Integrates with the LINE Messaging API to let AI agents interact with a LINE Official Account, including sending push and broadcast text or flex messages, retrieving user profiles, checking message quotas, managing rich menus, getting follower IDs, and retrieving group summaries.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@LINE Bot MCP Server broadcast a text message to all followers saying we're open today"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Model Context Protocol (MCP) server implementation that integrates the LINE Messaging API to connect an AI Agent to the LINE Official Account.
This repository is provided as a preview version. While we offer it for experimental purposes, please be aware that it may not include complete functionality or comprehensive support.
push_text_message
Push a simple text message to a user via LINE.
Inputs:
userId (string?): The user ID to receive a message. Defaults to DESTINATION_USER_ID. Either userId or DESTINATION_USER_ID must be set.
message.text (string): The plain text content to send to the user.
push_flex_message
Push a highly customizable flex message to a user via LINE.
Inputs:
userId (string?): The user ID to receive a message. Defaults to DESTINATION_USER_ID. Either userId or DESTINATION_USER_ID must be set.
message.altText (string): Alternative text shown when flex message cannot be displayed.
message.contents (any): The contents of the flex message. This is a JSON object that defines the layout and components of the message.
message.contents.type (enum): Type of the container. 'bubble' for single container, 'carousel' for multiple swipeable bubbles.
broadcast_text_message
Broadcast a simple text message via LINE to all users who have followed your LINE Official Account.
Inputs:
message.text (string): The plain text content to send to the users.
broadcast_flex_message
Broadcast a highly customizable flex message via LINE to all users who have added your LINE Official Account.
Inputs:
message.altText (string): Alternative text shown when flex message cannot be displayed.
message.contents (any): The contents of the flex message. This is a JSON object that defines the layout and components of the message.
message.contents.type (enum): Type of the container. 'bubble' for single container, 'carousel' for multiple swipeable bubbles.
get_profile
Get detailed profile information of a LINE user including display name, profile picture URL, status message and language.
Inputs:
userId (string?): The ID of the user whose profile you want to retrieve. Defaults to DESTINATION_USER_ID.
get_message_quota
Get the message quota and consumption of the LINE Official Account. This shows the monthly message limit and current usage.
Inputs:
None
get_rich_menu_list
Get the list of rich menus associated with your LINE Official Account.
Inputs:
None
delete_rich_menu
Delete a rich menu from your LINE Official Account.
Inputs:
richMenuId (string): The ID of the rich menu to delete.
set_rich_menu_default
Set a rich menu as the default rich menu.
Inputs:
richMenuId (string): The ID of the rich menu to set as default.
cancel_rich_menu_default
Cancel the default rich menu.
Inputs:
None
create_rich_menu
Create a rich menu based on the given actions. Generate and upload an image. Set as default.
Inputs:
chatBarText (string): Text displayed in chat bar, also used as rich menu name.
actions (array): The actions of the rich menu. You can specify minimum 1 to maximum 6 actions. Each action can be one of the following types:
postback: For sending a postback action
message: For sending a text message
uri: For opening a URL
datetimepicker: For opening a date/time picker
camera: For opening the camera
cameraRoll: For opening the camera roll
location: For sending the current location
richmenuswitch: For switching to another rich menu
clipboard: For copying text to clipboard
get_follower_ids
Get a list of user IDs of users who have added the LINE Official Account as a friend. This allows you to obtain user IDs for sending messages without manually preparing them.
Inputs:
start (string?): Continuation token to get the next array of user IDs. Returned in the next property of a previous response.
limit (number?): The maximum number of user IDs to retrieve in a single request.
get_group_summary
Get the group chat summary including group ID, group name, and group icon URL, using the group ID.
Inputs:
groupId (string): The group ID of the target group chat.
Related MCP server: MCP LINE Server
requirements:
Node.js v22 or later
This MCP server utilizes a LINE Official Account. If you do not have one, please create it by following this instructions.
If you have a LINE Official Account, enable the Messaging API for your LINE Official Account by following this instructions.
Please add the following configuration for an AI Agent like Claude Desktop or Cline.
