Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP GlitchTip Show me all unresolved errors from GlitchTip"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that integrates GlitchTip error monitoring with AI assistants like Claude. This allows AI to analyze and help resolve errors from your GlitchTip instance.
This MCP server enables AI assistants to:
Fetch and analyze current issues from your GlitchTip instance
Get detailed error context including stack traces, user data, and breadcrumbs
Help debug and suggest solutions based on error patterns
User: "Check GlitchTip for any payment-related errors"
AI Assistant:
- Fetches all unresolved issues from GlitchTip
- Identifies payment component errors
- Analyzes stack traces and error patterns
- Suggests specific fixes based on the error contextRelated MCP server: Bugsink MCP Server
You'll need:
Authentication: Either an API token (recommended) or Session ID Cookie
Organization Slug: Your organization identifier in GlitchTip
Base URL (optional): Your GlitchTip instance URL if self-hosted
Option 1: API Token (Recommended)
Log in to your GlitchTip instance
Go to /profile/auth-tokens
Create a new API token with appropriate permissions
Copy the token for use as GLITCHTIP_TOKEN
Option 2: Session ID
Log in to your GlitchTip instance
Open browser developer tools (F12)
Go to Application/Storage > Cookies
Find the sessionid cookie value
Copy this value for use as GLITCHTIP_SESSION_ID
Create a .mcp.json file in your project root:
{
"mcpServers": {
"glitchtip": {
"command": "npx",
"args": ["-y", "mcp-glitchtip"],
"env": {
"GLITCHTIP_TOKEN": "your-api-token-here",
"GLITCHTIP_ORGANIZATION": "your-org-slug",
"GLITCHTIP_BASE_URL": "https://app.glitchtip.com"
}
}
}
}Note: Add .mcp.json to your .gitignore to keep credentials secure:
echo ".mcp.json" >> .gitignoreWhen you open your project folder in Claude Desktop, it will automatically detect the .mcp.json configuration and connect to your GlitchTip instance.
Environment Variable | Required | Description | Default |
| Yes* | Your GlitchTip API token (recommended) | - |
| Yes* | Your GlitchTip session cookie | - |
| Yes | Organization slug from GlitchTip URL | - |
| No | GlitchTip instance URL |
|
*Either GLITCHTIP_TOKEN or GLITCHTIP_SESSION_ID is required. If both are provided, GLITCHTIP_TOKEN takes priority.
If you're using a self-hosted GlitchTip instance, update the GLITCHTIP_BASE_URL:
"GLITCHTIP_BASE_URL": "https://glitchtip.your-domain.com"glitchtip_issuesFetches all issues from GlitchTip (unresolved by default).
Usage: "Show me all GlitchTip errors"
glitchtip_latest_eventGets the most recent event for a specific issue with full error context.
Parameters:
issueId: The issue ID to get details for
Usage: "Get details for GlitchTip issue #123"
glitchtip://issuesA resource endpoint that provides all current issues in JSON format.
User: "Check GlitchTip for recent 500 errors"
AI: [Fetches issues] I found 3 recent 500 errors:
1. DatabaseConnectionError in /api/users
2. TimeoutError in payment processing
3. ValidationError in checkout flow
User: "Show me details about the payment timeout"
AI: [Gets latest event] The TimeoutError occurs when...
[Provides stack trace analysis and suggested fixes]User: "What are the most frequent errors in GlitchTip?"
AI: [Analyzes issue counts] The top errors by frequency are:
1. CORS policy errors (145 occurrences)
2. Missing authentication token (89 occurrences)
3. Rate limit exceeded (67 occurrences)git clone https://github.com/coffebar/mcp-glitchtip.git
cd mcp-glitchtip
npm install
npm run buildnpm run watch # Auto-rebuild on changesnpm run inspectorSet the required environment variables before running the inspector:
export GLITCHTIP_TOKEN="your-api-token"
# OR export GLITCHTIP_SESSION_ID="your-session-id"
export GLITCHTIP_ORGANIZATION="your-org"
npm run inspectorIf you see "Authentication failed. Check your token or session ID":
If using a token: Verify it's valid and has appropriate permissions
If using a session ID: Your session may have expired - get a new session ID from GlitchTip
Verify you're using the correct organization slug
Check if your GlitchTip instance requires additional authentication headers
If you see "Failed to connect to GlitchTip":
Verify your GLITCHTIP_BASE_URL is correct
Check if you're behind a proxy or firewall
Ensure your GlitchTip instance is accessible from your network
If the tool returns empty results:
Verify there are actually issues in your GlitchTip project
Check if your organization slug is correct
Ensure your session has permission to view the issues
Never commit .mcp.json to version control - it contains sensitive credentials
For team usage, each developer should use their own API token or session ID
Contributions are welcome! Please:
Fork the repository
Create a feature branch
Make your changes
Add tests if applicable
Submit a pull request
MIT License - see LICENSE file for details.
Issues: GitHub Issues
Documentation: GitHub README
GlitchTip Docs: GlitchTip Documentation
Get all issues from GlitchTip
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only says 'Get all issues' without disclosing pagination, authentication needs, or whether it returns a list or stream. Minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no wasted words. Efficiently states the purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description should detail the return format or behavior. It does not, leaving the agent uncertain about the output structure or limitations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Baseline for 0 parameters is 4, but the description lacks details on what 'all issues' entails (e.g., scope, filters). Thus a slight deduction to 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get all issues from GlitchTip' provides a clear verb and resource, and distinguishes it from the sibling glitchtip_latest_event which implies a single event retrieval.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus the sibling. There is no mention of alternatives or context where one is preferred over the other.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the latest event for a specific issue
| Name | Required | Description | Default |
|---|---|---|---|
| issueId | Yes | The issue ID to get the latest event for |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must carry burden. It only states the action without disclosing behavioral traits such as authentication needs, read-only nature, or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise and front-loaded, but it is overly brief and omits potentially useful context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description is minimally adequate but lacks details about what constitutes an 'event' or prerequisites.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the single parameter, so baseline is 3. Description adds no extra meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the verb 'Get' and resource 'latest event for a specific issue', distinguishing it from the sibling tool 'glitchtip_issues' which likely lists issues.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like glitchtip_issues. Lacks any when-not or context for invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The two tools are clearly distinct: one lists all issues, the other retrieves the latest event for a specific issue. No overlap.
Both tools follow a consistent snake_case pattern with the 'glitchtip_' prefix and a clear noun phrase.
With only 2 tools, the server is minimal. While not extreme, it feels thin for a typical issue-tracking domain.
Only read operations are available (list issues, get latest event). Missing create, update, delete, and other event retrieval, leaving significant gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Direct access to Cypress tests results and accessibility reports in your AI workflow.
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
Connect AI assistants to Xitoring monitoring: servers, uptime, incidents, metrics, SSL, and alerts.
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/coffebar/mcp-glitchtip'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
