# Axiom MCP for AI Agents AI Agent Connect > Axiom MCP. Manage logs and observability data via Axiom. Ingest data, run APL queries, and manage datasets or monitors directly from any AI agent. ## Overview - **Category:** data-analytics - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_e61fohuL5myEGCp75T44EWD2aXWWhlKb6QKmFZpL/ai-agent-connect - **Tags:** telemetry, log-analysis, real-time-monitoring, data-ingestion, apl-queries, cloud-observability ## Description Axiom is an Connector that lets you manage your observability and log data through a natural conversation with your agent. You can ask it to run complex APL queries to find specific errors, check your monitor statuses, or organize your datasets without ever leaving your chat interface. It handles the heavy lifting of ingesting JSON or CSV files and keeping your infrastructure telemetry organized. Instead of manually clicking through multiple dashboards to find a single trace ID, you can just tell your agent what you need. It can check if your production monitors are firing, update existing alerts, or create new ones on the fly. Because Vinkius hosts this Connector, you can connect it to your existing workflow and start talking to your data instead of just looking at it. It turns your agent into a hands-on operator for your entire observability stack. You get the ability to visualize trends and mark significant system events using annotations, all while keeping your workspace clean. This means you spend less time navigating menus and more time actually solving production issues. It is built for people who need to move fast. Whether you're trying to figure out why a deployment failed or you're building a new dashboard to track system health, this Connector puts the power of your Axiom account directly into your agent's hands. You can manage your organization details, retrieve user info, and keep your API tokens organized, ensuring your agent always has the right permissions to do its job. It's about making your observability data actionable without the overhead of a manual UI. ## Tools ### create_annotation This tool creates a new annotation. Use it to mark a specific point in time on your logs to highlight an incident. ### create_dashboard This tool creates a new dashboard. It lets your agent build a new visualization for you on the fly. ### create_dataset This tool creates a new dataset. Use it to organize new telemetry streams into their own category. ### create_monitor This tool creates a new monitor. It lets you set up new alerts for system performance or errors. ### create_notifier This tool creates a new notifier. Use it to set up new ways to receive alerts about your system. ### delete_annotation This tool deletes an annotation. Use it to remove markers that are no longer relevant to your logs. ### delete_dashboard This tool deletes a dashboard. Use it to clean up old or unnecessary visualizations from your account. ### delete_dataset This tool deletes a dataset. Use it to remove telemetry groups that you no longer need to track. ### get_annotation This tool retrieves a specific annotation by ID. It helps you see the details of a specific marker on your logs. ### get_user This tool retrieves a specific user by ID. It helps you verify user details within your organization. ### ingest_data This tool ingests data into an Axiom dataset. It allows your agent to upload JSON or CSV files for you. ### list_annotations This tool lists all annotations. It shows you every marker currently on your logs to help you see past events at a glance. ### list_dashboards This tool lists all dashboards. Use it to see all the different visualizations you have created. ### list_datasets This tool lists all datasets. It helps you see all the different telemetry groups available in your account. ### list_monitors This tool lists all monitors. Use it to see every alert currently running in your environment. ### list_notifiers This tool lists all notifiers. It shows you all the different ways your system sends out alerts. ### list_users This tool lists all users. Use it to see who has access to your Axiom data. ### delete_monitor This tool deletes a monitor. Use it to remove alerts that are no longer useful for your workflow. ### delete_notifier This tool deletes a notifier. Use it to remove old alert delivery methods from your account. ### list_tokens This tool lists all API tokens. Use it to see which keys are active for your account and manage your access. ### get_dashboard This tool retrieves a specific dashboard by UID. It pulls up a specific set of visualizations so you can see a particular view. ### get_dataset This tool retrieves a specific dataset by ID. It helps you quickly access a specific group of telemetry data. ### get_monitor This tool retrieves a specific monitor by ID. Use it to check the current status of a specific system alert. ### get_notifier This tool retrieves a specific notifier by ID. It allows you to see how specific alerts are being delivered. ### get_org This tool retrieves an organization by ID. It provides the high level details of your Axiom account structure. ### run_query This tool runs an APL query against Axiom data. It lets your agent find specific logs or summarize metrics for you. ### update_annotation This tool updates an existing annotation. Use it to modify the details of a marker already on your logs. ### update_dashboard This tool updates an existing dashboard. It lets your agent modify the visualizations you already have. ### update_dataset This tool updates an existing dataset. Use it to modify the properties of a specific telemetry group. ### update_monitor This tool updates an existing monitor. Use it to change the thresholds or frequency of your