Set the environment variables or arguments as follows:
CHANNEL_ACCESS_TOKEN: (required) Channel Access Token. You can confirm this by following this instructions.
DESTINATION_USER_ID: (optional) The default user ID of the recipient. If the Tool's input does not include userId, DESTINATION_USER_ID is required. You can confirm this by following this instructions.
{
"mcpServers": {
"line-bot": {
"command": "npx",
"args": [
"@line/line-bot-mcp-server"
],
"env": {
"NPM_CONFIG_IGNORE_SCRIPTS": "true",
"CHANNEL_ACCESS_TOKEN" : "FILL_HERE",
"DESTINATION_USER_ID" : "FILL_HERE"
}
}
}
}This MCP server utilizes a LINE Official Account. If you do not have one, please create it by following this instructions.
If you have a LINE Official Account, enable the Messaging API for your LINE Official Account by following this instructions.
Clone this repository:
git clone git@github.com:line/line-bot-mcp-server.gitBuild the Docker image:
docker build -t line/line-bot-mcp-server .Please add the following configuration for an AI Agent like Claude Desktop or Cline.
Set the environment variables or arguments as follows:
mcpServers.args: (required) The path to line-bot-mcp-server.
CHANNEL_ACCESS_TOKEN: (required) Channel Access Token. You can confirm this by following this instructions.
DESTINATION_USER_ID: (optional) The default user ID of the recipient. If the Tool's input does not include userId, DESTINATION_USER_ID is required.
You can confirm this by following this instructions.
{
"mcpServers": {
"line-bot": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"CHANNEL_ACCESS_TOKEN",
"-e",
"DESTINATION_USER_ID",
"line/line-bot-mcp-server"
],
"env": {
"CHANNEL_ACCESS_TOKEN" : "FILL_HERE",
"DESTINATION_USER_ID" : "FILL_HERE"
}
}
}
}You can use the MCP Inspector to test and debug the server locally.
Clone the repository:
git clone git@github.com:line/line-bot-mcp-server.git
cd line-bot-mcp-serverInstall dependencies:
npm installBuild the project:
npm run buildAfter building the project, you can start the MCP Inspector:
npx @modelcontextprotocol/inspector node dist/index.js \
-e CHANNEL_ACCESS_TOKEN="YOUR_CHANNEL_ACCESS_TOKEN" \
-e DESTINATION_USER_ID="YOUR_DESTINATION_USER_ID"This will start the MCP Inspector interface where you can interact with the LINE Bot MCP Server tools and test their functionality.
This project respects semantic versioning
Please check CONTRIBUTING before making a contribution.
Broadcast a highly customizable flex message via LINE to all users who have added your LINE Official Account. Supports both bubble (single container) and carousel (multiple swipeable bubbles) layouts. Please be aware that this message will be sent to all users.
| Name | Required | Description | Default |
|---|---|---|---|
| message | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With destructiveHint=true in annotations, the description adds valuable context by specifying the scope of the destructive impact: 'this message will be sent to all users.' This complements rather than contradicts the annotation, giving the agent a concrete sense of the blast radius. No annotation contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences with no wasted words: action+audience, capability (bubble/carousel), and a deliberate warning. The warning in sentence three slightly echoes sentence one's 'all users,' but this repetition is justified emphasis for a destructive broadcast operation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a highly complex, destructive broadcast tool with no output schema, the description covers the core semantics and audience scope but misses operational realities: quota consumption (sibling get_message_quota hints this matters), non-reversibility of broadcasts, and any structural guidance for the message parameter. An agent would benefit from knowing this action cannot be undone.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% for the single required 'message' parameter, so the description must compensate. It does add meaningful semantics by explaining the two layout options (bubble and carousel) that map to the contents oneOf in the schema. However, given the extreme complexity of the nested message object, it only scratches the surface—it doesn't mention required altText or the structural rules (e.g., body must be a Box).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb (broadcast), resource (flex message), and scope (all users who added the LINE Official Account), making the tool's function unambiguous. It naturally distinguishes itself from siblings like push_flex_message (targeted) and broadcast_text_message (text-only) by naming the audience and message type.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description makes the broadcast scope explicit with 'all users who have added your LINE Official Account' and reinforces it with the warning that the message goes to everyone. This clearly implies the push vs broadcast decision context, though it doesn't explicitly name alternatives like push_flex_message or state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Broadcast a simple text message via LINE to all users who have followed your LINE Official Account. Use this for sending plain text messages without formatting. Please be aware that this message will be sent to all users.
