Camel Components

AI Prompt

Since Camel 4.24

Only consumer is supported

The AI Prompt component exposes Camel routes as reusable prompt templates through an MCP server. Each prompt has a name, description, optional title and a set of string arguments. MCP clients discover the prompt with prompts/list and request the rendered messages with prompts/get.

Maven users will need the following dependency:

<dependency>
    <groupId>org.apache.camel</groupId>
    <artifactId>camel-ai-prompt</artifactId>
    <version>x.x.x</version>
</dependency>

URI format

ai-prompt:promptName[?options]

The promptName is the stable identifier shown to MCP clients.

Configuring Options

Camel components are configured on two separate levels:

component level
endpoint level

Configuring Component Options

At the component level, you set general and shared configurations that are, then, inherited by the endpoints. It is the highest configuration level.

For example, a component may have security settings, credentials for authentication, urls for network connection and so forth.

Some components only have a few options, and others may have many. Because components typically have pre-configured defaults that are commonly used, then you may often only need to configure a few options on a component; or none at all.

You can configure components using:

the Component DSL.
in a configuration file (application.properties, *.yaml files, etc).
directly in the Java code.

Configuring Endpoint Options

You usually spend more time setting up endpoints because they have many options. These options help you customize what you want the endpoint to do. The options are also categorized into whether the endpoint is used as a consumer (from), as a producer (to), or both.

Configuring endpoints is most often done directly in the endpoint URI as path and query parameters. You can also use the Endpoint DSL and DataFormat DSL as a type safe way of configuring endpoints and data formats in Java.

A good practice when configuring options is to use Property Placeholders.

Property placeholders provide a few benefits:

They help prevent using hardcoded urls, port numbers, sensitive information, and other settings.
They allow externalizing the configuration from the code.
They help the code to become more flexible and reusable.

The following two sections list all the options, firstly for the component followed by the endpoint.

Component Options

The AI Prompt component supports the following options which are listed below.

Name	Description	Default	Type
arguments (consumer)	Prompt arguments. Configure each argument with argument.NAME.description=TEXT and/or argument.NAME.required=true or false. An argument is declared by either option. This is a multi-value option with prefix: argument.		Map
bridgeErrorHandler (consumer)	Allows for bridging the consumer to the Camel routing Error Handler, which mean any exceptions (if possible) occurred while the Camel consumer is trying to pickup incoming messages, or the likes, will now be processed as a message and handled by the routing Error Handler. Important: This is only possible if the 3rd party component allows Camel to be alerted if an exception was thrown. Some components handle this internally only, and therefore bridgeErrorHandler is not possible. In other situations we may improve the Camel component to hook into the 3rd party component and make this possible for future releases. By default the consumer will use the org.apache.camel.spi.ExceptionHandler to deal with exceptions, that will be logged at WARN or ERROR level and ignored.	false	boolean
configuration (consumer)	The component configuration.		AiPromptConfiguration
description (consumer)	Human-readable description of what this prompt provides. When omitted, defaults to the prompt name.		String
tags (consumer)	Comma-separated list of tags used to group prompts. MCP servers select which prompts to expose using these tags. When omitted, the prompt goes into a default pool that is not exposed to remote clients.		String
title (consumer)	Optional display title for MCP prompt listings.		String
autowiredEnabled (advanced)	Whether autowiring is enabled. This is used for automatic autowiring options (the option must be marked as autowired) by looking up in the registry to find if there is a single instance of matching type, which then gets configured on the component. This can be used for automatic configuring JDBC data sources, JMS connection factories, AWS Clients, etc.	true	boolean

Name

Description

Default

Type

arguments (consumer)

Prompt arguments. Configure each argument with argument.NAME.description=TEXT and/or argument.NAME.required=true or false. An argument is declared by either option. This is a multi-value option with prefix: argument.

Map

bridgeErrorHandler (consumer)

Allows for bridging the consumer to the Camel routing Error Handler, which mean any exceptions (if possible) occurred while the Camel consumer is trying to pickup incoming messages, or the likes, will now be processed as a message and handled by the routing Error Handler. Important: This is only possible if the 3rd party component allows Camel to be alerted if an exception was thrown. Some components handle this internally only, and therefore bridgeErrorHandler is not possible. In other situations we may improve the Camel component to hook into the 3rd party component and make this possible for future releases. By default the consumer will use the org.apache.camel.spi.ExceptionHandler to deal with exceptions, that will be logged at WARN or ERROR level and ignored.

false

boolean

configuration (consumer)

The component configuration.

AiPromptConfiguration

description (consumer)

Human-readable description of what this prompt provides. When omitted, defaults to the prompt name.

String

tags (consumer)

Comma-separated list of tags used to group prompts. MCP servers select which prompts to expose using these tags. When omitted, the prompt goes into a default pool that is not exposed to remote clients.

String

title (consumer)

Optional display title for MCP prompt listings.

String

autowiredEnabled (advanced)

Whether autowiring is enabled. This is used for automatic autowiring options (the option must be marked as autowired) by looking up in the registry to find if there is a single instance of matching type, which then gets configured on the component. This can be used for automatic configuring JDBC data sources, JMS connection factories, AWS Clients, etc.

true

boolean

Endpoint Options

The AI Prompt endpoint is configured using URI syntax:

ai-prompt:promptName

With the following path and query parameters:

Path Parameters

Name	Description	Default	Type
promptName (consumer)	Required The prompt name advertised to MCP clients.		String

Name

Description

Default

Type

promptName (consumer)

Required The prompt name advertised to MCP clients.

