MCP Gateway · Claude Code
Connect Sentry to Claude Code
When a production error lands, Claude Code can pull the Sentry issue, its events and a Seer root cause analysis into the same session as the code that threw it. Speakeasy's hooks check each prompt and tool call before Claude Code runs it, and each person only reaches what their own Sentry account already can.
- Category
- Developer tools
- Tools
- 22
- Authentication
- OAuth
- Claude Code
- CLI
Behind the MCP Gateway
Run Sentry MCP behind the MCP Gateway
One URL for every agent, sign-in through your IdP, RBAC down to the tool, and every Sentry call inspected and logged.
Before you start
What Sentry needs first
Any Sentry user with access to the needed organizations and projects does the Sentry side of the setup.
- You create nothing in Sentry before adding the server.
- Users can only reach what their Sentry account already can.
Set up
Add Sentry to Claude Code in 4 steps
- 01
Add Sentry from the catalog
An admin finds Sentry in the MCP Catalog (MCP Gateway > MCP > Catalog) and clicks Add. Speakeasy registers the vendor's server as a remote MCP server and proxies sessions to it. Nothing is copied or re-hosted.
Sentry uses OAuth. Servers that support dynamic client registration get their OAuth configuration applied automatically.
Where MCP-scoped policies are enabled, the install offers a recommended risk policy for the new server that detects secrets and PII and inspects tool requests and responses.
- 02
Choose who can use Sentry
Give teams the
mcp:connectscope on the Sentry server through team access or a role. The organization gateway works out each person's servers from their live access, so granting access adds Sentry to their gateway on the next call, and removing it takes it away. - 03
Connect Claude Code
Add the organization gateway as an HTTP MCP server, then authenticate from /mcp.
Run the command below with your organization gateway URL.
Open
/mcpin Claude Code and choose Authenticate to sign in.claude mcp add --transport http --scope user \ 'speakeasy' \ 'https://<organization host>/mcp/gateway/<organization slug>' - 04
Sign in and use Sentry from Claude Code
The first time Claude Code connects, it opens a browser so the person can sign in to Speakeasy through your identity provider.
Sentry needs its own OAuth grant, so each person connects it once. Until they do, Sentry calls fail while the rest of the gateway keeps working.
From then on, Sentry's tools appear in Claude Code, limited to what the person's access allows, and every call lands in the gateway's tool logs.
To roll it out to a whole team, publish the server in a plugin and register the plugin marketplace in Claude Code's managed settings, so every member gets it without running the command. The device agent can also write and reapply these settings on each laptop.
Use cases
What Claude Code users do with Sentry
Fix the error behind an alert
Give Claude Code the Sentry issue URL. It fetches the issue and its events, reads the stack trace against your local checkout, and proposes a change.
Ask Seer for the root cause
For an error that isn't obvious from the trace, have Seer analyze it and return a root cause with suggested code fixes, then let Claude Code apply and test them.
Resolve the issue with the fix
Once the fix is merged, Claude Code marks the Sentry issue resolved or assigns it to the release owner, so nobody triages it twice.
Tools
22 tools
Each Sentry tool can be allowed or denied per team and role at the MCP Gateway before Claude Code sees it.
whoami
Identify the authenticated user in Sentry.
find_organizations
Find organizations that the user has access to in Sentry.
find_teams
Find teams in an organization in Sentry.
find_projects
Find projects in Sentry.
find_releases
Find releases in Sentry.
get_issue_tag_values
Get tag value distribution for a specific Sentry issue.
Control
What Speakeasy can see and stop in Claude Code
The gateway covers every client the same way. The rest depends on what Claude Code exposes to Speakeasy.
Tool logs
Gateway
Every Sentry call is logged with the person and the client that made it.
Access by role
Gateway
People reach only the Sentry tools their team or role allows.
Request and response blocking
Gateway
A risk policy scoped to Sentry can reject a tool request before it reaches the server, or withhold a result from Claude Code. MCP-scoped policies are enabled per organization.
Prompt and tool-call blocking
Claude Code
Agent hooks send each prompt and tool call to Speakeasy, which allows or denies it before Claude Code runs it.
User attribution
Claude Code
Claude Code's OpenTelemetry exporter ties each session to a named person. Without it, activity can't be attributed.
Budgets
Claude Code
Spend limits can block Claude Code traffic once a budget is reached.
Device agent and MDM
Claude Code
The device agent installs the marketplace, plugin and telemetry settings and reapplies them every minute. It deploys through MDM.
Anthropic inference hooks
Claude Code
On Claude Enterprise, prompts can be checked before inference with nothing installed on the device (beta).
- Claude Code on the web doesn't use the laptop setup. It needs the device agent in a shared Anthropic-hosted environment.
- Plugin marketplace URLs for Claude Code carry an access token, so share install snippets only through a private channel.
Questions
Frequently asked questions
Does Sentry need any setup before adding it to Speakeasy?
Can Claude Code resolve Sentry issues on its own?
How do Claude Code users get Sentry?
Are Sentry calls from Claude Code logged?
Connect more