This service provides a Model Context Provider for interacting with Sentry's API.
While this service is maintained by Sentry, it is very much still a proof-of-concept as the protocol is still in development (as is our own thinking around its usage).
{ "mcpServers": { "sentry": { "command": "npx", "args": [ "-y", "mcp-remote", "https://sentry.cool/sse" ] } } }
Or if you just need the server itself (requires an OAuth compatible client):
https://sentry.cool/sse
With Cursor
- Cmd + Shift + J to open Cursor Settings.
- Select MCP.
- Select Add new global MCP server.
With Windsurf
- Open Windsurf Settings.
- Under Cascade, you'll find Model Context Provider Servers.
- Select Add Server.
Note: Windsurf requires an enterprise account to utilize MCP. 😕
With VSCode
- CMD + P
- Select MCP: Add Server...
- Select Command (stdio).
- Enter
npx mcp-remote https://sentry.cool/sse
- Enter
Sentry
- Select User settings or Workspace settings (to limit to specific project)
Note: MCP is supported in VSCode 1.99 and above.
With Zed
- CMD + , to open Zed settings.
{ "context_servers": { "sentry": { "command": { "command": "npx", "args": [ "-y", "mcp-remote", "https://sentry.cool/sse" ] } }, "settings": {} } }
Workflows
Here's a few sample workflows (prompts) that we've tried to design around within the provider:
Check Sentry for errors in
@file.tsx
and propose solutions.Diagnose issue
ISSUE_URL
in Sentry and propose solutions.Create a new project in Sentry for
service-name
and setup local instrumentation using it.
Available Tools
Note: Any tool that takes an organization_slug
parameter will try to infer a default organization, otherwise you should mention it in the prompt.
list_organizations
List all organizations that the user has access to in Sentry.
list_teams
List all teams in an organization in Sentry.
organizationSlug
- The organization's slug. This will default to the first org you have access to.
list_projects
Retrieve a list of projects in Sentry.
organizationSlug
- The organization's slug. This will default to the first org you have access to.
get_error_details
Retrieve error details from Sentry for a specific Issue ID, including the stacktrace and error message. Either issueId or issueUrl MUST be provided.
organizationSlug
- The organization's slug. This will default to the first org you have access to.
issueId
- The Issue ID. e.g. `PROJECT-1Z43`
issueUrl
- The URL of the issue to retrieve details for.
search_errors
Search for errors in Sentry.
organizationSlug
- The organization's slug. This will default to the first org you have access to.
filename
- The filename to search for errors in. This is a suffix based search, so only using the filename or the direct parent folder of the file. The parent folder is preferred when the filename is in a subfolder or a common filename.
query
- The search query to apply. Use the `help` tool to get more information about the query syntax rather than guessing.
sortBy
- Sort the results either by the last time they occurred or the count of occurrences.
create_team
Create a new team in Sentry.
organizationSlug
- The organization's slug. This will default to the first org you have access to.
name
- The name of the team to create.
create_project
Create a new project in Sentry, giving you access to a new SENTRY_DSN.
organizationSlug
- The organization's slug. This will default to the first org you have access to.
teamSlug
- The team's slug. This will default to the first team you have access to.
name
- The name of the project to create. Typically this is commonly the name of the repository or service. It is only used as a visual label in Sentry.
platform
- The platform for the project (e.g., python, javascript, react, etc.)
help
Get information to help you better work with Sentry.
subject
- The subject to get help with.