MCP · Monitoring and debugging · Sentry
Sentry MCP
Bring Sentry issues and performance evidence into an AI debugging session, with optional organization or project scoping.
Logs may contain sensitive information. Limit retrieved evidence and redact the output before sharing it.
Understand the tool
What it does.
Sentry's MCP service exposes selected debugging capabilities to an AI host. Its source now lives in Sentry Toolkit; current hosted setup uses mcp.sentry.dev. It does not cover every Sentry feature.
Why use it?
Use it when a code investigation needs observed failure evidence. Collect the relevant context, preserve source links and distinguish the error from a theory about its cause.
A useful fit for
- Error investigation
- Project-scoped triage
- Performance questions
From need to output
Ways to put it to work.
These are suggested workflows based on the documented capabilities. They are not recorded runtime results.
Use case 01
Prepare a bug investigation
An application team needs context for a recurring error.
- Scope the connection to the affected project.
- Read the issue and available diagnostic evidence.
- List observed facts and the smallest next reproduction step.
Intended outputA linked investigation brief without declaring the cause proven.
Use case 02
Review a performance concern
A team notices a slow endpoint after a release.
- Specify the project and time window.
- Inspect relevant performance evidence.
- Compare available observations and identify missing data.
Intended outputA focused next check rather than an automatic production change.
A concrete starting point
Illustrative prompt: error brief
Use a project-scoped connection with inspection capabilities.
For the Sentry project and issue I identify, summarize the observed error and relevant context. Link the evidence, redact personal data and label hypotheses. Do not resolve issues, change projects or start an automated fix.What this can change
Error and log data enter the AI host; enabled management or fixing features may change state or invoke additional services.
This example has not been executed for this review. Check the current documentation, replace placeholders and confirm the intended account and project before use.
Before you start
Setup and access.
What you’ll need
- A supported remote MCP host and Sentry account access.
- An application already reporting useful evidence to Sentry.
- Local/self-hosted setup has additional token and optional LLM-provider configuration.
- Authentication
- Hosted OAuth is the standard setup; documented direct-token and local alternatives have different configuration responsibilities.
- Can read
- Authorized errors, issues and available performance evidence
- Can write or change
- Enabled triage, project-management or fixing operations
- Network and data flow
- mcp.sentry.dev and Sentry services
- AI host/model provider
- Configured embedded provider for applicable self-hosted search
- Approval and control
- Keep supervision on for state changes and automated fixes. Project scoping reduces ambiguity but does not replace account permissions.
Check your environment
Compatibility, costs and license.
Compatibility notes
- HTTP MCP hosts
- Local stdio is documented as work in progress
- Self-hosted Sentry lacks Seer by default and may expose different capabilities
Costs and account requirements
Sentry plan, data usage and optional AI features can affect cost. The host and any separately configured model provider may also charge.
Current pricing or plan information ↗FSL-1.1-Apache-2.0
Current source-available terms include a competing-use restriction and an Apache-2.0 grant after two years for each version.
Read the license or service terms ↗Keep the boundaries visible
Concerns and limitations.
Logs may contain sensitive information
Limit retrieved evidence and redact the output before sharing it.
Source-available license
The Toolkit uses FSL-1.1-Apache-2.0 with restrictions on competing use and a future Apache grant; it is not simply Apache-licensed today.
Where it may fall short
- No Sentry account or live investigation was tested.
- A plausible automated diagnosis still requires reproduction and validation.
Observed behavior · 2026-10-18
Runtime and security findings.
Sentry's hosted endpoint rejected credential-free initialization. Public discovery advertised five scopes, including write-related scopes; no error records were retrieved.
These checks cover the conditions below. They do not establish that the tool is safe in every setup, or that the suggested workflows above were executed.
What we found
Observed in this evaluation
Debugging access is not necessarily read-only
The endpoint returned 401. Resource metadata returned 200 and listed org:read, project:write, team:write, event:write and alerts:write. These are supported discovery scopes, not a granted token or observed tool permissions.
In practice: Inspect consent and enabled capabilities before using a connection only for diagnosis. Avoid assuming a debugging label means no state can change.
