AppSignal MCP connector for AI agents

CALL ANY TOOL

Error monitoring end to end: list exception and anomaly incidents, read logs and traces, and manage the triggers that page your team.

appsignalmcp_get_exception_incidents

List exception incidents

List and search exception incidents with optional date range, state, namespace, and deploy revision filters.

Parameters

Name

Type

Required

Description

app_environment

string

Required

The environment of the AppSignal application (e.g. production, staging).

app_name

string

Required

The name of the AppSignal application.

context

object

Required

AppSignal context object (app name, environment, org token)

deploy_revision

string

Optional

Filter incidents introduced in a specific deploy revision.

end

string

Optional

ISO 8601 end date/time for filtering incidents by occurrence time.

limit

integer

Optional

Maximum number of incidents to return.

namespace

string

Optional

Filter incidents by namespace (e.g. web, background).

start

string

Optional

ISO 8601 start date/time for filtering incidents by occurrence time.

state

string

Optional

Filter incidents by state (e.g. open, closed, wontfix).

appsignalmcp_get_incident

Get incident details

appsignalmcp_get_anomaly_incidents

List anomaly alerts

appsignalmcp_get_traces

Query traces

appsignalmcp_get_log_lines

Query logs

appsignalmcp_get_metrics_timeseries

Get metric timeseries

appsignalmcp_manage_trigger

Manage triggers

appsignalmcp_update_incidents

Update incidents

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// AppSignal tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["appsignalmcp"], toolNames: [
    "appsignalmcp_get_exception_incidents",
    "appsignalmcp_get_incident",
    "appsignalmcp_get_traces"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Any new exceptions since the last deploy?" }] });

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

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["appsignalmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Which endpoints slowed down after yesterday's deploy?" }],
  tools,
});

// Execute the tool call with the user's vaulted AppSignal credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

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

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["appsignalmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Summarize open anomaly alerts for the web namespace." }],
  tools,
});

// Tool call runs with the user's vaulted AppSignal credential
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["appsignalmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "appsignal_oncall_agent",
  model: "gemini-2.5-pro",
  instruction: "Triage AppSignal incidents for the signed-in user.",
  tools,
});

await agent.run("Assign the checkout exception spike to the payments team.");

Try these prompts

Copy any prompt into your agent. Each maps directly to an AppSignal tool. Click to copy, paste into your agent, done.

Triage errors

Copy the prompt

Copied

List open exception incidents from the last 24 hours.

Copy the prompt

Copied

Show details for incident 482 and its recent occurrences.

Copy the prompt

Copied

Which exceptions started after deploy revision a1f2c9?

Performance and logs

Copy the prompt

Copied

Trace the slowest checkout requests from this morning.

Copy the prompt

Copied

Query error-level log lines mentioning timeout in the web app.

Copy the prompt

Copied

Plot the response time timeseries for the API namespace this week.

Alerts and cleanup

Copy the prompt

Copied

Create a trigger that alerts when queue latency passes 5 seconds.

Copy the prompt

Copied

List anomaly alerts that are still open and unassigned.

Copy the prompt

Copied

Close all resolved incidents and assign the rest to on-call.

SEE HOW AUTH WORKS

Your users connect once. Their AppSignal credentials stay vaulted, every call is scope-checked, and every action is logged.

1

Authorize

Your user connects

AppSignal 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

2

Store

Their

AppSignal 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

3

Resolve

When your agent calls a

AppSignal 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

4

Audit

Every

AppSignal 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 monitoring connectors.

ENGINEERING

DevOps assistant agent

Triage GitHub incidents, open Linear tickets, and notify the on-call channel in Slack with context already attached.

ENGINEERING

Engineering standup agent

Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with identity, scope enforcement, and audit. Connectors follow.

01.

Shared tokens break per-user analytics

A shared AppSignal key looks fine in a demo. In production every incident closed and trigger changed looks like one service account, and you cannot tell who silenced an alert before an outage. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

AppSignal today. Ten connectors 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 AppSignal as the user or through a shared key?

As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every incident update and trigger change in your audit trail is attributed to a real user, not a shared service account.

Where is the AppSignal API key stored?

In an AES-256 encrypted vault with per-tenant namespacing. Keys are resolved at request time, never enter LLM context, and can be rotated or revoked from one dashboard.

Can I limit what the agent does in AppSignal?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example read-only incident and trace queries without update_incidents or manage_trigger. Scalekit also enforces scope checks before every API call.

What happens when a user revokes access?

The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.

Can the agent close incidents or change alert triggers on its own?

Only if you expose those tools. update_incidents, manage_trigger, and archive_trigger are separate tool names, so you can keep agents read-only or gate writes to specific users. Every state change is scope-checked first and logged with the user who triggered it.

AppSignal MCP

Tools your on-call agent reaches for on AppSignal, scoped per user.