Allows sending WhatsApp messages to individuals or broadcasts, managing devices, saving contacts, and retrieving account info through the Kirimi WhatsApp API.
Click on "Install 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., "@kirimi-mcp send a WhatsApp message to Alice saying 'see you at 5pm'"
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.
MCP server for Kirimi WhatsApp API. Exposes Kirimi API tools to AI agents via the Model Context Protocol.
Tool | Description |
| Send a WhatsApp message to a single recipient |
| Broadcast to multiple recipients (max 1000) |
| List all connected WhatsApp devices |
| Get status of a specific device |
| Save a single contact |
| Bulk import contacts (max 1000) |
| Get account info, saldo, and stats |
Related MCP server: WAHA MCP
Get an API key from dash.kirimi.id/settings?tab=api
Find your device ID in the Kirimi dashboard
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"kirimi": {
"command": "npx",
"args": ["-y", "kirimi-mcp"],
"env": {
"KIRIMI_API_KEY": "your_api_key_here",
"KIRIMI_DEVICE_ID": "D-XXXXX"
}
}
}
}claude mcp add kirimi npx kirimi-mcp \
-e KIRIMI_API_KEY=your_api_key_here \
-e KIRIMI_DEVICE_ID=D-XXXXXVariable | Required | Description |
| ✅ | API key from Kirimi dashboard |
| ✅ | Default device ID for sending messages |
| ❌ | Override API base URL (default: |
bun install
bun run devMIT
Send a WhatsApp message to multiple recipients at once. Max 1000 numbers per call. Delay between sends is enforced automatically (min 30s).
| Name | Required | Description | Default |
|---|---|---|---|
| delay | No | Fixed delay in seconds between sends (default 30, min 30) | |
| label | Yes | Broadcast label/name (max 100 chars) | |
| message | No | Text message to broadcast | |
| numbers | Yes | Array of recipient phone numbers | |
| delay_max | No | Maximum delay in seconds for random delay range | |
| delay_min | No | Minimum delay in seconds for random delay range | |
| media_url | No | Optional media URL to attach to every message |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that delay is enforced automatically with a 30s minimum, which is a behavioral trait. However, it does not mention error handling, idempotency, or whether messages are queued or sent synchronously.
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 unnecessary words. It front-loads the core purpose and then adds constraints, achieving high density of useful 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?
Given 7 parameters and no output schema, the description is too brief. It fails to explain the relationship between delay, delay_min, delay_max (fixed vs random range), and does not describe label or media_url parameters. The return value or error behavior is also not mentioned.
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%, baseline 3. The description adds value by specifying the maximum numbers constraint (not in schema) and clarifying that delay is enforced with a minimum of 30s, which complements the delay parameter's description.
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 it sends a WhatsApp message to multiple recipients, distinguishing it from sibling send_message which likely targets a single recipient. It also specifies the limit of 1000 numbers per call.
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 key usage constraints: max 1000 numbers and minimum 30s delay between sends. It implicitly guides the agent to use this tool for bulk messaging versus send_message for single messages, but lacks explicit when-not-to-use or alternative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed status of a specific WhatsApp device.
| Name | Required | Description | Default |
|---|---|---|---|
| device_id | No | Device ID (e.g. D-XXXXX). Defaults to KIRIMI_DEVICE_ID env var if not provided. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It only says 'Get detailed status', leaving the agent guessing about what fields are returned, possible side effects (none likely but unstated), permissions needed, or rate limits. Minimal disclosure.
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?
Single sentence that is front-loaded and to the point. No extraneous information, every word carries meaning.
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 no output schema and no annotations, the description does not fully explain what 'detailed status' entails. Missing return format or examples, making it insufficient for a complete understanding.
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 already includes a description with default value fallback. The tool description adds no new information about the parameter beyond what the schema provides, so baseline of 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 'Get detailed status of a specific WhatsApp device', using a specific verb and resource. It distinguishes itself from sibling 'list_devices' by focusing on a single device.
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 when one needs status of a specific device, but does not explicitly state when to use this tool versus alternatives like 'list_devices' or other tools. No exclusions or nuances provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get current Kirimi account info: name, saldo, AI quota, device counts, and message stats.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It implies a read-only operation by 'Get', but does not explicitly state safety, auth needs, or rate limits. The behavior is straightforward given zero parameters, but lacks explicit disclosure beyond the obvious.
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?
A single sentence that is efficient and front-loaded, conveying all necessary information without redundancy.
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 (no parameters, no output schema), the description completely covers what the tool does by listing the specific fields returned. No additional context is needed.
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?
There are no parameters, so the description adds value by detailing the returned fields. According to the rubric, 0 parameters yields a baseline of 4, and the description meets that benchmark by specifying what info is retrieved.
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 'current Kirimi account info', and lists specific fields (name, saldo, AI quota, device counts, message stats). This differentiates it from sibling tools like send_message or list_devices.
