IBM APIs for AI Agents
Developer ToolsCi CdTask ManagementMixed ProvenanceBearer tokenBasic authapiKey, basic, bearerAgent Ready
For Agents
APIs8 in catalogue
Endpoints119 indexed
AuthBearer token / Basic auth / apiKey, basic, bearer
ProvenanceMixed provenance
An agent can publish and govern APIs through API Connect, run and monitor DataStage and webMethods integrations, drive Business Automation Workflow processes and cases, call Operational Decision Manager rules for deterministic decisions, provision and message on IBM MQ, and turn text into audio with Watson. It can chain these, for example provisioning a queue manager then sending messages to it, or backing a published API Connect product with a webMethods flow.
IBM's APIs on Jentic are the runtime and lifecycle surfaces of IBM Cloud Pak for Integration and IBM Cloud, spanning API management, workflow, decisioning, ETL, iPaaS, enterprise messaging, and speech in one portfolio. They suit teams already standardised on IBM who want to operate these products from CI or agents rather than the individual web consoles.
Use for: Operating IBM Cloud Pak for Integration and IBM Cloud runtime and lifecycle surfaces over REST: API Connect publishing, BAW processes and cases, ODM rule execution, DataStage and webMethods runs, IBM MQ provisioning and messaging, and Watson speech synthesis.
Not supported: low-code authoring, developer-portal content, BI reporting, speech-to-text, real-time streaming, rule debugging
Credentials: No single credential covers the portfolio: cloud services such as DataStage, MQ Cloud, and Watson use IBM Cloud IAM bearer tokens, on-prem BAW and ODM use HTTP basic auth, API Connect and webMethods use their own bearer tokens, and the MQ REST API accepts an LtpaToken session, basic, or bearer, so each API is credentialed separately.
Across 8 IBM APIs: 7 vendor-official, 1 Jentic-generated, all indexed by Jentic and kept validated and agent-ready.
IBM's integration and automation APIs on Jentic cover the operational surface of IBM Cloud Pak for Integration and IBM Cloud services: managing the API Connect lifecycle, running Business Automation Workflow processes and cases, executing Operational Decision Manager rules, running DataStage ETL and webMethods integrations, provisioning and messaging on IBM MQ, and synthesising speech with Watson Text to Speech. Together they let platform teams and agents drive publishing, integration, decisioning, data pipelines, messaging, and voice output over REST instead of the vendor consoles.
IBM API Catalog
8 APIs across 6 product groups.
Developer Tools3
IBM API Connect Management APIManage the full IBM API Connect lifecycle - orgs, drafts, catalogs, products, applications, and subscriptions - from CI or an agent.~25 endpointsIBM webMethods Integration APIRun and monitor IBM webMethods workflows and flow services, manage connector accounts, and inspect execution history through a single REST surface.~15 endpointsIBM Operational Decision Manager APIExecute IBM ODM business rules and decision services - call rulesets and decision services with input payloads and get back rule-engine outputs.~12 endpoints
Cloud Infrastructure1
Which IBM API should I use?
| I want to... | Use | Why |
|---|---|---|
| Route work between enterprise messaging APIs | IBM MQ Cloud API | MQ Cloud provisions and tears down queue managers as a managed service; use it for lifecycle, not runtime messaging. |
| Route work between enterprise messaging APIs | IBM MQ REST API | The MQ REST API administers an existing queue manager and puts or gets messages over HTTPS; use it once the queue manager is running. |
| Coordinate a business process versus a single decision | IBM Business Automation Workflow API | BAW drives long-running, multi-step processes, human tasks, and case folders. |
| Coordinate a business process versus a single decision | IBM Operational Decision Manager API | ODM executes a single deterministic rule or decision service and returns the rule-engine output. |
| Move or transform data between systems | IBM DataStage API | DataStage runs bulk ETL flows and jobs on IBM Cloud with run history and logs. |
| Move or transform data between systems | IBM webMethods Integration API | webMethods runs event-driven workflows and reusable flow services across SaaS and on-prem connectors. |
Install Jentic One Beta
Connect the IBM APIs to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the IBM APIs, 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.
1
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%2Fibm.com" | sh2
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%2Fibm.com" | 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.
Once connected, ask your agent something like: “automate IBM integration, messaging, and workflow tasks”.
What AI Agents Can Do with IBM
Each workflow spans multiple IBM APIs. Jentic routes each operation to the right API automatically.
Provision a queue manager then send messages to it
Provision an IBM MQ queue manager on IBM Cloud, wait for it to reach a running state, then administer its queues and put messages onto them once it is live. MQ Cloud handles the lifecycle and MQ REST handles the runtime messaging, which lets an agent stand up messaging infrastructure and use it in one flow.
Example prompt:
Create a queue manager named QM_TEST via mq-cloud-api, poll its status until running, then POST an order message to its ORDERS.IN queue via ibm-mq-rest-api.
