{"slug": "appsignal-mcp-server-get-started-in-your-ide", "title": "AppSignal MCP Server: Get Started in your IDE", "summary": "AppSignal has launched a Model Context Protocol (MCP) server that lets AI coding agents in Cursor, Claude Code, VS Code with GitHub Copilot, and Zed directly access production monitoring data, enabling them to investigate errors, query metrics, manage dashboards, and document incidents from within the IDE. The MCP server connects via a public endpoint at https://appsignal.com/api/mcp using an AppSignal MCP token, eliminating the previous need for a Docker container, and supports OAuth authentication across supported editors.", "body_md": "Cursor, Claude, and their fellow tools are great when they are speaking code, but once that code hits production, they are not exactly native. However, if your code is monitored by [AppSignal](https://appsignal.com/), an MCP server can bridge that gap and allow agents to poke around the production.\n\n**TL;DR** Adding your AI agent into the monitoring loop gives it direct access to the context from monitoring data. That means you can transition from knowing that there is a bug to having that bug-fix deployed, all in your editor. In this guide, I will quickly introduce you to [AppSignal’s MCP server](https://docs.appsignal.com/mcp.html) and show you how to set it up in your favorite IDE in under five minutes. Stroopwafels on us! 🧇\n\nWhat Is MCP?\n\n[Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) is an open standard that lets AI agents interact with external tools and data sources. It may feel like an API, but really, it gives AI systems a common way to connect with external tools and data sources. Kind of like a USB-C!\n\n[AppSignal’s MCP server](https://docs.appsignal.com/mcp.html) implements several tools across seven areas:\n\nWhat You Can Do With AppSignal’s MCP\n\nOnce you are connected to the MCP server, your AI agent can:\n\n**Investigate and triage errors**: The agent can list open incidents, pull stack traces, bulk-update states, assign team members, and more.** Review anomaly alerts**: You can browse open anomaly incidents, check which triggers are configured for a specific metric, and see alert history.**Query metrics**: The agent lets you discover available metrics and pull timeseries data.** Manage dashboards**: You can create new dashboards and charts from a prompt.** Document investigations**: Your team can add notes to incidents so that everyone has the full context.\n\nPrerequisites\n\nBefore your agent starts communicating with AppSignal, you need:\n\n[AppSignal account with an app](https://appsignal.com/users/sign_up)- AppSignal MCP token (you can generate one from\n)**Account Settings > MCP Tokens** - Preferred IDE of your choice (\n[Cursor](https://cursor.com),[Claude Code](https://claude.com/product/claude-code),[VS Code with GitHub Copilot](https://github.com/features/copilot/ai-code-editor), or[Zed](https://zed.dev))\n\n💡 Tokens have configurable permissions per toolset. By default, you get\n\n`write`\n\naccess to exceptions and dashboards +`read`\n\naccess to app discovery. You can adjust as necessary. ✨\n\nSetup Options\n\nPreviously, if you wanted to connect an AI agent to AppSignal, you had to have a Docker container running. And while this worked, it just added unnecessary overhead.\n\nAppSignal’s MCP public endpoint sits at [ https://appsignal.com/api/mcp](https://appsignal.com/api/mcp). This approach cuts out all the extra steps: just point your agent, authenticate with a token, and you’re good to go.\n\nThe Docker image is still available if you need a local MCP server, but for most cases, the public endpoint will do just fine.\n\nAgent Setup with a Public Endpoint (Recommended)\n\n💡 OAuth support is now available across all our supported editors. If the OAuth tab doesn’t work for your editor, just switch to the Bearer token tab and let us know in our\n\n[Discord community]. We can use your feedback to tighten these instructions. ✨\n\nClaude Code\n\n*Tabbed code from https://docs.appsignal.com/mcp.html*\n\nCursor\n\nAdd this to your Cursor MCP configuration (`~/.cursor/mcp.json`\n\n):\n\n*Tabbed code from https://docs.appsignal.com/mcp.html*\n\nSee [Cursor's MCP docs](https://cursor.com/docs/mcp) for more on managing MCP servers.\n\nVS Code with GitHub Copilot\n\nAdd the code below to `.vscode/mcp.json`\n\nin your project or your user-level settings ([VS Code MCP docs](https://code.visualstudio.com/docs/copilot/chat/mcp-servers)):\n\n*Tabbed code from https://docs.appsignal.com/mcp.html*\n\n🚧\n\nNote for GitHub Copilot organization accounts:Make sure MCP servers are enabled atOrganization Settings > Copilot > Policies > MCP servers in Copilot. 🚧\n\nZed\n\nOpen your Zed settings file and add the `context_servers`\n\nsection ([Zed MCP docs](https://zed.dev/docs/ai/mcp)):\n\n*Tabbed code from https://docs.appsignal.com/mcp.html*\n\nAgent Setup with Docker (Local Server)\n\nThe Docker image is available on [GitHub](https://github.com/appsignal/appsignal-mcp) for setups that require a local MCP server. Use your AppSignal API key (not your MCP token) for Docker-based setups.\n\nClaude Desktop\n\nEdit `~/Library/Application Support/Claude/claude_desktop_config.json`\n\n:\n\nYou can find this by navigating to your **Profile > Settings > Developer** and then pressing **Edit Config**.\n\nClaude Code\n\nCursor / Windsurf\n\nFor Cursor use `~/.cursor/mcp.json`\n\nFor Windsurf use `~/.codeium/windsurf/mcp_config.json`\n\nZed\n\nOpen your Zed settings file and add the `context_servers`\n\nsection:\n\nVS Code with GitHub Copilot\n\nAdd this config to your `.vscode/mcp.json`\n\nsettings:\n\nVerify That Everything Works\n\nOpen a conversation with your AI agent and ask:\n\nWhat apps do I have in AppSignal?\n\nIf connected correctly, the agent will return your app list. However, if it responds with generic advice instead of actual data or states that it cannot find necessary tools, revisit your configuration. The most common cause is a malformed token header or a missing Bearer prefix.\n\nYour First Investigation\n\nWith the AppSignal MCP server connected, you can now try a real end-to-end workflow:\n\n**Step 1: Check current status**\n\nAre there any open incidents in my production app?\n\nThe agent queries all open incidents scoped to your production environment and returns a summary list.\n\n**Step 2: Dig into an error**\n\nShow me the stack trace for the most recent Payment Failed error.\n\nThe agent pulls the full incident detail for the most recent matching error. If the same error has multiple samples, it can surface the most recent one. That way, you’ll be looking at the freshest occurrence, not a stale one from last week.\n\n**Step 3: Correlate with deploys**\n\nWhen was the last deploy? Did error rates change after it?\n\nThe agent checks your deploy markers and cross-references them against error rate data around the same time window.\n\n**Step 4: Document what you find**\n\nAdd a note to that incident that we're investigating a timeout in the payment gateway.\n\nThe agent writes a timestamped note and attaches it directly to the incident in AppSignal. Anyone on the team who opens the incident gets the context immediately.\n\n**Step 5: Update the incident state**\n\nMark that incident as acknowledged and assign it to me.\n\nThe agent updates the incident state to **acknowledged** and assigns it to your AppSignal user. It will chain the underlying tools on its own. You don’t even need to know which tools exist. 😉\n\nSee the full reference in the [AppSignal MCP Tool Reference](https://docs.appsignal.com/mcp/reference.html).\n\nTips for Productivity and Effective Use\n\nTo have your MCP be as effective as possible, consider these few productivity tips:\n\n**Be specific about time ranges**: “Errors in the last hour” will give better results than “recent errors.”** Name your apps clearly**: The agent uses app names to scope queries. Ambiguous names produce ambiguous results, it’s just simple math.