| Name | Required | Description | Default |
|---|---|---|---|
| message | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotation destructiveHint=true is reinforced and expanded by the description's explicit warning that the message goes to all followers, which is a significant behavioral consequence. This goes beyond the annotation by explaining the reach and potential impact. The description does not mention rate limits or response details, but for a broadcast action, the key behavior is covered. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no filler. The main action is front-loaded ('Broadcast a simple text message via LINE to all users'), followed by a usage condition and a warning. Every sentence adds value, and the length is appropriate for the tool's simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the core purpose, the usage condition (plain text), and the broadcast scope warning. It does not mention prerequisites like authentication, but that may be implicit for LINE API tools. It also lacks explicit mention of the alternative for targeted sends, but the 'all users' phrase covers that. Given the single nested parameter and lack of output schema, the description is mostly complete, with only minor gaps around explicit alternative routing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, meaning the tool description must compensate for parameter meaning. The description only says 'simple text message' and 'plain text', but does not explain that the message parameter is an object with a required 'text' field and an optional 'type' constrained to 'text'. The schema itself does provide descriptions for the 'text' property, but the tool description adds no additional parameter-level guidance, leaving the agent to rely solely on the schema structure. This is a notable gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (broadcast), the resource (text message to all LINE followers), and the scope (all users who followed the Official Account). It also distinguishes from siblings by specifying 'plain text messages without formatting', which implies the existence of a flex alternative, and 'all users' which implies targeted sends. This makes the tool's purpose unambiguous and differentiates it from push_text_message and broadcast_flex_message.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Use this for sending plain text messages without formatting', giving a clear condition for when to use it. It also warns 'Please be aware that this message will be sent to all users', which signals the impact and implicitly cautions against using it for targeted audiences. However, it does not name the alternative tools (e.g., push_text_message for targeted sends), so the guidance is helpful but not fully explicit about exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a list of user IDs of users who have added the LINE Official Account as a friend. This allows you to obtain user IDs for sending messages without manually preparing them.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | The maximum number of user IDs to retrieve in a single request. | |
| start | No | Continuation token to get the next array of user IDs. Returned in the 'next' property of a previous response. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations include readOnlyHint=true, which already indicates a safe read operation. The description goes further by explaining the purpose (obtaining IDs for messaging) and implying the data is a list, which aligns with the read-only nature. It does not contradict annotations, and the additional context about the use case enhances transparency beyond the annotation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, with two sentences that directly state the tool's function and a key use case. It is front-loaded with the primary action ('Get a list of user IDs') and avoids unnecessary detail. Every word earns its place, making it easy for an agent to scan quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (few params, no output schema, read-only), the description is nearly complete. The main missing piece is the return format, but with no output schema and the schema already providing param descriptions, this is a minor gap. The description sufficiently explains the tool's role in the context of messaging, which is enough for an agent to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents both parameters (limit and start). The description does not add syntax or format details beyond that. However, it does implicitly convey that the result is a list of IDs and that 'start' is a continuation token, which is already in the schema. The description adds little incremental meaning, so a baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the function: retrieving user IDs of friends who added the LINE Official Account, with a specific purpose (sending messages). This distinguishes it from sibling tools like get_profile (which retrieves a single user's profile) and the messaging tools (which send messages). The verb 'get' plus the resource 'follower IDs' makes the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for obtaining user IDs for messaging, but does not provide explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives. Sibling tools like get_profile exist for retrieving individual profiles, but the description does not contrast them. The intended use case is clear enough for an agent to infer, but explicit routing is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the group chat summary including group ID, group name, and group icon URL, using the group ID.
