# MonkeyLearn MCP for AI Agents AI Agent Connect > MonkeyLearn MCP lets you perform sentiment analysis and keyword extraction through your AI agent. It connects your existing MonkeyLearn account to any MCP-compatible client, allowing you to run classifiers, inspect models, and track processing activity without manual API calls. It's the fastest way to bring high-level NLP into your daily chat. ## Overview - **Category:** customer-support - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_ajv6syROl8nKEZz1ZGobS0MBFBO5sLwE0cSqFWQ2/ai-agent-connect - **Tags:** text-classification, entity-extraction, sentiment-analysis, nlp, machine-learning, data-labeling ## Description This Connector lets you run MonkeyLearn's NLP models directly through your AI agent. Instead of jumping between a dashboard and your editor, you can just ask your agent to tell you what people are saying or to pull specific data out of a messy block of text. It works by connecting to your existing account, so you can use the classifiers and extractors you've already built. You can check your active pipelines, see what tags your models are using, and keep an eye on your processing activity in real-time. It's a way to bring high-level text analysis into your daily chat with your AI. You can find this among the 4,000+ options in the Vinkius catalog, making it easy to plug into your existing workflow. You don't need to write any new code or manage complex API headers. If you need to know if a customer is angry or if a review mentions a specific product, you just ask. The agent handles the heavy lifting of talking to MonkeyLearn and gives you the answer in plain English. It makes your AI much smarter at understanding the nuance of human language. You can use it to see which models are currently active in your account or get the specific metadata for a model you're trying to debug. It also helps you stay on top of your automated workflows, letting you see what's running and what's finished. Whether you're trying to understand the why behind customer feedback or just need to pull a list of keywords for an SEO project, this Connector puts that power right in your chat window. It turns your AI into a specialized NLP analyst that knows your specific account setup inside and out. ## Tools ### classify_text Use a model to categorize text. It's perfect for identifying sentiment or intent in a few seconds. ### extract_text_entities Extract entities ### get_classifier_details View metadata for a specific classifier. It helps you check the exact settings for your NLP models. ### get_extractor_details Get the metadata for an extractor. This shows you how your data points are being pulled. ### list_classifier_tags List model tags ### list_classifiers See all classifiers in your account. This helps you find the right model for a new project. ### list_extractor_tags List extractor tags ### list_extractors List all the extractors you have. Use this to see what data you can currently pull from text. ### list_model_versions List model versions ### list_nlp_workflows List account workflows ### run_workflow Run NLP workflow ### get_api_status Get account status ## Prompt Examples **Prompt:** ``` Classify the sentiment of this review: 'The product exceeded all my expectations, truly amazing!' ``` **Response:** ``` I've analyzed that review for you. Based on the sentiment analysis, the text is categorized as **Positive**. **Analysis Details:** - **Sentiment:** Positive - **Confidence Score:** 98.5% - **Key Themes:** High satisfaction, exceeded expectations. ``` **Prompt:** ``` List all the classifiers I have in my MonkeyLearn account. ``` **Response:** ``` I've pulled your available classifiers. Here is what you have ready to use: | Model Name | ID | Purpose | | :--- | :--- | :--- | | **Sentiment Analysis** | `cl_oZ9GRg8P` | General mood detection | | **Topic Detection** | `cl_piuz8L9` | Identifying main subjects | | **Support Ticket Classifier** | `cl_abc123` | Routing customer issues | | **Email Intent** | `cl_xyz789` | Categorizing incoming emails | ``` **Prompt:** ``` Show me my recent activity from the last 24 hours. ``` **Response:** ``` Here is a summary of your account activity from the last 24 hours: - **Total API Calls:** 156 - **Most Used Model:** Sentiment Analysis - **Active Workflows:** 3 - **Status:** All systems operational and within your credit limit. ``` ## Capabilities ### Classify text sentiment Run a sentiment analysis model on any text to see if it's positive, negative, or neutral. ### Extract keywords from raw data Pull specific data points like dates or entities out of unstructured text strings automatically. ### Browse active classifiers