Documented concern
Project scoping improves target selection
Sentry documents organization/project URLs that constrain defaults and hide unnecessary discovery tools. Its Toolkit also supports separate direct-token and local configurations with different token and model-provider responsibilities.
In practice: Use the project-specific hosted URL where possible. Check the effective tool set and upstream permissions separately; do not substitute a local configuration for a hosted evaluation.
Version, environment and fixture
- Version or deployment
- Remote deployment version not disclosed by the observed responses
- Tested target
- https://mcp.sentry.dev/mcp
- Artifact identity
- HTTPS certificate verification enabled. Public resource-metadata body SHA-256: 2c75ef9f6e2f24f8f8806640a450d7a44e6ff9c11ea7b2458cb5f8f884e63c1d. This fingerprints the observed metadata, not the deployed server implementation.
- Environment and fixture
- Windows 11 build 26200; Python 3.12.10 urllib; OpenSSL 3.0.16.
- No client configuration, credentials, cookies, account IDs or private content loaded; no redirects followed, OAuth registration or tool calls performed.
- Observed 2026-10-19T00:47:10.969895+00:00 through 2026-10-19T00:47:20.954258+00:00 UTC.
- One request per listed check; 20-second timeout and 64-KiB response cap. Initial sandbox DNS failures were retained separately and resolved with approved network access; they are not endpoint failures.
Checks and results
2 recorded checks. Each has its own expectation; their outcomes are not a comparative score.
Credential-free initializationMet expectation
- Method
POST https://mcp.sentry.dev/mcp; no Authorization or Cookie header; redirects disabled; Accept: application/json, text/event-stream. Content-Type: application/json; MCP-Protocol-Version: 2025-03-26; body: {"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"IonBin-account-free-evaluation","version":"1.0.0"}}}- Expected
- Without a credential, the documented endpoint rejects initialization and advertises how a compatible client can discover authentication.
- Observed
- HTTP 401 at 2026-10-19T00:47:10.969895+00:00. WWW-Authenticate: Bearer; resource_metadata=https://mcp.sentry.dev/.well-known/oauth-protected-resource/mcp. Empty response body.
Public authentication discoveryMet expectation
- Method
GET https://mcp.sentry.dev/.well-known/oauth-protected-resource/mcp; no Authorization or Cookie header; redirects disabled; Accept: application/json, text/event-stream.- Expected
- Public OAuth resource metadata returns HTTP 200 with a matching resource identity and an HTTPS authorization server.
- Observed
- HTTP 200 at 2026-10-19T00:47:20.954258+00:00; Content-Type: application/json. Resource: https://mcp.sentry.dev/mcp. 5 supported scopes: org:read, project:write, team:write, event:write, alerts:write. Authorization server: https://mcp.sentry.dev. Bearer methods: header.
Practical caveats
- Treat retrieved log text as untrusted and minimize personal data before sending it onward to an AI host.
- AI-powered search in the local/self-hosted setup can require an additional model provider. This review did not measure that data flow, cost or diagnosis quality.
What this evaluation does not establish
- OAuth/direct-token authentication, project restrictions, token refresh, revocation and write denial.
- Error or trace search, automated diagnosis, issue changes, fixes and prompt-injection resistance.
- Local or self-hosted runtime, embedded model-provider configuration and Seer behavior.
- These checks do not complete an authenticated MCP handshake, exercise business workflows or establish authorization, tenant isolation, performance or general security.
Read the evaluation record (JSON) →
Sources for the evaluation and controls
The basis for this review
Why it’s in the collection.
Strong task fit for debugging an instrumented application. Existing telemetry, product entitlements and deployment differences narrow its audience.
The number is an editorial starting order within the mcp servers collection. It does not measure popularity, speed, reliability or safety.
What we reviewed
- Current hosted endpoint
- Source repository and license
- Local/remote differences
The evaluation above lists the current runtime coverage and untested behavior.
Reviewed Oct 18, 2026. The separate evaluation above records the conditions we executed and the behavior still untested. Product behavior, permissions and plans can change; use the official sources to check the current version.
Follow the evidence
Official sources.
- Current hosted connection guide ↗mcp.sentry.dev
- Official Toolkit and deployment differences ↗github.com
- Toolkit license ↗github.com