alerts. ### update_notifier This tool updates an existing notifier. Use it to change how your alerts are delivered to your team. ## Prompt Examples **Prompt:** ``` List all my available Axiom datasets. ``` **Response:** ``` I've retrieved your datasets. You have 3 active datasets: | Dataset Name | ID | | :--- | :--- | | **production-logs** | ds_123 | | **staging-metrics** | ds_456 | | **security-audit** | ds_789 | Would you like to see more details on any of these? ``` **Prompt:** ``` Run an APL query to count errors in 'production-logs' from the last 24 hours. ``` **Response:** ``` Executing query: `['production-logs'] | where level == 'error' | summarize count()`... **Results:** - **Error Count:** 142 - **Timeframe:** Last 24 hours - **Dataset:** production-logs I found 142 error events in the specified timeframe. Would you like to see the specific error messages? ``` **Prompt:** ``` Create a new monitor named 'High Latency' that checks for response times over 500ms. ``` **Response:** ``` I've created the **High Latency** monitor for you. **Monitor Details:** - **Name:** High Latency - **Condition:** Response times > 500ms - **Frequency:** Every 5 minutes - **Monitor ID:** mon_abc123 I'll let you know if this threshold is breached. ``` ## Capabilities ### Run APL queries This tool lets you ask your agent to filter and summarize logs using Axiom's processing language. ### Ingest new data This tool lets you send JSON, NDJSON, or CSV files directly into your Axiom datasets. ### Manage monitors This tool lets you create, update, or delete system monitors and notifiers through natural language. ### Build dashboards This tool lets you generate new dashboards or modify existing ones to track specific metrics. ### Organize datasets This tool lets you list, create, and delete datasets to keep your telemetry data structured. ### Manage annotations This tool lets you add or remove markers on your logs to highlight significant system events. ## Use Cases ### Finding a specific error An engineer asks the agent to find all 'error' level logs in the production dataset from the last hour using run_query. ### Setting up a new alert An SRE asks the agent to create a monitor using create_monitor for response times over 500ms. ### Organizing telemetry A data analyst asks the agent to list all datasets and then create a new one for security audits using create_dataset. ### Reviewing dashboards A manager asks the agent to get a specific dashboard using get_dashboard to check the current status of the staging environment. ## Benefits - Faster debugging with run_query. You can get specific log results in seconds by asking your agent to execute APL queries. - Automated monitoring with create_monitor. Set up new alerts for high latency or error spikes without leaving your chat. - Easier data organization with create_dataset. Keep your telemetry clean by having your agent manage your dataset structure. - Instant dashboarding with create_dashboard. Build and update visualizations on the fly to see what matters most. - Streamlined data ingestion with ingest_data. Move JSON and CSV files into your platform without manual uploads. - Better incident tracking with create_annotation. Add markers to your logs so your team knows exactly what happened and when. ## How It Works Axiom is the tool that lets you manage your entire observability stack through a simple chat interface. 1. Get your Axiom API token and Organization ID from your account settings. 2. Add the Connector to your AI client and provide your credentials. 3. Ask your agent to query logs, create monitors, or manage your datasets. ## Frequently Asked Questions **How can I use the Axiom MCP to manage my logs?** You can use the Axiom MCP to query logs, create monitors, and manage datasets through a natural conversation with your AI agent. It removes the need to navigate the Axiom web console for every routine task. **Can the Axiom MCP run APL queries for me?** Yes, your agent can execute complex APL queries to filter and summarize your log data. Just tell your agent what you want to find, and it will handle the query logic for you. **Is the Axiom MCP good for DevOps teams?** It is ideal for DevOps and SRE teams who need to quickly check monitor statuses, manage alerts, and debug production issues without switching between multiple tools. **Can I ingest data into Axiom using this Connector?** Yes, the Connector allows your agent to ingest JSON, NDJSON, and CSV files directly into your Axiom datasets, making it much faster to analyze new data batches. **Does the Axiom MCP support dashboard management?** It does. You can ask your agent to list, create, or update dashboards, allowing you to manage your visualizations through a simple chat interface. **How do I set up the Axiom MCP with my account?** You just need to provide your Axiom API token and optional Organization ID to your AI client. From there, you can start managing your observability data immediately. **Can I run complex log analysis using Axiom Processing Language (APL)?** Yes! Use the `run_query` tool to execute any APL string. You can specify `start_time` and `end_time` to filter your data and get precise analytical results directly in the chat. **How do I send new log data to my Axiom datasets?** You can use the `ingest_data` tool. Simply provide the `dataset_name`, the data `payload`, and the `content_type` (JSON, NDJSON, or CSV) to stream data into your Axiom account. **Is it possible to manage system monitors and alerts through this integration?** Absolutely. You have access to a full suite of tools including `list_monitors`, `create_monitor`, and `update_monitor` to configure threshold or anomaly detection alerts based on your APL queries.