Model Context Protocol server for Rollbar
Squadcast is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Read incidents, services, teams, on-call schedules; acknowledge, resolve and note incidents.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http squadcast-mcp https://squadcast.usefulapi.io/mcp
# 2 — ask your agent for something these tools do
# squadcast_list_incidents, squadcast_get_incident, squadcast_get_incident_events and 13 more
Squadcast costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http squadcast-mcp https://squadcast.usefulapi.io/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
16 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search/list incidents over a time window with filters (status, service, priority, assignee, tags, sources, starred, SLO-affecting) and sorting. start_time, end_time (both ISO8601) and owner_id (a TEAM id — use squadcast_list_teams to find it) are REQUIRED. Squadcast: GET /v3/incidents/export.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| startTime | string | yes | ISO8601 start of the window (required) → start_time. |
| endTime | string | yes | ISO8601 end of the window (required) → end_time. |
| ownerId | string | yes | Team id that owns the incidents (required) → owner_id. Use squadcast_list_teams to find it. |
| status | array | no | Filter by incident status(es) → status. |
| services | array | no | Filter by service id(s) → services. |
| priority | array | no | Filter by priority (e.g. P1..P5) → priority. |
| assignedTo | array | no | Filter by assignee id(s) → assigned_to. |
| tags | array | no | Filter by tag(s) → tags. |
| sources | array | no | Filter by alert source(s) → sources. |
| sortBy | string | no | Sort field → sort_by. |
| textFilter | string | no | Free-text filter → textFilter. |
| isStarred | string | no | Filter to starred incidents → is_starred. |
| sloAffecting | string | no | Filter by SLO-affecting → slo_affecting. |
Get a single incident by its id. Squadcast: GET /v3/incidents/{incidentID}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| incidentId | string | yes | The incident id (required). |
Get the timeline of events for a single incident (state changes, notifications, actions). Squadcast: GET /v3/incidents/{incidentID}/events.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| incidentId | string | yes | The incident id (required). |
List the war-room notes on a single incident. Squadcast: GET /v3/incidents/{IncidentId}/warroom.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| incidentId | string | yes | The incident id (required). |
List services for a team. owner_id (a TEAM id — use squadcast_list_teams to find it) is REQUIRED. Squadcast: GET /v3/services.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ownerId | string | yes | Team id that owns the services (required) → owner_id. |
| name | string | no | Filter by service name → name. |
| entityOwner | string | no | Filter by entity owner → entity_owner. |
Get a single service by its id. Squadcast: GET /v3/services/{serviceID}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| serviceId | string | yes | The service id (required). |
List all users in the organization. Squadcast: GET /v3/users.
No parameter schema on file.
Get a single user by their id. Squadcast: GET /v3/users/{userID}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| userId | string | yes | The user id (required). |
List all teams in the organization. A team id is the owner_id/teamID several other tools require. Squadcast: GET /v3/teams.
No parameter schema on file.
Get a single team by its id. Squadcast: GET /v3/teams/{teamId}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| teamId | string | yes | The team id (required). |
List squads for a team. owner_id (a TEAM id — use squadcast_list_teams to find it) is REQUIRED. Squadcast: GET /v4/squads.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ownerId | string | yes | Team id that owns the squads (required) → owner_id. |
List on-call schedules for a team. teamID is REQUIRED (use squadcast_list_teams to find it). Set myOnCall to filter to schedules where the token's own user is currently on call — the 'who's on call' lens. Squadcast: GET /v4/schedules.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| teamId | string | yes | Team id whose schedules to list (required) → teamID. |
| myOnCall | boolean | no | Only schedules where the token's user is on call now → myOnCall (the 'who's on call' lens). |
| participants | array | no | Filter by participant user id(s) → participants. |
| scheduleName | string | no | Filter by schedule name → scheduleName. |
| search | string | no | Free-text search → search. |
| pageSize | number | no | Page size → pageSize. |
| cursor | string | no | Pagination cursor → cursor. |
List escalation policies for a team. owner_id (a TEAM id — use squadcast_list_teams to find it) is REQUIRED. Squadcast: GET /v3/escalation-policies.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ownerId | string | yes | Team id that owns the escalation policies (required) → owner_id. |
| pageNumber | number | no | Page number → page_number. |
| pageSize | number | no | Page size → page_size. |
Acknowledge a triggered incident on the LIVE account (stops escalation/paging for it). Squadcast: POST /v3/incidents/{incidentID}/acknowledge.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| incidentId | string | yes | The incident id to acknowledge (required). |
Resolve an incident on the LIVE account, recording a resolution message. Squadcast: POST /v3/incidents/{incidentID}/resolve.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| incidentId | string | yes | The incident id to resolve (required). |
| message | string | yes | Resolution reason/message (required). |
Add a war-room note to a LIVE incident (optionally with attachment URLs). Squadcast: POST /v3/incidents/{IncidentId}/warroom.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| incidentId | string | yes | The incident id to add a note to (required). |
| message | string | yes | The note message (required). |
| attachments | array | no | Attachment URLs (defaults to none). |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Squadcast or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| squadcast_list_incidents | no tags | |
| squadcast_get_incident | no tags | |
| squadcast_get_incident_events | no tags | |
| squadcast_list_incident_notes | no tags | |
| squadcast_list_services | no tags | |
| squadcast_get_service | no tags | |
| squadcast_list_users | no tags | |
| squadcast_get_user | no tags | |
| squadcast_list_teams | no tags | |
| squadcast_get_team | no tags | |
| squadcast_list_squads | no tags | |
| squadcast_list_schedules | no tags | |
| squadcast_list_escalation_policies | no tags | |
| squadcast_acknowledge_incident | state-write | state-write: declares destructiveHint: true |
| squadcast_resolve_incident | state-write | state-write: declares destructiveHint: true |
| squadcast_add_incident_note | state-write | state-write: declares destructiveHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.11.1.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Squadcast can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.