Freshservice connector for AI agents

Tools your IT service agent reaches for on Freshservice, scoped per user.

CALL ANY TOOL

119 tools for IT service management in Freshservice: create, update, and reply to tickets, log time, track assets, contracts, and software, manage changes, problems, releases, and projects, place service requests, and write knowledge base articles.

freshservice_agent_fields_list

List agent fields

List the fields on Freshservice agent profiles, including custom fields. Returns each field's name, label, type, required flags and choices. Use this to learn field names before filtering agents.

Parameters

Name

Type

Required

Description

—

No parameters required

freshservice_agent_get

Get agent

freshservice_agents_filter

Agents filter

freshservice_announcements_list

List announcements

freshservice_asset_create

Create asset

freshservice_asset_requests_list

List asset requests

freshservice_asset_type_get

Get asset type

freshservice_asset_update

Update asset

freshservice_assets_search

Search assets

freshservice_business_hours_list

List business hours

freshservice_change_notes_list

List change notes

freshservice_conversation_update

Update conversation

freshservice_departments_list

List departments

freshservice_itam_asset_get

Get itam asset

freshservice_problem_create

Create problem

Create a problem record in Freshservice to track the root cause behind one or more incidents. Returns the created problem object with its id. Use this for underlying causes. Use freshservice_ticket_create for an individual incident. Identify the initiator with email or requester_id.

Parameters

Name

Type

Required

Description

description

string

Required

Description of the problem in HTML. Plain text also works.

due_by

string

Required

Time the problem is due to be resolved, as an ISO 8601 datetime.

impact

integer

Required

Problem impact: 1 = Low, 2 = Medium, 3 = High. One of: `1`, `2`, `3`.

priority

integer

Required

Problem priority: 1 = Low, 2 = Medium, 3 = High, 4 = Urgent. One of: `1`, `2`, `3`, `4`.

status

integer

Required

Problem status: 1 = Open, 2 = Change Requested, 3 = Closed. One of: `1`, `2`, `3`.

subject

string

Required

Subject of the problem. Example: Recurring outages on email server ES3.

agent_id

integer

Optional

User ID of the agent the problem is assigned to.

analysis_fields

object

Optional

Root-cause analysis text. Each entry (problem_cause, problem_symptom, problem_impact) is an object with a description. Example: {"problem_cause": {"description": "Faulty power supply"}}

assets

array

Optional

Assets to associate, each given by its display ID. Example: [{"display_id": 8}].

tags

array

Optional

Tags to attach to the ticket. On update, send the full list you want to keep, because it replaces the existing tags. Example: ["vpn", "remote"].

urgency

integer

Optional

Urgency of the ticket: 1 = Low, 2 = Medium, 3 = High. One of: `1`, `2`, `3`.

workspace_id

integer

Optional

ID of the workspace the ticket belongs to. Omit to use the primary workspace. Applies only to accounts that use workspaces; it cannot be changed later with an update.

freshservice_ticket_time_entries_list

List ticket time entries

For more tools, view docs.

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);

// Freshservice tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["freshservice"], toolNames: [
    "freshservice_tickets_filter",
    "freshservice_ticket_get",
    "freshservice_ticket_note_create"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Triage urgent open tickets in the Network group and add a note to each" }] });

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: ["freshservice"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Triage urgent open tickets in the Network group and add a note to each" }],
  tools,
});

// Execute the tool call with the user's vaulted Freshservice API key
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: ["freshservice"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Triage urgent open tickets in the Network group and add a note to each" }],
  tools,
});

// Tool call runs with the user's vaulted Freshservice API key
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: ["freshservice"] }, pageSize: 100,
});

const agent = new Agent({
  name: "it_service_agent",
  model: "gemini-2.5-pro",
  instruction: "Freshservice tools scoped to this user",
  tools,
});

await agent.run("Triage urgent open tickets in the Network group and add a note to each");

Try these prompts

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

Tickets

Copy the prompt

Copied

List urgent open tickets assigned to the Network group.

Copy the prompt

Copied

Reply to ticket 4821 saying the VPN fix is rolling out tonight.

Copy the prompt

Copied

Log 45 minutes on ticket 4821 for troubleshooting.

Assets and catalog

Copy the prompt

Copied

Find the asset with tag LAP-0192 and show who it is assigned to.

Copy the prompt

Copied

Reassign laptop LAP-0192 to priya@acme.com.

Copy the prompt

Copied

Place a service request for a new monitor for Alex Kim.

Changes and knowledge

Copy the prompt

Copied

Create a change request to upgrade the core switches this Saturday.

Copy the prompt

Copied

List problems opened this month with their status.

Copy the prompt

Copied

Search the knowledge base for VPN setup on macOS.

SEE HOW AUTH WORKS

Each user connects their own Freshservice API key once, and Scalekit sends it with every call. API keys stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Freshservice

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

Freshservice

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

Freshservice

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

Freshservice

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 customer support and service desk connectors.

Support and Ops Teams

Support ticket automation agent

Fetches new Zendesk tickets, drafts a reply from Notion knowledge base articles, digests what it cannot answer to Slack, and archives the rest, acting as the support agent rather than a shared API key.

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.

Support and Ops Teams

Support triage agent

Fetches new Zendesk tickets, classifies them by type and urgency, searches the Notion knowledge base for an answer, and routes what it cannot resolve to Slack. Every call runs on the support agent's own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Freshservice API key looks fine in a demo. In production every ticket update and reply looks like one service account, and you cannot tell which user triggered it. 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.

Freshservice 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 Freshservice as the user or through a shared API key?

As the user. Each user connects their own Freshservice API key once, and Scalekit sends it with every call. Audit logs attribute every ticket, reply, and asset change to that user, not a shared service account.

Where is the Freshservice API key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Freshservice?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the ticket and asset read tools without freshservice_ticket_reply_create, which sends a public reply to the requester. None of the 119 tools delete data. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Freshservice 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.

Does the connector cover changes, problems, and releases, or only tickets?

All of them. Beyond tickets, the tools create and update changes, problems, releases, and projects, add notes and tasks to each, and read approvals, SLA policies, the service catalog, and IT asset management records.