Sentry MCP server and Dome
Let agents triage Sentry issues. Never let them silence one for good.
Connect Sentry's MCP server to Dome with OAuth. Each engineer consents once, and calls made for them run with their Sentry access. Rules read the arguments of every call, down to how an issue is ignored.
How Dome helps
Dome provides a tool gateway and authorization for Sentry
Decided on the arguments
The same update_issue call resolves an issue or ignores it until it escalates. Ignoring it forever is refused.
Their Sentry access
With per-user OAuth, each engineer consents once. An agent acting for them reaches only what they can.
No side door
Sentry's execute_sentry_tool runs any tool in its catalog by name. Rules read that name too, so deletes routed through it are refused.
Get started
Sentry behind the Gateway in three steps
Add the server, sync its tools into the Gateway's catalog, and apply the rules. Sentry supports dynamic client registration, so there is no OAuth app to create.
01
Add the Sentry MCP server
Dome registers itself as a client with Sentry and holds each engineer's tokens. Calls made for them carry their own.
$ dome tools add --name sentry \--url https://mcp.sentry.dev/mcp \--auth-method oauth --credential-type per-user \--oauth-authorize-url https://mcp.sentry.dev/oauth/authorize \--oauth-token-url https://mcp.sentry.dev/oauth/token \--oauth-registration-url https://mcp.sentry.dev/oauth/register \--gateway eng-gateway02
Sync the catalog
Run it once your own Sentry consent is attached. Until then the sync fails, and agents get “tool not available in this gateway”.
$ dome tools catalog sync sentry03
Apply the rules
Scope them to one agent while you try them. Simulate before you deploy.
$ dome rules apply sentry-triage.cedar \--agent issue-triager --name sentry-triage
Commands and rules tested against a Dome workspace on October 1, 2026. For anything about Sentry itself, see Sentry's documentation.
Rules
Triage freely, never ignore forever
The permit opens Sentry to the agent. The first forbid refuses ignoring an issue forever. The second refuses deletes, and update_issue itself, when they come through execute_sentry_tool.
permit (principal, action == Dome::Action::"mcp:call", resource is Dome::MCPTool)when { resource.connection_name == "sentry" }; forbid (principal, action == Dome::Action::"mcp:call", resource is Dome::MCPTool)when { resource.connection_name == "sentry" && resource.tool_name == "update_issue" && resource has arguments && resource.arguments has ignoreMode && resource.arguments.ignoreMode == "forever"}; forbid (principal, action == Dome::Action::"mcp:call", resource is Dome::MCPTool)when { resource.connection_name == "sentry" && resource.tool_name == "execute_sentry_tool" && resource has arguments && resource.arguments has name && (resource.arguments.name like "delete_*" || resource.arguments.name == "update_issue")};Try it
One call, two outcomes
Switch the caller or the argument and watch the same call decide differently. Every decision lands in audit.
Ignore mode
- Agentissue-triager is registered and active
- Callerj.alvarez verified through Okta
- RuleIssues may be ignored until they escalate
Example agents
Three agents on Sentry
From our template library. Each one reads broadly and writes narrowly.
issue-triager
Triage new issues
Reads new issues and their events, then resolves, assigns, or ignores them until they escalate.
- sentry/search_issues
- sentry/get_sentry_resource
- sentry/update_issue
root-cause-analyst
Find the root cause
Pulls the stack trace and surrounding events for an issue and asks Seer for the root cause. It changes nothing in Sentry.
- sentry/get_sentry_resource
- sentry/search_events
- sentry/analyze_issue_with_seer
alert-tuner
Tune noisy alerts
Finds alert rules that fire too often and adjusts their thresholds. Deleting a rule stays with an engineer.
- sentry/search_sentry_tools
- sentry/search_events
- sentry/execute_sentry_tool
Agent workflow
Bringing it together
Connecting Sentry to registered agents, models, and identity in Dome completes a governed agent application.
Acting for
Control point
Gateway
- Rules
- Guards
- Quotas
Every call decided and audited
Tools
MCP server
Sentry
This page
FAQ
Common questions
Does Dome work with Sentry's remote MCP server?
Yes. Add https://mcp.sentry.dev/mcp with per-user OAuth, and Dome registers itself as a client through dynamic client registration.
Can an AI agent resolve Sentry issues but not ignore them forever?
Yes. A rule reads the ignoreMode argument of update_issue and refuses the call when it is forever.
What is execute_sentry_tool, and why does the rule name it?
It runs any tool in Sentry's catalog by name. A rule on update_issue alone would miss the same change made through it.
Whose Sentry permissions does an agent use?
With per-user OAuth, the permissions of the engineer it acts for. Dome picks their token from their verified identity.
Explore
More of what Dome works with
Model
Claude Fable
Fable 5.1 from Anthropic and Amazon Bedrock in one failover pool, open to one group and capped by quota.
Read moreProvider
Anthropic
The Claude API behind the Model Broker: the key held in Dome, every call authorized, metered and audited.
Read moreIdentity
Microsoft Entra ID
Entra access tokens verified on every agent call, so rules read app roles and audit names the person.
Read moreRuntime
LangGraph
LangGraph agents with their model calls on the Model Broker and their MCP tools on the Tool Gateway.
Read moreClient
Codex
Codex on a Dome Gateway with per-developer sign-in, rules on every tool call, and audit by name.
Read moreAgent service
TinyFish
TinyFish's web agents behind the Tool Gateway, with rules that decide each run on the site it targets.
Read moreNext steps
Talk with our FDE team
Our forward deployed engineers work with your platform team to get your agents into production and under control: the first one governed on your own systems, and a pattern your teams can repeat for every agent after it.
No card required to start. Register your first agent in minutes.
MCP servers for AI agents: per-argument rules on every call
Put any remote MCP server behind the Tool Gateway. Agents reach it through one governed endpoint, and rules decide each call on its arguments.
See them all