MCP Gateway · Claude Code
Connect PagerDuty to Claude Code
When the pager goes off, the engineer on call is usually already in a terminal. Claude Code can pull the incident, its alerts and recent changes into the session, check whether it has happened before, and write findings back as incident notes. The Speakeasy MCP Gateway logs each PagerDuty call against the engineer who made it.
- Category
- Infrastructure
- Tools
- 64
- Authentication
- API key
- Claude Code
- CLI
Behind the MCP Gateway
Run PagerDuty MCP behind the MCP Gateway
One URL for every agent, sign-in through your IdP, RBAC down to the tool, and every PagerDuty call inspected and logged.
Set up
Add PagerDuty to Claude Code in 4 steps
- 01
Add PagerDuty from the catalog
An admin finds PagerDuty 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.
PagerDuty authenticates with an API key. Enter it under Upstream headers in the install dialog, or later on the server's Settings tab. The key is stored on the server, sent with every upstream request, and never reaches anyone's client configuration.
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 PagerDuty
Give teams the
mcp:connectscope on the PagerDuty server through team access or a role. The organization gateway works out each person's servers from their live access, so granting access adds PagerDuty 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 PagerDuty 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.
From then on, PagerDuty'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 PagerDuty
Investigate an incident from the terminal
Give Claude Code the incident ID and it reads the incident, its alerts and the change events linked to it, then lines them up with the code you have open.
get_incidentlist_alerts_from_incidentlist_incident_change_events
Check whether it happened before
Claude Code fetches past and related incidents for the current one, so you can see how a similar failure was resolved last time.
Write findings to the incident
As you narrow down the cause, Claude Code adds notes to the incident with what you checked and what you ruled out, so the next responder starts from there.
Tools
64 tools
Each PagerDuty tool can be allowed or denied per team and role at the MCP Gateway before Claude Code sees it.
list_alert_grouping_settings
List all alert grouping settings with optional filtering.
get_alert_grouping_setting
Get details for a specific alert grouping setting.
list_alerts_from_incident
List alerts for a specific incident.
get_alert_from_incident
Get a specific alert from an incident.
list_change_events
List all change events with optional filtering.
get_change_event
Get details about a specific change event.
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 PagerDuty call is logged with the person and the client that made it.
Access by role
Gateway
People reach only the PagerDuty tools their team or role allows.
Request and response blocking
Gateway
A risk policy scoped to PagerDuty 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
Can Claude Code change incidents, or only read them?
Can Speakeasy stop a PagerDuty tool call in Claude Code?
How do Claude Code users get PagerDuty?
Are PagerDuty calls from Claude Code logged?
Connect more