--- title: "Tools | Micdrop" description: "The Agent system supports adding and removing custom tools to extend its capabilities." url: "https://micdrop.dev/docs/server/tools" --- * [Getting Started](/docs/getting-started) * [Client (Browser)](/docs/client) * [Installation](/docs/client/installation) * [React Hooks](/docs/client/react-hooks) * [Start/Stop Call](/docs/client/start-stop-call) * [Pause/Resume Call](/docs/client/pause-resume-call) * [Mute/Unmute Call](/docs/client/mute-unmute-call) * [Call State](/docs/client/call-state) * [Display Conversation Messages](/docs/client/display-conversation-messages) * [Handling Tool Calls](/docs/client/handling-tool-calls) * [Device Management](/docs/client/devices-management) * [Voice Activity Detection (VAD)](/docs/client/vad) * [Turn Detection](/docs/client/turn-detection) * [Reducing Latency](/docs/client/latency) * [Error Handling](/docs/client/error-handling) * Utility Classes * [Mic](/docs/client/utility-classes/mic) * [MicdropClient](/docs/client/utility-classes/micdrop-client) * [MicRecorder](/docs/client/utility-classes/mic-recorder) * [Speaker](/docs/client/utility-classes/speaker) * [Client (React Native)](/docs/react-native) * [Installation](/docs/react-native/installation) * [Hooks and Call State](/docs/react-native/hooks) * [Audio Output and Devices](/docs/react-native/audio-output) * [Voice Activity Detection (VAD)](/docs/react-native/vad) * [Turn Detection](/docs/react-native/turn-detection) * [Using Another Audio Library](/docs/react-native/custom-audio) * [Server (Node.js)](/docs/server) * [Installation](/docs/server/installation) * [With Fastify](/docs/server/with-fastify) * [With NestJS](/docs/server/with-nestjs) * [Auth and Parameters](/docs/server/auth-and-parameters) * [First Message](/docs/server/first-message) * [Dictation and Text-Only Calls](/docs/server/dictation) * [Partial Messages](/docs/server/partial-messages) * [Save Messages](/docs/server/save-messages) * [Resume a Conversation](/docs/server/resume-conversation) * [Recording Audio](/docs/server/recording-audio) * [Error Handling](/docs/server/error-handling) * [Tools](/docs/server/tools) * [Extract Value from Answer](/docs/server/extract) * [Auto End Call](/docs/server/auto-end-call) * [Semantic Turn Detection](/docs/server/semantic-turn-detection) * [Noise Filtering](/docs/server/noise-filtering) * [Micdrop Protocol](/docs/server/protocol) * [AI Integrations](/docs/ai-integration) * Provided Integrations * [AI SDK](/docs/ai-integration/provided-integrations/ai-sdk) * [Cartesia](/docs/ai-integration/provided-integrations/cartesia) * [ElevenLabs](/docs/ai-integration/provided-integrations/elevenlabs) * [Gladia](/docs/ai-integration/provided-integrations/gladia) * [Gradium](/docs/ai-integration/provided-integrations/gradium) * [Kokoro](/docs/ai-integration/provided-integrations/kokoro) * [Mistral](/docs/ai-integration/provided-integrations/mistral) * [OpenAI](/docs/ai-integration/provided-integrations/openai) * [Piper](/docs/ai-integration/provided-integrations/piper) * [Pocket TTS](/docs/ai-integration/provided-integrations/pocket-tts) * [Qwen3-TTS](/docs/ai-integration/provided-integrations/qwen-tts) * [Whisper](/docs/ai-integration/provided-integrations/whisper) * Custom Integrations * [Agent (LLM)](/docs/ai-integration/custom-integrations/custom-agent) * [Speech-to-Text (STT)](/docs/ai-integration/custom-integrations/custom-stt) * [Text-to-Speech (TTS)](/docs/ai-integration/custom-integrations/custom-tts) * Fallback Strategies * [FallbackAgent](/docs/ai-integration/fallback-strategies/agent-fallback) * [FallbackSTT](/docs/ai-integration/fallback-strategies/stt-fallback) * [FallbackTTS](/docs/ai-integration/fallback-strategies/tts-fallback) * [Local Models](/docs/ai-integration/local-models) * [Local LLM](/docs/ai-integration/local-models/agent) * [Local STT](/docs/ai-integration/local-models/speech-to-text) * [Local TTS](/docs/ai-integration/local-models/text-to-speech) * [Latency and Memory](/docs/ai-integration/local-models/performance) * [Explorations](/docs/ai-integration/local-models/explorations) * [MiniCPM5-2B](/docs/ai-integration/local-models/explorations/minicpm) * [Mistral 7B](/docs/ai-integration/local-models/explorations/mistral-7b) * [Voxtral Mini 3B](/docs/ai-integration/local-models/explorations/voxtral-stt) * [Voxtral TTS 4B](/docs/ai-integration/local-models/explorations/voxtral-tts) * [AuK and AuK-Flash](/docs/ai-integration/local-models/explorations/auk) * [IA Vocale Souveraine 🇫🇷🇪🇺](/docs/ai-integration/sovereign-voice-ai) * [Migration](/docs/migration) * [Upgrade to v3](/docs/migration/v3) [Micdrop](/) › [Documentation](/docs/getting-started) › [Server (Node.js)](/docs/server) # Tools The Agent system supports adding and removing custom tools to extend its capabilities. ## Adding Tools Use `addTool(tool: Tool)` to add custom functions that the agent can call during conversations: ``` import { z } from 'zod'import { OpenaiAgent } from '@micdrop/openai'import { MicdropServer } from '@micdrop/server' const agent = new OpenaiAgent({ apiKey: process.env.OPENAI_API_KEY || '', systemPrompt: 'You are a helpful