Server facts
Sentry MCP
Project
- Author
- getsentry
- Repository
- github.com/getsentry/sentry-mcp
- Website
- mcp.sentry.dev
- License
- Not specified
- Category
- Developer Tools
Tech
- Runtime / language
- node
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 754
- Last commit
- Data as of
Tags
- Debugging
- Issue Triage
- Observability
- Sentry
Overview
Sentry MCP connects coding assistants to the Sentry API with a deliberate emphasis on debugging and developer workflows. The project targets agents used with human oversight, including Cursor and Claude Code, rather than attempting to be a universal interface for every Sentry operation. Its available tools can locate organizations and projects, search grouped issues, inspect events, retrieve resources, and change issue assignments or status. Seer integration adds root-cause investigation and suggested code fixes when that capability is available in the connected Sentry deployment.
The repository supports a hosted remote service as well as a stdio package launched through npx. The README describes stdio as still evolving but useful for connecting to self-hosted Sentry. A host override selects a private deployment, and individual skills can be disabled when the target lacks features such as Seer. AI-assisted search requires a configured language-model provider; other tools remain usable without that provider. Supported provider choices include OpenAI, Azure OpenAI, Anthropic, and OpenRouter. For operations outside the direct tool list, catalog search and execution tools expose additional Sentry capabilities. Remote clients may authenticate through MCP OAuth or pass a Sentry token using the documented custom authorization scheme. Token lifetime remains the client's responsibility in that direct-token setup.
Install & configure
Requirements
- Node.js with npx
- Sentry user token
- LLM provider credentials for AI-powered search
npx @sentry/mcp-serverThis is the README stdio configuration. Required token scopes are event:write, project:write, team:read, org:read, team:write, and project:read. Remote access is also documented at https://mcp.sentry.dev/mcp. Use --host for self-hosted Sentry; unsupported skills can be disabled.
Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"sentry-mcp": {
"command": "npx",
"args": [
"@sentry/mcp-server"
],
"env": {
"SENTRY_ACCESS_TOKEN": "<Sentry user auth token with documented scopes>",
"EMBEDDED_AGENT_PROVIDER": "<Explicit LLM provider for AI-powered search>",
"OPENAI_API_KEY": "<OpenAI key if selecting OpenAI>"
}
}
}
}Config file · Project: .cursor/mcp.json
User: ~/.cursor/mcp.json
The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"sentry-mcp": {
"command": "npx",
"args": [
"@sentry/mcp-server"
],
"env": {
"SENTRY_ACCESS_TOKEN": "<Sentry user auth token with documented scopes>",
"EMBEDDED_AGENT_PROVIDER": "<Explicit LLM provider for AI-powered search>",
"OPENAI_API_KEY": "<OpenAI key if selecting OpenAI>"
}
}
}
}Config file · Workspace: .vscode/mcp.json
For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.
{
"servers": {
"sentry-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"@sentry/mcp-server"
],
"env": {
"SENTRY_ACCESS_TOKEN": "<Sentry user auth token with documented scopes>",
"EMBEDDED_AGENT_PROVIDER": "<Explicit LLM provider for AI-powered search>",
"OPENAI_API_KEY": "<OpenAI key if selecting OpenAI>"
}
}
}
}Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json
Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json
Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"sentry-mcp": {
"command": "npx",
"args": [
"@sentry/mcp-server"
],
"env": {
"SENTRY_ACCESS_TOKEN": "<Sentry user auth token with documented scopes>",
"EMBEDDED_AGENT_PROVIDER": "<Explicit LLM provider for AI-powered search>",
"OPENAI_API_KEY": "<OpenAI key if selecting OpenAI>"
}
}
}
}Config file · Project scope: .mcp.json at the repository root
The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"sentry-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"@sentry/mcp-server"
],
"env": {
"SENTRY_ACCESS_TOKEN": "<Sentry user auth token with documented scopes>",
"EMBEDDED_AGENT_PROVIDER": "<Explicit LLM provider for AI-powered search>",
"OPENAI_API_KEY": "<OpenAI key if selecting OpenAI>"
}
}
}
}Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Tools
Source: repository tool metadata. Tool descriptions are a documented snapshot, not a live capability check.
| Tool | What it does |
|---|---|
| find_organizations | Locate accessible organizations and their slugs. |
| find_projects | Find projects within a Sentry organization. |
| update_issue | Change an issue status or assignment. |
| search_events | Search events and replays, including statistical queries. |
| analyze_issue_with_seer | Ask Seer to investigate an error and propose code fixes. |
| search_issues | Find grouped issues using natural language or Sentry query syntax. |
| get_sentry_resource | Retrieve an issue, event, trace, replay, or other supported resource. |
| search_sentry_tools | Find additional operations in the Sentry MCP tool catalog. |
| execute_sentry_tool | Run a discovered operation with arguments matching its schema. |
Names, permissions, and defaults can change. Check the current upstream documentation before granting access.
Use cases
- Investigate production errors alongside application code.
- Find organizations and project identifiers for follow-up requests.
- Resolve, reopen, ignore, or assign issues.
- Search event statistics and retrieve trace resources.
- Request Seer analysis for an issue.
Strengths
- Designed around coding-agent debugging tasks.
- Supports hosted and self-hosted Sentry workflows.
- Tool discovery provides access beyond top-level operations.
Limitations
- AI-powered search needs an LLM provider.
- Some self-hosted deployments lack Seer.
- The README describes stdio support as work in progress.
Frequently asked questions
Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.
