# Vigilon

> Vigilon is an MCP server for developer tools. Let a coding agent read production errors, traces and job runs from Vigilon. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free trial
- **Platforms:** API
- **Website:** https://vigilon.io/docs/mcp
- **MCP Registry name:** io.vigilon/mcp
- **Categories:** developer tools
- **Listing updated:** 2026-11-14

## About

Vigilon's server gives an agent the same telemetry you see in the dashboard, so it can investigate a failure while working in your repo. Rather than pasting one stack trace, the agent reads the whole error group: how often it happens, when it started, whether it returned after being resolved, which endpoints or jobs it hits, and the trace of a failing request with its database queries and outgoing calls. After a fix ships it can check whether the group still occurs.

All tools are read-only and work inside your workspace. An agent cannot resolve or mute error groups and has no access to settings, users, API keys or billing. Without an environment named it uses the project's default, and without a time range it looks at the last 24 hours.

Limits are 120 requests a minute per user, shared across connected agents, with 50 rows a page. Stack traces over 20,000 characters and traces over 200 spans are shortened, with failed spans kept first. Insight tools need the Team or Pro plan.

## Features

- **Error group detail:** Shows counts, first and last seen, status and affected endpoints or jobs.
- **Occurrence samples:** Returns the exception type, message and stack trace of one occurrence.
- **Trace search:** Filters request traces by endpoint, method, errors or duration.
- **Failed requests:** Lists 5xx requests linked to their error group and trace.
- **Background job health:** Reports run counts, failure rate, duration and individual run errors.
- **Automatic insights:** Reads findings such as error spikes and slower endpoints, on Team and Pro plans.

## Good for

- Ask what started failing in production today
- Pull the stack trace for the newest error group
- Find which background jobs are failing and why
- Confirm a deployed fix stopped an error group
- Investigate a regressed error and propose a patch

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http mcp https://mcp.vigilon.io/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.vigilon.io/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.vigilon.io/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.vigilon.io/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://mcp.vigilon.io/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.vigilon.io/mcp"
    }
  }
}
```

## Tools

- `list_projects`: Lists the projects in your workspace.
- `get_project_overview`: Shows request volume, error rate and latency compared with the previous period.
- `list_error_groups`: Lists error groups with counts, timing and status.
- `get_error_group`: Returns one error group, what it affects and recent occurrences.
- `get_error_group_sample`: Returns the exception and stack trace of one occurrence.
- `search_traces`: Searches request traces by endpoint, method, errors or duration.
- `get_trace`: Returns one trace with spans, attributes and events.
- `list_failed_requests`: Lists requests that ended in a 5xx response.
- `list_jobs`: Lists background jobs with failure rate and health.
- `get_job_detail`: Returns one job compared with the previous period.
- `list_job_runs`: Lists the runs of one job.
- `list_insights`: Lists findings raised from telemetry.
- `get_insight`: Returns one insight with its numbers.

## FAQ

### Do I need an API key?

No. You add the URL to your client and sign in with your Vigilon account in the browser.

### Can the agent resolve or mute errors?

No. It can read but not change anything, and has no access to settings, users, API keys or billing.

### Which clients are supported?

Claude Code, Codex, VS Code with GitHub Copilot, Claude and ChatGPT.

### Why did a list come back empty?

The default range is the last 24 hours. Ask for a longer range and check the project receives telemetry in that environment.

### Is Vigilon free?

Vigilon is a paid product with a free trial.

### How do I add Vigilon to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://mcp.vigilon.io/mcp

### What are the best alternatives to Vigilon?

The closest alternatives to Vigilon are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/vigilon