| Name | Required | Description | Default |
|---|---|---|---|
| groupId | Yes | The group ID of the target group chat. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint=true already declares this as a safe read, and the description does not contradict it. Beyond that, it adds little behavioral context — no auth requirements, error cases, or whether the group must be one the bot is in. The disclosed return fields are useful but primarily response-shape information.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, front-loaded with the resource and the identifier needed, with no filler. Every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description usefully names the fields returned (ID, name, icon URL), which an agent would otherwise not know. For a single-parameter read tool with a readOnlyHint, that covers most of what is needed, though call preconditions remain unstated.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the single parameter is fully documented in the schema. The description's 'using the group ID' adds no syntax, format, or constraint detail beyond what the schema already states, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Specific verb (Get) and resource (group chat summary), and it enumerates the returned fields (group ID, name, icon URL). It does not distinguish itself from siblings like get_profile or get_message_quota, but the purpose is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No when-to-use guidance, no prerequisites, and no mention of when another sibling tool would be a better choice. The usage is only implied by the tool name and the mention of 'using the group ID'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the message quota and consumption of the LINE Official Account. This shows the monthly message limit and current usage.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true. Description adds context about monthly message limit and current usage, which is valuable beyond the annotation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, clear and front-loaded with no extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description fully covers the tool's purpose for a simple read-only operation with no parameters and no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist in the schema; description adds no parameter details, but baseline is 4 for 0-parameter tools with 100% schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'message quota and consumption'. It distinguishes from sibling tools that are about sending messages or managing rich menus.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for checking quota before sending messages, but does not explicitly state when to use this tool over siblings or provide alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed profile information of a LINE user including display name, profile picture URL, status message and language.
| Name | Required | Description | Default |
|---|---|---|---|
| userId | No | The user ID to get a profile. Defaults to DESTINATION_USER_ID. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the agent knows this is a safe read operation. The description adds the specific fields returned, which is useful context beyond the annotation. However, it does not disclose potential error conditions (e.g., invalid userId, user not found) or rate-limit behavior, which would be valuable for a read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the main purpose and lists the returned fields. It is efficient and easy to parse, though it could be slightly more structured by separating the purpose from the field list. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read tool with one optional parameter and no output schema, the description is mostly complete. It covers what the tool does and what it returns. However, it lacks information about error handling, whether the userId must be a friend of the bot, and any authentication requirements, which are relevant for LINE API calls. The annotations cover the safety profile, but the description could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents the userId parameter. The description adds the default behavior (defaults to DESTINATION_USER_ID) which is already in the schema's default field. The description does not add significant meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: retrieving detailed profile information for a LINE user, and enumerates the specific fields returned (display name, profile picture URL, status message, language). This is a specific verb+resource combination that distinguishes it from sibling tools like push_text_message or get_rich_menu_list.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for fetching a user's profile but does not explicitly state when to use this tool versus alternatives. It does not mention exclusions or prerequisites, such as whether the user must be a friend or have consented. The context is clear enough for a simple read operation, but no explicit when/when-not guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Push a highly customizable flex message to a user via LINE. Supports both bubble (single container) and carousel (multiple swipeable bubbles) layouts.
| Name | Required | Description | Default |
|---|---|---|---|
| userId | No | The user ID to receive a message. Defaults to DESTINATION_USER_ID. | |
| message | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations include destructiveHint: true, which already signals that this operation has side effects. The description adds no extra behavioral context beyond the obvious fact that it sends a message. It does not mention any rate limits, authentication requirements, or other operational details, but the annotation covers the safety profile, so this is acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, using only two sentences to convey the core purpose and the two layout variants. It is front-loaded with the main action and target, and every word earns its place. There is no redundant or filler text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the extreme complexity of the message schema (nested objects, many options), the description is far too brief. It does not mention the required fields (altText, contents), the structure of the message, or any constraints. With no output schema and only 50% parameter coverage, an agent would struggle to construct a valid call without additional documentation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 50%, meaning the description must compensate for the missing parameter documentation. The description does not explain the message structure, the required fields, or the meaning of the parameters. The schema itself provides some descriptions (e.g., userId) but the message parameter is complex and undocumented. The description adds no value beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (push) and the resource (flex message) and specifies the delivery target (to a user via LINE). It also mentions the two layout options (bubble and carousel), which adds specificity. However, it does not explicitly distinguish from sibling tools like broadcast_flex_message or push_text_message, though the singular 'user' implies a direct push rather than a broadcast.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention that this is for a single user vs. broadcast, nor does it reference the sibling tools or any selection criteria. An agent would have to infer usage from the name and context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Push a simple text message to a user via LINE. Use this for sending plain text messages without formatting.