** Iteration over one-shots**: Start broad (”what is happening in prod?”), and then narrow it down (”tell me more about why we have an outage in the USA”)**Use investigation notes**: Let the agent add notes directly to incidents so that your team has context without a separate Slack thread.** Combine with code context**: I like this one! In Cursor, Claude or your IDE of choice, ask the agent to look at your source code and monitoring data together.\n\nWrap Up and Next Steps\n\nGetting your agent to talk to AppSignal takes less than five minutes. Once connected, your agent can query everything AppSignal’s dashboard would conventionally offer, but at a speed of communication (in plain English as well!).\n\nGenerate your MCP token in the [Account Settings](https://appsignal.com/users/mcp_tokens), and connect it to your favorite editor.\n\nIf you don’t have an AppSignal account yet, [start a free 30-day trial](https://appsignal.com/users/sign_up) (no credit card required).\n\nFrequently Asked Questions (FAQ)\n\nDo I need Docker to use AppSignal MCP?\n\nNo, the public endpoint works for all supported editors without Docker. Docker is only necessary if your environment restricts outbound traffic to the public endpoint.\n\nWhat is the difference between an MCP token and an API key?\n\nMCP tokens are generated separately in **Account Settings** and have per-toolset read/write permissions. API keys are used for the Docker setup and grant broader access. Use MCP tokens for the public endpoint.\n\nCan I limit what my AI agent can access?\n\nYes. When generating an MCP token, configure each toolset (`exceptions`\n\n, `anomalies`\n\n, `metrics`\n\n, `dashboards`\n\n, `app_discovery`\n\n) as `read`\n\n, `write`\n\n, or disabled. You can also scope a token to specific apps.\n\nDoes this work with Windsurf?\n\nIt absolutely does.\n\nThe agent returns generic advice instead of my AppSignal data? What happened?\n\nIt’s almost always a token header issue. Double-check that the header is `Authorization: Bearer your-mcp-token`\n\nwith the `Bearer`\n\nprefix and that you're using an MCP token (not your API key) for the public endpoint setup.\n\nPublished\n\n## Wondering what you can do next?\n\n[Try out AppSignal with a 30-day free trial](https://appsignal.com/users/sign_up).[Reach out to our support team with any feedback or questions](mailto:support@appsignal.com).\n\n- Share this article on social media\n\n## Dejan Lukić\n\nOur guest author Dejan is an electronics and backend engineer, who is pursuing entrepreneurship with SaaS and service-based agencies and is passionate about content creation.\n\n[All articles by Dejan Lukić](/authors/dejan-lukić.html)\n\nBecome our next author!\n\n[Find out more](/write-for-us.html)\n\n## AppSignal monitors your apps\n\nAppSignal provides insights for Ruby, Rails, Elixir, Phoenix, Node.js, Express and many other frameworks and libraries. We are located in beautiful Amsterdam. We love [stroopwafels](https://www.appsignal.com/waffles). If you do too, [let us know](mailto:contact@appsignal.com). We might send you some!\n\n[Discover AppSignal](https://www.appsignal.com)", "url": "https://wpnews.pro/news/appsignal-mcp-server-get-started-in-your-ide", "canonical_source": "https://blog.appsignal.com/2026/07/29/appsignal-mcp-server-get-started-in-your-ide.html", "published_at": "2026-07-29 00:00:00+00:00", "updated_at": "2026-07-29 11:30:43.083666+00:00", "lang": "en", "topics": ["developer-tools", "ai-agents", "ai-tools", "artificial-intelligence"], "entities": ["AppSignal", "Model Context Protocol", "Cursor", "Claude Code", "VS Code", "GitHub Copilot", "Zed", "Discord"], "alternates": {"html": "https://wpnews.pro/news/appsignal-mcp-server-get-started-in-your-ide", "markdown": "https://wpnews.pro/news/appsignal-mcp-server-get-started-in-your-ide.md", "text": "https://wpnews.pro/news/appsignal-mcp-server-get-started-in-your-ide.txt", "jsonld": "https://wpnews.pro/news/appsignal-mcp-server-get-started-in-your-ide.jsonld"}}