APIs used
IBM MQ Cloud API + IBM MQ REST API
Publish an integration flow as a managed API
Build the integration logic as a webMethods workflow or flow service, then publish and govern it as a managed API through API Connect so partners can consume it. webMethods provides the runnable integration and API Connect provides the catalog membership, subscriptions, and gateway binding.
Example prompt:
Confirm the order-fulfilment workflow runs via webmethods-integration, then publish the backing product to a staging catalog and subscribe a partner application through main.
APIs used
IBM webMethods Integration API + IBM API Connect Management API
Run a process that calls a deterministic decision
Drive a long-running Business Automation Workflow process and, at a decision point, call an Operational Decision Manager ruleset for a deterministic and auditable answer such as loan eligibility. BAW orchestrates the multi-step flow and ODM returns the rule-engine output the process acts on.
Example prompt:
Start a LoanApproval process via business-automation-workflow-api, execute the eligibility ruleset via odm-api with the applicant payload, and resume the process with the decision.
APIs used
IBM Business Automation Workflow API + IBM Operational Decision Manager API
Run an ETL job then voice the result
Run a DataStage ETL job on IBM Cloud, inspect its run status and logs, and on completion synthesise a spoken summary of the outcome with Watson Text to Speech. DataStage handles the data pipeline and Watson turns the summary text into audio for a briefing.
Example prompt:
Run the daily-customer-load job via datastage-api, poll the run to completion, then POST a summary line to /v1/synthesize via text-to-speech and save the MP3.
APIs used
IBM DataStage API + IBM Watson Text to Speech
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring these IBM APIs by hand means handling several auth schemes, resolving on-prem hosts and IBM Cloud regional endpoints, and mapping each product's routes yourself. Through Jentic you install once, then you or your agent add any of the IBM APIs from the Jentic directory to your workspace and store each credential once.
Permission scoping
Most of these IBM APIs put their key identifiers in the URL path, such as an org or catalog in API Connect, a service instance and queue manager in MQ, or a rule app in ODM, so your own rules can pin the agent to specific resources and a chosen set of operations. State-changing calls like provisioning a queue manager or reassigning a task are not available to the agent unless you add them.
Credential isolation
Each IBM credential, whether an IAM token, a basic-auth login, or an API Connect or webMethods token, is stored encrypted by your own Jentic One instance and injected at execution time. Credentials never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search the Jentic directory by intent, such as create a queue manager, publish a product to a catalog, execute a ruleset, or synthesise speech, and Jentic returns the matching IBM operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
FAQs
Specific to using IBM APIs through Jentic.
Which IBM APIs are available through Jentic?
The portfolio spans eight APIs: API Connect for API lifecycle management, Business Automation Workflow for processes and cases, Operational Decision Manager for business rules, DataStage for ETL, webMethods Integration for iPaaS, the IBM MQ REST API and IBM MQ Cloud API for enterprise messaging, and Watson Text to Speech for voice output. They cover the runtime and lifecycle surfaces of IBM Cloud Pak for Integration and several IBM Cloud services.
Do these IBM APIs share one credential?
No. Cloud services such as DataStage, MQ Cloud, and Watson authenticate with IBM Cloud IAM bearer tokens, while on-prem BAW and ODM use HTTP basic auth, and API Connect, webMethods, and the MQ REST API use their own token or session schemes. Each API is added to your Jentic One instance with its own credential, stored separately.
Which IBM API should I use for enterprise messaging?
Use the IBM MQ Cloud API to provision, configure, and tear down queue managers as a managed service, and use the IBM MQ REST API to administer an existing queue manager and put or get messages over HTTPS. They are complementary: MQ Cloud is the lifecycle surface and the MQ REST API is the runtime surface.
When should I use BAW versus ODM?
Use Business Automation Workflow when the task is a long-running, multi-step process with human tasks or case folders. Use Operational Decision Manager when you need a single deterministic, auditable decision such as an eligibility check or pricing tier. A BAW process commonly calls an ODM ruleset at a decision point.
Can these IBM APIs be combined in one agent workflow?
Yes. An agent can back an API Connect product with a webMethods flow, call an ODM ruleset from inside a BAW process, provision a queue manager on MQ Cloud and then message it through the MQ REST API, or run a DataStage job and voice the result with Watson. Each API is discovered and executed the same way through Jentic.
Are these the on-prem or the cloud IBM products?
It is a mix. API Connect, BAW, ODM, and the IBM MQ REST API address deployments that can be on-prem or on IBM Cloud and take a host and port, while DataStage, MQ Cloud, and Watson Text to Speech are IBM Cloud managed services reached at IBM Cloud regional hosts. Point each API at your own deployment when you add it.
If you need a different Developer Tools vendor
All 4 are in the Jentic catalogue with the same one-credential, intent-search pattern.
BOOK A DEMO
Start Connecting APIs to Your AI Agents
Browse thousands of APIs and connect them all to your agent with Jentic One. One layer, one credential — every API your agent needs.