See all the sentiment and topic detection models available in your account. ### View extractor metadata Check the specific configuration and rules for your data extraction models. ### Monitor account activity Check your recent API calls and processing logs to stay on top of your usage. ### List NLP pipelines View your sequenced NLP tasks to see how your data moves through your models. ### Inspect tag hierarchies Look at the tag trees to understand how your models are organizing your data. ### Track automated workflows See your scheduled processing jobs and monitor their current status. ## Use Cases ### Analyzing customer reviews A product manager wants to know if a new feature is being received well. They ask the agent to run classify_text on 50 recent reviews to summarize the overall sentiment. ### Extracting SEO keywords A content writer needs to pull 10 specific keywords from a long blog draft. They ask the agent to use extract_text to get a clean list of terms in seconds. ### Checking model configurations A data scientist needs to see what models are active. They ask the agent to list_classifiers to find the right one for a new test. ### Monitoring API usage An ops lead wants to see how many calls were made today. They ask the agent to list_activity to check the logs and stay under budget. ## Benefits - Get instant sentiment scores on customer feedback using classify_text to understand the mood of your audience. - Turn messy notes into structured data by using extract_text to pull out dates, names, and specific entities. - Manage your entire NLP library easily by browsing your models with list_classifiers and list_extractors. - Keep a close eye on your costs and API limits by checking your recent logs with list_activity. - Visualize your data organization by using list_tag_trees to see how your models group different categories. - Stay on top of your automated data processing by checking your scheduled jobs with list_workflows. ## How It Works The bottom line is you get to run complex NLP tasks using natural language instead of writing custom scripts. 1. Connect your MonkeyLearn API key in your Connector client. 2. Ask your agent to run a specific classifier or pull data from a text block. 3. Get back the analyzed results or model metadata immediately. ## Frequently Asked Questions **Can I use MonkeyLearn MCP to see if my reviews are positive?** Yes, it lets you run sentiment analysis on any text you provide. Your agent can process a list of reviews and tell you the overall mood and specific highlights. **How do I see what models I have in MonkeyLearn?** You can ask your agent to list all your classifiers. It will show you every model in your account, like sentiment analysis or topic detection, so you can pick the right one. **Can this Connector help me pull specific data from a paragraph?** Definitely. You can use it to extract keywords, dates, or entities from raw text. Your agent will return a clean list of the data points you asked for. **Is MonkeyLearn MCP good for tracking my API usage?** Yes, you can ask the agent to show your recent activity. It will pull the latest logs from your account so you can see how many calls you've made and which models you're using most. **Can I see how my models are organized?** You can ask your agent to show your tag trees. It'll pull the hierarchy from your account so you can see exactly how your data is being categorized. **Does MonkeyLearn MCP work with my current account?** Yes, it connects directly to your existing MonkeyLearn account using your API key. You keep all your models and data, but gain a new way to interact with them. **Where do I find my MonkeyLearn API Key?** Log in to MonkeyLearn and go to your API Settings page. You'll find your personal API Key there. **Can I use custom models I've trained myself?** Yes! The `classify_text` and `extract_text` tools work with both pre-trained models and any custom models you have created in your account. Just provide the specific Model ID. **What is a Pipeline in MonkeyLearn?** Pipelines allow you to chain multiple processing steps together (e.g., classification followed by extraction). You can use the `list_pipelines` tool to see what's available in your account. **Can I classify text by sentiment or topic?** Yes. Point to any classifier model ID and pass text to get classification results with confidence scores. **How does MonkeyLearn authentication work?** MonkeyLearn uses `Authorization: Token {API_KEY}` header against `api.monkeylearn.com/v3`. **Can I extract named entities from text?** Yes. Use an extractor model to pull keywords, people names, organizations, locations, and more from raw text.