assistant that can manage user information.',}) // Add a simple tool without parametersagent.addTool({ name: 'get_time', description: 'Get the current time', execute: () => new Date().toLocaleTimeString(),}) // Add a tool with typed parameters using Zod schemaagent.addTool({ name: 'set_user_info', description: 'Save user information to the database', inputSchema: z.object({ city: z.string().describe('City'), jobTitle: z.string().describe('Job title').nullable(), experience: z .number() .describe('Number of years of experience of the user') .nullable(), }), execute: ({ city, jobTitle, experience }) => { // Your implementation here console.log('Saving user:', { city, jobTitle, experience }) return { success: true, message: 'User information saved' } },}) // Add a tool that returns data for the conversationagent.addTool({ name: 'search_database', description: 'Search for items in the database', parameters: z.object({ query: z.string().describe('Search query'), limit: z.number().default(10).describe('Maximum number of results'), }), execute: async ({ query, limit }) => { // Your search implementation const results = await searchDatabase(query, limit) return { results, total: results.length } }, emitOutput: true, // Enable tool call events}) // Add a tool that can interact with the server (e.g., delayed responses)function addTools(server: MicdropServer, agent: OpenaiAgent) { agent.addTool({ name: 'say_something_later', description: 'Say something later (can be used as an alarm clock or reminder)', inputSchema: z.object({ message: z.string().describe('The message to say'), delay: z.number().describe('The delay in seconds'), }), execute: async ({ message, delay }) => { setTimeout(() => { agent.addAssistantMessage(message) server.speak(message) }, delay * 1000) return { success: true } }, })} ``` ## Tool Options Option Type Default Description `name` `string` Required Unique name for the tool `description` `string` Required Description of what the tool does `inputSchema` `z.ZodObject` Optional Zod schema for parameter validation `execute` `(input, agent) => any | Promise` Required Function to execute when tool is called `skipAnswer` `boolean` `false` Skip assistant response after tool call `emitOutput` `boolean` `false` Emit ToolCall events for monitoring 💡 Tip If `emitOutput` is true, the tool call output is also sent to the client and available with the `ToolCall` event. ## The `agent` context The `execute` function receives the executing agent as a second argument. Use it instead of capturing a specific agent in a closure, so tools stay portable and can be shared between agents (this is what lets [FallbackAgent](/docs/ai-integration/fallback-strategies/agent-fallback) hand the same tools to every provider it switches to): ``` agent.addTool({ name: 'count_messages', description: 'Count the messages exchanged so far', execute: (input, agent) => ({ count: agent.conversation.length }),}) ``` The first `input` argument is always present; the `agent` argument is optional, so simple tools can keep ignoring it. The built-in `autoEndCall`, `autoSemanticTurn` and `autoIgnoreUserNoise` tools use this same mechanism internally. ## Removing Tools Use `removeTool(name: string)` to remove tools by name: ``` // Remove a specific toolagent.removeTool('get_time') ``` ## Getting Tools Use `getTool(name: string)` to retrieve a tool by name: ``` // Get a specific tool (undefined if not found)const tool = agent.getTool('get_time') ``` ## Tool Call Events Monitor tool executions in real-time by enabling the `emitOutput` option and listening for `ToolCall` events: ``` import { OpenaiAgent } from '@micdrop/openai' const agent = new OpenaiAgent({ apiKey: process.env.OPENAI_API_KEY || '', systemPrompt: 'You are a helpful assistant with access to tools.',}) // Add tool with emitOutput enabledagent.addTool({ name: 'save_user_data', description: 'Save user data to the system', inputSchema: z.object({ name: z.string(), email: z.string().email(), }), emitOutput: true, // Enable events for this tool}) // Listen for tool call eventagent.on('ToolCall', (toolCall) => { console.log(`Tool called: ${toolCall.name}`) console.log('Parameters:', toolCall.parameters) console.log('Output:', toolCall.output) if (toolCall.name === 'save_user_data') { // Sync data to external systems syncToDatabase(toolCall.output) }}) ``` 💡 Tip It may be easier and safer to use tool `execute` option if you don’t need to emit the output to the client. ## Tool Call Event Structure The `ToolCall` event provides complete information about tool execution: ``` interface ToolCall { name: string // Tool name that was called parameters: any // Parameters passed to the tool output: any // Result returned by the tool execute function} ``` [Previous← Error Handling](/docs/server/error-handling)[NextExtract Value from Answer →](/docs/server/extract) On this page * [Adding Tools](#adding-tools) * [Tool Options](#tool-options) * [The agent context](#the-agent-context) * [Removing Tools](#removing-tools) * [Getting Tools](#getting-tools) * [Tool Call Events](#tool-call-events) * [Tool Call Event Structure](#tool-call-event-structure)