Betterstack MCP Connector for AI Agents

Betterstack MCP tools for AI agents

CALL ANY TOOL

12 tools covering add, acknowledge.

betterstackmcp_acknowledge_incident

Acknowledge incident

Acknowledge an ongoing incident

Parameters

Name

Type

Required

Description

integer

Required

The ID of the incident to acknowledge

acknowledged_by

string

Optional

User email or identifier of who acknowledged the incident. Optional - when omitted, the action is attributed to the authenticated OAuth user (or "API" for team/organisation API tokens). Only pass this if the user has explicitly told you who acknowledged the incident on their behalf.

betterstackmcp_add_chart_to_dashboard

Add chart to dashboard

betterstackmcp_available_incident_escalation_policies

Available incident escalation policies

betterstackmcp_chart_alert_help

Chart alert help

betterstackmcp_create_application

Create application

betterstackmcp_create_dashboard

Create dashboard

betterstackmcp_create_metric_expression

Create metric expression

betterstackmcp_create_status_page_report

Create status page report

betterstackmcp_dashboard

Dashboard

betterstackmcp_dashboard_query_help

Dashboard query help

betterstackmcp_delete_chart_alert

Delete chart alert

betterstackmcp_documentation

Documentation

betterstackmcp_edit_application

Edit application

betterstackmcp_escalation_policies

Escalation policies

betterstackmcp_heartbeat_availability

Heartbeat availability

betterstackmcp_incident_comments

Incident comments

betterstackmcp_metric

Metric

betterstackmcp_metrics_query_help

Metrics query help

betterstackmcp_monitor_availability

Monitor availability

betterstackmcp_on_call

Call on

betterstackmcp_on_calls

On calls

betterstackmcp_remove_chart

Remove chart

betterstackmcp_remove_dashboard_variable

Remove dashboard variable

betterstackmcp_resolve_incident

Resolve incident

betterstackmcp_set_dashboard_variable

Set dashboard variable

Create or update a dashboard template variable: a user-facing filter in the dashboard toolbar, referenced in chart SQL as {{name}} (required: the chart errors until it resolves to a value) or [[ AND col = {{name}} ]] (optional: the whole [[ ... ]] clause is dropped while the variable is empty). Saving a chart auto-creates a plain text variable (or a source variable when the name contains 'source') for any undefined required {{name}}, but it starts empty: use this tool to give it a typed definition or a default value so the chart resolves without manual input. Fields per type: select_value (Static list) uses default_values (first = default selection); select_with_sql (Dynamic list) uses an option-yielding expression in sql_definition, e.g. label('_host'); both list types accept allow_multiple_values to let users pick several options at once; select_predefined_sql (Query per value) uses named full-query SQL filters in `filters`, default picked via selected_label; string/number/boolean use default_values as [default]; sql_expression uses default_values as [raw SQL] spliced unescaped; source uses source_ids to pick which sources the variable resolves to; date/datetime use an ISO date in default_values. SQL-backed types are validated at save time by running their SQL against the dashboard's source. The names source, start_time, end_time, and time are reserved.

Parameters

Name

Type

Required

Description

dashboard_id

integer

Required

The ID of the dashboard

name

string

Required

Variable name used as {{name}} in chart queries

variable_type

string

Required

The variable type

allow_multiple_values

boolean

Optional

select_value / select_with_sql: let users pick several options at once; the variable then interpolates as a quoted regex used with match(), never IN. Ignored for other types.

default_values

array

Optional

select_value: the options (first = default). string/number/boolean: [default]. sql_expression: [raw SQL]. date/datetime: [ISO date], e.g. ['2026-07-23T14:30:00Z'].

filters

array

Optional

select_predefined_sql: named SQL filters. Unlike sql_definition, each sql is a FULL query returning one column, whose rows are injected into the chart as an IN-list. Filter time with dt BETWEEN {{start_time}} AND {{end_time}}, never {{time}}.

selected_label

string

Optional

select_predefined_sql: the default filter label.

source_ids

array

Optional

source: the source IDs this variable resolves to (must be accessible to the dashboard's team). Ignored for other types.

sql_definition

string

Optional

select_with_sql / multi_select_with_sql: an expression (NOT a full query) yielding the option values: interpolated as SELECT DISTINCT <sql_definition> AS option FROM {{source}} WHERE dt BETWEEN {{start_time}} AND {{end_time}} LIMIT 50. Example: label('_host').

betterstackmcp_source_fields

Source fields

betterstackmcp_status_page_report_update

Update status page report

betterstackmcp_status_page_reports

Status page reports

betterstackmcp_team_members

Team members

betterstackmcp_update_status_page

Update status page

For more tools, view docs.

Build your Agent

Same auth pattern across every framework.

from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="betterstackmcp")

mcp = MultiServerMCPClient({
    "betterstackmcp": {
        "url": "https://mcp.scalekit.com/betterstackmcp",
        "headers": {"Authorization": "Bearer " + token}
    }
})
tools = await mcp.get_tools()

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "betterstackmcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/betterstackmcp
// Pass: Authorization: Bearer + token

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "betterstackmcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/betterstackmcp
// Pass: Authorization: Bearer + token

from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="betterstackmcp")
# Connect to MCP at https://mcp.scalekit.com/betterstackmcp
# Pass: Authorization: Bearer + token

Try these prompts

Paste any prompt into your agent to get started.

Get started

Copy the prompt

Copied

Update an existing metric expression?

Copy the prompt

Copied

Pause or unpause a chart alert?

Advanced

Copy the prompt

Copied

List all available teams in Better Stack Logs?

Copy the prompt

Copied

List all status pages with filtering and pagination options?

SEE HOW AUTH WORKS

User authorises once. Every agent call after uses their token with scope enforcement.

Authorize

Your user connects

Betterstack MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Betterstack MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Betterstack MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Betterstack MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other connectors.

Engineering Teams

DevOps assistant agent

Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

Engineering Teams

Auto release notes agent

Reads merged GitHub PRs, groups them into structured release notes, publishes the page to Notion, and announces the release in Slack. Every call runs on the engineer's own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.

// shared token
 audit → bot_service_account

 // scalekit
 audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

One connector today. Ten tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Betterstack as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Betterstack OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Betterstack?
Yes. Pass a tool name filter to listScopedTools so the on-call agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Betterstack.

What happens when a user revokes Betterstack access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent acknowledge incidents on behalf of anyone?
No. Incident acknowledgments and escalation changes run as the authorizing user, so on-call actions in Better Stack attribute to the responder who actually triggered them.

What other MCP connectors does Scalekit support?
Scalekit runs the Bugsnag MCP server, Sentry MCP server, and PostHog MCP server on the same per-user auth, token vault, and audit trail. Browse 500+ connectors in the MCP connector directory.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit