Connect the AppSignal MCP server to Unblocked to give AI agents live error and performance context

Fixing an AppSignal exception usually means copying a stack trace out of the incident page, checking whether the action has been getting slower, and searching logs for the request that failed. A coding agent sees only the code in front of it. AppSignal’s MCP server exposes exception incidents, performance traces, logs, metrics, and anomaly alerts to AI agents, and Unblocked connects to it once so every agent can ask about your apps without its own AppSignal setup.

This is a third-party MCP server: AppSignal hosts and maintains it, and Unblocked connects to it as a verified MCP server. Nothing is ingested or indexed — Unblocked calls the read-only tools you allow when a question needs them, so an incident’s state, a slow action’s trace, or a log query comes from AppSignal as it is now.

Wiring AppSignal’s MCP server straight into an agent gives it incidents and traces. Unblocked’s Context Engine reasons across those results and your other sources — following an exception incident to the deploy marker it first appeared after, the pull request in that deploy, and the Slack thread where a customer reported it — and returns one cited answer.

Once connected, any MCP-compatible coding agent — Claude Code, Cursor, Devin, GitHub Copilot, Codex — reaches AppSignal context through a single Unblocked MCP server connection.

What you get

• Live exceptions and performance — Agents list and search exception incidents, inspect their details and notes, and pull performance and error traces with span trees from your AppSignal apps as they are now.
• Logs, metrics, and anomaly alerts — Agents query log lines, fetch metric timeseries, and check open anomaly detection alerts, so a fix is grounded in what production is actually doing.
• Read-only, tool-level control — Tools that change incident state, edit notes, or manage triggers, monitors, and dashboards are never offered. You choose which read-only AppSignal tools Unblocked may call from Settings → Data Sources.
• Context Engine reasoning — AppSignal results are reconciled with your code, pull requests, tickets, and conversations, so an exception leads to the change that introduced it — with citations.

Prerequisites

• An Unblocked account (free to start).
• An AppSignal account with access to the apps you want agents to query, and permission to authorize the connection to AppSignal.
• An MCP-compatible coding agent (Claude Code, Cursor, Devin, etc.) to use the context in your editor.

Step 1: Connect AppSignal to Unblocked

1. In Unblocked, go to Settings → Data Sources → Connect another data source, and under Incident Management select AppSignal.
2. The AppSignal MCP server URL is filled in for you. Choose OAuth, click Connect, and sign in to AppSignal to authorize Unblocked.
3. Once Unblocked discovers the server’s tools, select the read-only tools it may use and click Save Settings.

Step 2: Install the Unblocked MCP server

On macOS or Linux, one command auto-detects and configures the supported agents on your machine:

On Windows, or when you prefer remote MCP, add the server manually using the configuration below, or follow the manual install guide .

claude mcp add -s user --transport http unblocked https://getunblocked.com/api/mcpsse

{
  "mcpServers": {
    "unblocked": {
      "url": "https://getunblocked.com/api/mcpsse"
    }
  }
}

https://getunblocked.com/api/mcpsse

AppSignal hosts and maintains this MCP server. Unblocked calls only the read-only tools you select, at the moment a question needs them:

• get_exception_incidentsLists and searches exception incidents and returns the matching incidents.
• get_incidentReturns the details of one incident, including its notes.
• get_performanceReturns performance traces and, for OpenTelemetry apps, a ranked list of slow actions.
• get_tracesLists performance or error traces and returns their span trees and span details.
• get_log_linesQueries log lines using AppSignal’s expression syntax and returns the matching lines.
• get_metrics_timeseriesReturns point-by-point data for a metric over a time range.

To give Claude Code, Cursor, GitHub Copilot, Codex, or another MCP-compatible AI coding agent access to AppSignal context, connect AppSignal to Unblocked and add the single Unblocked MCP server to your agent.

Unblocked acts as the MCP context layer for your AppSignal data, searching errors, performance, and metrics alongside your other connected sources and returning cited results through these tools:

• context_researchResearches a question across your connected sources and calls the AppSignal tools you selected when exceptions, traces, logs, or metrics are relevant, returning a synthesized answer with citations.
• context_get_urlsFetches the full content behind URLs your agent encounters across connected sources — Jira, Linear, Notion, Confluence, Slack, GitHub, and more.

Questions you (or your agent) can ask Unblocked about your AppSignal data:

• Which new exception incidents appeared after the last deploy, and which pull request in that deploy is the likely cause?
• Why is the orders#create action slow this week, and has anyone changed that controller recently?
• What do the logs around this AppSignal incident show, and is there a Linear issue or Slack thread about it?
• Is there an open anomaly alert on the background job queue, and what did the team decide last time it fired?