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 retrieving account overview but does not explicitly state when to use this tool versus siblings like device_status or list_devices. No exclusions or alternative suggestions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all WhatsApp devices connected to this Kirimi account with their status.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden; it states listing devices with status, implying read-only, but doesn't disclose other behavioral traits like response format or pagination (if any).
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?
Single sentence, front-loaded with verb and resource, no extraneous 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 no output schema, no parameters, and no annotations, the description provides all necessary information: what the tool does and what it returns (list with status).
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 exists, so baseline score of 4 applies. Description does not need to add param info.
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?
Description clearly states verb 'List' and resource 'WhatsApp devices' with detail about status, distinguishing it from siblings like device_status which likely checks a single device.
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?
Provides context of listing devices for the account, but no explicit guidance on when to use vs alternatives or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Save a single contact to the Kirimi contact list.
| Name | Required | Description | Default |
|---|---|---|---|
| nama | Yes | Contact name | |
| nomor | Yes | Contact phone number | |
| device_id | No | Optional device ID to associate this contact with |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description provides no behavioral details beyond mutation. It lacks information on idempotency, conflict handling, overwrite behavior, or authorization requirements.
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 directly states the tool's purpose with no wasted words. It is appropriately sized for a simple tool but could include more context.
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 basic purpose but lacks usage guidelines and behavioral transparency. For a tool with no output schema and simple parameters, it is adequate but not 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 all parameters. The description adds no additional meaning or context beyond what is in the schema.
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 ('Save'), the resource ('contact'), and the specific scope ('a single contact to the Kirimi contact list'), distinguishing it from the sibling 'save_contacts_bulk' tool.
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 guidance is given on when to use this tool versus alternatives such as 'save_contacts_bulk' or other sibling tools, or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Import multiple contacts at once (max 1000). Duplicates are skipped.
| Name | Required | Description | Default |
|---|---|---|---|
| contacts | Yes | Array of contact objects | |
| device_id | No | Optional device ID to associate all contacts with |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description discloses key behaviors: a maximum batch size of 1000 and duplicate skipping. It could add more detail on idempotency or side effects but is good for what it provides.
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 with no waste, front-loaded with the main purpose. Every word 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?
The description lacks information on return values, error handling, and confirmation of success. For a bulk import tool, this is a noticeable gap despite moderate complexity.
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 input schema has 100% coverage with descriptions for both contacts and device_id. The description adds no additional meaning beyond the schema, meeting the baseline.
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 it imports multiple contacts at once with a max of 1000 and duplicate handling, distinguishing it from the sibling save_contact which handles single contacts.
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 batch usage but does not explicitly state when to use versus alternatives like save_contact for single contacts, nor does it provide exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Send a WhatsApp message to a single recipient. Supports text, media URL, and quoted replies.
| Name | Required | Description | Default |
|---|---|---|---|
| message | No | Text message to send | |
| receiver | Yes | Recipient phone number (e.g. 628123456789) or group JID | |
| media_url | No | Optional public URL of image/video/document to attach | |
| quoted_message_id | No | Optional message ID to quote/reply to |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description should fully disclose behavior. Mentions supported content types but omits crucial details like whether it sends immediately, requires opt-in, returns message ID, or handles errors.
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 concise sentences, no wasted words. Could be slightly more structured, but efficient.
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?
No output schema, so description should hint at return value. Missing behavioral context like success indicators or error states. Parameter info is good but overall incomplete for a mutation tool.
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 covers all 4 parameters with descriptions. Description adds minimal value beyond schema (e.g., 'supports text, media URL, quoted replies'), but 100% coverage means baseline is 3.
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?
Clearly states verb 'Send', resource 'WhatsApp message', and scope 'single recipient'. Distinguishes from sibling broadcast_message by specifying single recipient.
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?
Implies usage for one-to-one messaging vs broadcast, but no explicit when-to-use, prerequisites, or alternatives. Lacks guidance on not using for multiple recipients.
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. Dates show when Glama detected each change.
v1.0.0broadcast_messagedevice_statusget_user_infolist_devicessave_contactsave_contacts_bulksend_messageEvery tool serves a distinct purpose: broadcast vs. single message, device list vs. status, single vs. bulk contact saving, and account info. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern with snake_case (e.g., broadcast_message, list_devices, save_contact). The mix of imperative and get_/list_ prefixes is uniform.
Seven tools is well-scoped for a WhatsApp messaging server, covering sending, broadcasting, contacts, devices, and account info without bloat or deficiency.
Core operations are covered, but notable gaps exist: no tool for reading incoming messages, checking message status, or updating/deleting contacts. However, the domain focus is on sending and management, so minor.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Drive WhatsApp from any MCP client: pair devices, send text and media, manage contacts and groups.
The Mobile Text Alerts SMS MCP server enables your AI to send SMS messages & manage contacts
WhatsApp (Web + Business API), SMS, contacts, and call records via 2Chat's MCP server.
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kiriminow/kirimi-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
