Sentry MCP
✓ Text source-checked Oct 23, 2026Sentry's MCP service is primarily designed for human-in-the-loop coding agents.
Source-checked against the vendor's site · rebuilt from the vendor's own pagesProfile updated Link checked Pricing captured How we rate
In short
Sentry MCP connects coding agents to Sentry for debugging. It uses natural language to query errors and traces via a remote server or stdio transport.
The Sentry Toolkit repository contains the Sentry CLI, the Sentry MCP server, and shared packages. The vendor says that the tool selection and priorities are focused on developer workflows and debugging use cases rather than providing a general-purpose MCP server for all Sentry functionality. The remote MCP server acts as middleware to the upstream Sentry API, optimized for coding assistants like Cursor, Claude Code, and similar development tools.
A Claude Code plugin provides a sentry-mcp subagent that Claude automatically delegates to when users ask about Sentry errors, issues, traces, or performance. The repository supports a stdio transport in addition to acting as an MCP service. The AI-powered search tools require an LLM provider such as OpenAI, Azure OpenAI, Anthropic, or OpenRouter. The AI-powered search tools use natural language processing to translate queries into Sentry's query syntax.
The stdio transport can connect to self-hosted Sentry deployments by specifying the host. Users can disable specific skills to prevent unsupported tools from being exposed.
According to Sentry MCP: The Sentry Toolkit repository contains the Sentry CLI, The Sentry MCP server, and shared packages. Its pages list this strength: Optimized for coding assistants like Cursor and Claude Code. They also state this limitation: AI-powered search tools require an external LLM provider.
— The AI Tool Bible editorial team
Pros
- ✅ Optimized for coding assistants like Cursor and Claude Code.
- ✅ Supports a stdio transport for local or self-hosted use.
- ✅ Can connect to self-hosted Sentry deployments.
- ✅ Allows disabling specific skills to control exposed tools.
- ✅ Provides automatic subagent delegation for Claude Code.
Cons
- ⚠️ AI-powered search tools require an external LLM provider.
Pricing (captured )
| Tier | Monthly | Per seat | Key features |
|---|---|---|---|
| Free | $0 USD per month | — |
|
| Team | $4 USD per user/month | Yes |
|
| Enterprise | Starting at $21 USD per user/month | Yes |
|
Prices change; we show the grid as captured on Oct 27, 2026. Check current pricing on the vendor's site →
Facts
- Pricing
- freemium - Free tier · from $4 USD/mo (not source-checked)
- API available
- Yes (not source-checked)
- Open source
- Yes (license: NOASSERTION) (not source-checked)
- GitHub stars
- 949 (checked Oct 29, 2026) (not source-checked)
- Last GitHub push
- Oct 29, 2026 (not source-checked)
- First commit
- Mar 2025 (not source-checked)
- Model used
- Bring-your-own LLM (OpenAI, Anthropic, Azure OpenAI, or OpenRouter) for natural-language search skills; agent-side model is whatever your MCP client runs. (not source-checked)
Where this tool sits
Use cases
Frequently asked
- How much does Sentry MCP cost?
- The pricing model is freemium, though specific details are not documented. You must bring your own LLM provider, such as OpenAI or Anthropic, for the natural-language search skills.
- Which LLM providers are supported?
- The AI-powered search tools require an LLM provider like OpenAI, Azure OpenAI, Anthropic, or OpenRouter. The agent-side model depends on your specific MCP client configuration.
- Can I use this with self-hosted Sentry?
- Yes. The stdio transport allows connections to self-hosted Sentry deployments by specifying the host. This provides flexibility for teams not using the remote MCP service.
- What coding agents does it integrate with?
- It is optimized for coding assistants like Cursor and Claude Code. A specific Claude Code plugin includes a sentry-mcp subagent that automatically handles Sentry-related queries.
- Can I limit which tools are exposed?
- Yes, users can disable specific skills to prevent unsupported tools from being exposed. This allows you to tailor the available functionality to your specific debugging needs.