Freshservice MCP Tools for AI Agents
Let an agent narrow ticket queues, read ticket history, find known causes, match requests to service catalog items, and retrieve solutions.
Available Tools
6 tools available in this integration
Freshservice.FindKnownCause Find the change or known problem that already explains a wave of tickets about one system.
Freshservice.FindRequester Find a Freshservice requester by internal id, exact email, or name.
Freshservice.GetTicket Read one ticket's whole story: fields, conversation, tasks, and any linked change or problem.
Freshservice.ListTickets Narrow the Freshservice ticket queue to what is actionable.
Freshservice.SearchServiceItems Search the Freshservice service catalog for an item that covers an ask.
Freshservice.SearchSolutions Search the Freshservice knowledge base, or fetch one article in full by id.
Working directly against the raw API? 214 more tools in the Freshservice API server →
Why agent-optimized tools matter
Built for intent, not API schemas
Ask the agent to "find the tickets about the payroll outage, identify the known cause, and show the affected requesters." Arcade picks the right Freshservice tools without guessing ticket IDs or requester IDs.
Up to 100x fewer tokens
Freshservice queue and search results return focused records, while full ticket conversations, tasks, and linked changes are fetched only when needed, so the agent does not load an entire ticket backlog into context.
Complete the workflow end to end
Narrow the ticket queue, read the full story, find the known cause, search the knowledge base, and check the service catalog through one toolkit designed around the complete IT service task.
Make actions predictable and controlled
Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.
Securing Freshservice
The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.
This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.
Learn about Contextual Access PoliciesFor Freshservice, you can implement some of these policies:
- Decide which tools an agent is allowed to see at all. A tool that is never listed cannot be called, whoever is asking.
- Inspect the inputs a call is about to run with, and block it or send it for human approval when they fall outside what the agent should do unsupervised.
- Redact Freshservice.GetTicket results, stripping requester phone numbers, email addresses, and conversation text before they reach the model, so ticket triage exposes only fields, tasks, and status.
- Strip Freshservice.FindRequester results of personal email addresses and phone numbers before the model sees them, so an agent can match a requester without retaining direct contact details.
- Redact Freshservice.SearchSolutions results, removing passwords, API keys, access tokens, and other credentials from knowledge-base articles before they reach the model.
How to use Freshservice with your agent
Pick your MCP client below and follow the setup from authentication through your first Freshservice request. You can have an agent searching tickets and knowledge articles in a few minutes.
Your questions, answered
A Freshservice MCP server exposes Freshservice service-management capabilities as structured tools that an AI agent can call through the Model Context Protocol. After a user authorizes their account, the agent can search tickets, inspect ticket histories, find requesters and known causes, and search service knowledge and catalog items.
Arcade's Freshservice integration is built by Arcade and provides Freshservice access through Arcade's MCP gateway and tool APIs. It adds per-user OAuth, approval workflows, response redaction, access controls, and agent-oriented actions, so teams can govern access consistently across clients and users.
Arcade agents can narrow the ticket queue, read a ticket's fields, conversation, tasks, and linked changes or problems, find requesters, identify known causes, search knowledge-base articles, and search service-catalog items. The integration also exposes broader Freshservice API coverage through raw API tools, subject to the permissions granted.
The listed Arcade-built actions are read-only and require OAuth permissions that allow the user to read Freshservice tickets, requesters, known causes, knowledge-base content, and service-catalog items. Permissions for broader raw API operations depend on the Freshservice access configured for those operations; grant only the access your workflow needs.
Yes. Each user authorizes their own Freshservice account through OAuth. Actions run under that user's authorization, so the agent can access only the Freshservice data and permissions that user has approved.
Yes. Contextual Access policies can require human approval before a consequential Freshservice action, including a write or destructive operation made through the broader API coverage. The call proceeds only after the policy's conditions are satisfied; the six Arcade-built actions are read-only.
Arcade proxies Freshservice API calls and does not persist your content as part of normal tool execution. Freshservice credentials are brokered and stored encrypted at rest, and the model never receives them.
Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.
Arcade refreshes access while the user's Freshservice authorization remains valid. If it is revoked, rotated, or can no longer be refreshed, calls stop until the user reconnects Freshservice.
Freshservice's own API rate limits and quotas apply to calls made through Arcade. The exact limits depend on your Freshservice plan and API usage, and no additional toolkit-specific quota is specified here.