The Sentry MCP server provides seamless integration with Sentry.io, allowing you to retrieve and analyze error reports, stacktraces, and debugging information from your Sentry account directly through the Model Context Protocol.
With uv
, you don't need to install the package separately. Simply use uvx
to run it directly:
uvx mcp-server-sentry --auth-token YOUR_SENTRY_TOKEN
Alternatively, install the package via pip:
pip install mcp-server-sentry
After installation, run it as a script:
python -m mcp_server_sentry --auth-token YOUR_SENTRY_TOKEN
Add the MCP server to your claude_desktop_config.json
using one of these methods:
"mcpServers": {
"sentry": {
"command": "uvx",
"args": ["mcp-server-sentry", "--auth-token", "YOUR_SENTRY_TOKEN"]
}
}
"mcpServers": {
"sentry": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/sentry", "--auth-token", "YOUR_SENTRY_TOKEN"]
}
}
"mcpServers": {
"sentry": {
"command": "python",
"args": ["-m", "mcp_server_sentry", "--auth-token", "YOUR_SENTRY_TOKEN"]
}
}
For VS Code, add this configuration to your User Settings (JSON) or to .vscode/mcp.json
in your workspace:
{
"mcp": {
"inputs": [
{
"type": "promptString",
"id": "auth_token",
"description": "Sentry Auth Token",
"password": true
}
],
"servers": {
"sentry": {
"command": "uvx",
"args": ["mcp-server-sentry"],
"env": {
"SENTRY_AUTH_TOKEN": "${input:auth_token}"
}
}
}
}
}
{
"mcp": {
"inputs": [
{
"type": "promptString",
"id": "auth_token",
"description": "Sentry Auth Token",
"password": true
}
],
"servers": {
"sentry": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/sentry"],
"env": {
"SENTRY_AUTH_TOKEN": "${input:auth_token}"
}
}
}
}
}
Add to your Zed settings.json:
"context_servers": [
"mcp-server-sentry": {
"command": {
"path": "uvx",
"args": ["mcp-server-sentry", "--auth-token", "YOUR_SENTRY_TOKEN"]
}
}
],
"context_servers": {
"mcp-server-sentry": {
"command": "python",
"args": ["-m", "mcp_server_sentry", "--auth-token", "YOUR_SENTRY_TOKEN"]
}
},
This tool retrieves and analyzes a Sentry issue by ID or URL, providing:
Use the MCP inspector to debug the server:
npx @modelcontextprotocol/inspector uvx mcp-server-sentry --auth-token YOUR_SENTRY_TOKEN
For local development:
cd path/to/servers/src/sentry
npx @modelcontextprotocol/inspector uv run mcp-server-sentry --auth-token YOUR_SENTRY_TOKEN
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.