is logged.
Is there a 9bot MCP server?
Yes: the 9bot gateway itself is a tool-calling gateway that exchanges JSON-RPC messages and discovers tools dynamically after OAuth authorization. Through Jentic you connect it from the API Directory without wiring that transport yourself: import it, store your credential once, and your agent calls it.
For Agents
Reach a tenant's enabled tools through one authenticated 9bot gateway endpoint, with OAuth and discovery metadata and a health check.
Use for: Exchange a tool message with the 9bot gateway, Discover which tools a 9bot tenant has enabled, Get the OAuth metadata for the 9bot gateway, Check whether the 9bot gateway is healthy
Not supported: Does not host the underlying tools, store business data, or manage user accounts. Use for routing agent tool calls and serving discovery metadata only.
The 9bot gateway API is the public HTTP surface of the 9bot agent tool gateway: it exchanges JSON-RPC tool messages, serves OAuth and discovery metadata, and reports gateway health. The exact tools and their input schemas are discovered dynamically after OAuth authorization and depend on the application scopes, authorized groups, and tenant configuration in play. It gives an agent one authenticated endpoint to reach whatever tools a tenant has enabled.
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>