| Name | Required | Description | Default |
|---|---|---|---|
| userId | No | The user ID to receive a message. Defaults to DESTINATION_USER_ID. | |
| message | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The destructiveHint annotation signals that pushing a message has irreversible side effects, but the description adds no behavioral context such as immediate delivery, inability to recall, or quota implications. It repeats the obvious action rather than disclosing consequences.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, front-loaded with the action and followed by a usage condition. No filler or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple direct-message tool, but it leaves the destructive/side-effect nature unexplained and does not reference the broadcast/flex siblings even though the schema and annotations are otherwise thin. It is callable but not fully contextualized.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already documents that text is plain content and that userId defaults to DESTINATION_USER_ID; the description's 'simple text message without formatting' adds little. With only 50% schema description coverage and no extra parameter guidance in the description, the gap is not compensated.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action ('Push a simple text message to a user via LINE') and explicitly limits scope to plain text without formatting, which distinguishes it from sibling flex and broadcast tools. The resource, channel, and message type are all clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'Use this for sending plain text messages without formatting' gives clear conditions for use and implies it is not for rich content. It does not explicitly name alternative tools or state when not to use it, so it falls one step short of fully explicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.0.1-localbroadcast_flex_messagebroadcast_text_messagecancel_rich_menu_defaultcreate_rich_menudelete_rich_menuget_follower_idsget_group_summaryget_message_quotaget_profileget_rich_menu_listpush_flex_messagepush_text_messageset_rich_menu_defaultScored across 13 tools
Tools are mostly distinct, targeting different combinations of message type (text/flex), delivery method (push/broadcast), and rich menu operations. However, push vs broadcast semantics are separated only by description, and rich menu tools form a cluster where create/delete/set/cancel are clear but get_rich_menu_list overlaps somewhat with set/cancel defaults. No two tools are truly indistinguishable.
Strong verb_noun pattern throughout (push_text_message, broadcast_flex_message, get_profile, create_rich_menu). Minor inconsistency: 'set_rich_menu_default' and 'cancel_rich_menu_default' put the verb first but the noun phrase ordering differs from 'delete_rich_menu' and 'get_rich_menu_list'.
13 tools is well-scoped for a LINE messaging and rich menu management server. Each tool has a clear role, covering messaging, user data, and rich menu lifecycle. Slightly high but reasonable given the two distinct functional areas.
Core messaging (push/broadcast text and flex), user profile, follower IDs, group summary, quota, and rich menu CRUD/default operations are present. However, notable gaps: no push/broadcast for other message types (image, video, sticker), no multicast, no get_rich_menu_by_id or update_rich_menu_image, and no group membership or leave operations. The surface is functional but incomplete for a full LINE Official Account integration.
Messaging tools for AI agents: send messages, manage chats, groups and channels.
Your own LinkedIn, WhatsApp, Instagram, Telegram, Email and Calendar accounts, usable from any agent
LinkedIn for AI agents: inbox, invitations, Sales Navigator search, posts, jobs, quotas, webhooks.
Carbon Voice MCP serves as a bridge that connects AI assistants like ChatGPT, Claude, and Cursor to a user's Carbon Voice account, turning voice messages and conversations into a private, on-demand knowledge base. It provides 28 specialized tools for comprehensive voice messaging management, including creating and sending messages, accessing conversation history with instant transcription, running AI actions (summarization, TLDR generation, meeting notes), and managing workspace collaboration through folders, contacts, and team communications.