String

Query Parameters

Name	Description	Default	Type
arguments (consumer)	Prompt arguments. Configure each argument with argument.NAME.description=TEXT and/or argument.NAME.required=true or false. An argument is declared by either option. This is a multi-value option with prefix: argument.		Map
description (consumer)	Human-readable description of what this prompt provides. When omitted, defaults to the prompt name.		String
tags (consumer)	Comma-separated list of tags used to group prompts. MCP servers select which prompts to expose using these tags. When omitted, the prompt goes into a default pool that is not exposed to remote clients.		String
title (consumer)	Optional display title for MCP prompt listings.		String
bridgeErrorHandler (consumer (advanced))	Allows for bridging the consumer to the Camel routing Error Handler, which mean any exceptions (if possible) occurred while the Camel consumer is trying to pickup incoming messages, or the likes, will now be processed as a message and handled by the routing Error Handler. Important: This is only possible if the 3rd party component allows Camel to be alerted if an exception was thrown. Some components handle this internally only, and therefore bridgeErrorHandler is not possible. In other situations we may improve the Camel component to hook into the 3rd party component and make this possible for future releases. By default the consumer will use the org.apache.camel.spi.ExceptionHandler to deal with exceptions, that will be logged at WARN or ERROR level and ignored.	false	boolean
exceptionHandler (consumer (advanced))	To let the consumer use a custom ExceptionHandler. Notice if the option bridgeErrorHandler is enabled then this option is not in use. By default the consumer will deal with exceptions, that will be logged at WARN or ERROR level and ignored.		ExceptionHandler
exchangePattern (consumer (advanced))	Sets the exchange pattern when the consumer creates an exchange. Enum values: InOnly InOut		ExchangePattern

Name

Description

Default

Type

arguments (consumer)

Map

description (consumer)

Human-readable description of what this prompt provides. When omitted, defaults to the prompt name.

String

tags (consumer)

String

title (consumer)

Optional display title for MCP prompt listings.

String

bridgeErrorHandler (consumer (advanced))

false

boolean

exceptionHandler (consumer (advanced))

To let the consumer use a custom ExceptionHandler. Notice if the option bridgeErrorHandler is enabled then this option is not in use. By default the consumer will deal with exceptions, that will be logged at WARN or ERROR level and ignored.

ExceptionHandler

exchangePattern (consumer (advanced))

Sets the exchange pattern when the consumer creates an exchange.

Enum values:

InOnly
InOut

ExchangePattern

Message Body

The message body at each side of the AI Prompt component: Consumer is the body of the messages the consumer creates, Consumer reply the bodies a consumer that answers its caller can reply with, Producer input the bodies the producer can send or write, and Producer output the body after the producer.

Side Body Description

Side	Body	Description
Consumer	`null`	No body is sent to the route. Each prompt argument is available as a message header with its configured argument name; values are strings.
Consumer reply	`text`, `list`, `bytes`, `stream` or `file`	A String, byte array, stream or file is converted to one user message. A List may contain Strings or Maps with role (user or assistant) and content. Content may be a String or an MCP content block.

Consumer

null

No body is sent to the route. Each prompt argument is available as a message header with its configured argument name; values are strings.

Consumer reply

text, list, bytes, stream or file

A String, byte array, stream or file is converted to one user message. A List may contain Strings or Maps with role (user or assistant) and content. Content may be a String or an MCP content block.

The bodies are the ones with the default options. A side that is not listed is not known, and tooling does not guess it. The carriers, the sides and the tools that use them are described in Message Body Types.

Usage

Each configured prompt argument is received by the route as a message header whose name is the argument name. MCP prompt arguments are strings. Configure an argument with argument.NAME.description and/or argument.NAME.required:

from("ai-prompt:summarize_account"
    + "?tags=crm"
    + "&description=Summarize an account"
    + "&title=Account summary"
    + "&argument.accountId.description=The account identifier"
    + "&argument.accountId.required=true")
    .setBody(simple("Summarize account ${header.accountId}, including its status and recent activity."));

A String route body becomes one MCP user message. A List route body becomes several messages, allowing a multi-turn prompt. List elements may be Strings (converted to user messages) or Maps containing role (user or assistant) and content. Content may be a String or an MCP content block, such as an image or embedded resource content object.

from("ai-prompt:review_code?tags=developer&argument.language.required=true")
    .process(exchange -> {
        String language = exchange.getMessage().getHeader("language", String.class);
        exchange.getMessage().setBody(List.of(
            "Review this " + language + " code for correctness and security.",
            Map.of("role", "assistant", "content", "I will focus on correctness, security and maintainability."),
            Map.of("role", "user", "content", "Return findings ordered by severity.")
        ));
    });

Tags and exposure

Tags group prompts so an MCP server can select which prompts to expose. A prompt without tags is placed in a default pool and is not exposed to remote clients. Configure camel.server.mcp-tags to select prompt routes alongside ai-tool and ai-resource routes.

Lifecycle and errors

A prompt is registered when its route starts or resumes and removed when it stops or suspends. Supporting MCP engines notify clients with notifications/prompts/list_changed when the prompt list changes.

Missing required arguments are rejected before the route executes. Route exceptions are logged server-side and returned to remote MCP clients as a generic prompt execution error. The MCP server applies a per-prompt execution timeout; a timed-out route may continue running on its worker thread until it completes.

Security

The messages returned by a prompt route are sent to the MCP client and placed in the model’s context as they are. When a route builds a prompt from data that outsiders can write, such as ticket comments, emails or documents, that data can contain instructions aimed at the model (prompt injection). Camel does not filter or mark such content. Include only data from sources you trust, or clearly mark untrusted content in the prompt, for example by placing it in its own delimited block and telling the model to treat it as data.