Connect
Optimize
Secure
Freshservice MCP Server
for AI Agents
Production-ready Freshservice MCP server with 84 extensible actions — plus built-in authentication, security, and optimized execution.
Freshservice MCP Server
Built by 
StackOne
StackOne 
Coverage
84 Agent Actions
Create, read, update, and delete across Freshservice — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Freshservice MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Freshservice tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Freshservice call.
Tools Discovery →What is the Freshservice MCP Server?
A Freshservice MCP server lets AI agents read and write Freshservice data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Freshservice MCP server ships with 84 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Freshservice MCP Tools and Actions
Every action from Freshservice's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Agents
- Create Agent
Create a new agent in Freshservice
- List Agents
Retrieve a list of all agents
- Get Agent
Retrieve a specific agent by ID
- Update Agent
Update an existing agent
Assets
- Create Asset
Create a new asset
- List Assets
Retrieve a list of all assets
- Get Asset
Retrieve a specific asset by display ID
- Update Asset
Update an existing asset
- Delete Asset
Delete an asset (moves to trash)
Changes
- Create Change
Create a new change request
- List Changes
Retrieve a list of all changes
- Get Change
Retrieve a specific change by ID
- Update Change
Update an existing change
- Delete Change
Delete a change
Contracts
- Create Contract
Create a new contract
- List Contracts
Retrieve a list of all contracts
- Get Contract
Retrieve a specific contract by ID
- Update Contract
Update an existing contract
Departments
- Create Department
Create a new department
- List Departments
Retrieve a list of all departments
- Get Department
Retrieve a specific department by ID
- Update Department
Update an existing department
- Delete Department
Delete a department
Groups
- Create Group
Create a new group
- List Groups
Retrieve a list of all groups
- Get Group
Retrieve a specific group by ID
- Update Group
Update an existing group
- Delete Group
Delete a group
Problems
- Create Problem
Create a new problem
- List Problems
Retrieve a list of all problems
- Get Problem
Retrieve a specific problem by ID
- Update Problem
Update an existing problem
- Delete Problem
Delete a problem
Releases
- Create Release
Create a new release
- List Releases
Retrieve a list of all releases
- Get Release
Retrieve a specific release by ID
- Update Release
Update an existing release
- Delete Release
Delete a release
Requesters
- Create Requester
Create a new requester
- List Requesters
Retrieve a list of all requesters
- Get Requester
Retrieve a specific requester by ID
- Update Requester
Update an existing requester
Solution Categorys
- Create Solution Category
Create a new solution category
- Get Solution Category
Retrieve a specific solution category by ID
- Update Solution Category
Update an existing solution category
- Delete Solution Category
Delete a solution category
Solution Folders
- Create Solution Folder
Create a new solution folder
- Get Solution Folder
Retrieve a specific solution folder by ID
- Update Solution Folder
Update an existing solution folder
- Delete Solution Folder
Delete a solution folder
Tickets
- Create Ticket
Create a new support ticket
- List Tickets
Retrieve a paginated list of all tickets
- Get Ticket
Retrieve a single ticket by ID
- Update Ticket
Update an existing ticket
- Delete Ticket
Delete a ticket (moves to trash)
Ticket Tasks
- Create Ticket Task
Create a task on a ticket
- List Ticket Tasks
Retrieve all tasks for a ticket
- Get Ticket Task
Retrieve a specific task on a ticket
- Update Ticket Task
Update a task on a ticket
- Delete Ticket Task
Delete a task from a ticket
Ticket Time Entrys
- Create Ticket Time Entry
Log time spent on a ticket
- Get Ticket Time Entry
Retrieve a specific time entry for a ticket
- Update Ticket Time Entry
Update a time entry on a ticket
- Delete Ticket Time Entry
Delete a time entry from a ticket
Other (20)
- Create Ticket Reply
Add a public reply to a ticket
- Create Child Ticket
Create a child ticket under an existing ticket
- Get Authenticated Agent
Retrieve the currently authenticated agent's profile
- List Contract Types
Retrieve all contract types
- List Solution Categories
Retrieve all solution categories
- List Ticket Conversations
Retrieve all conversations for a ticket
- List Ticket Time Entries
Retrieve all time entries for a ticket
- Get Ticket Activity
Retrieve activity log for a ticket
- Deactivate Agent
Deactivate an agent
- Filter Agents
Search agents using query language
- Forget Agent
Permanently delete an agent and their tickets
- Filter Assets
Search assets using query language
- Submit Contract For Approval
Submit a contract for approval
- Approve Contract
Approve a pending contract
- Reject Contract
Reject a pending contract
- Filter Departments
Search departments using query language
- Filter Requesters
Search requesters using query language
- Deactivate Requester
Deactivate a requester
- Forget Requester
Permanently delete a requester's data
- Filter Tickets
Search tickets using query language
Set Up Your Freshservice MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Freshservice in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}More Customer Support MCP Servers
Intercom
123+ actions
SurveyMonkey
104+ actions
ServiceNow
74+ actions
Freshdesk
71+ actions
Gorgias
69+ actions
Discourse
67+ actions
Dixa
65+ actions
Freshservice MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Freshservice MCP Server FAQ
Freshservice MCP server vs direct API integration — what's the difference?
A Freshservice MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Freshservice. A Freshservice MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Freshservice at runtime. StackOne provides both.
How does Freshservice authentication work for AI agents?
Freshservice authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Freshservice account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Freshservice MCP tools vulnerable to prompt injection?
Yes — Freshservice MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Freshservice agent and how do I avoid it?
Context bloat happens when Freshservice tool schemas and API responses eat your Freshservice agent's memory, preventing it from reasoning effectively. A single Freshservice query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Freshservice agent can access?
Yes — you can limit which actions your Freshservice agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Freshservice MCP server?
Yes — you can create custom agent actions for your Freshservice MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Freshservice's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Freshservice MCP server?
Skip a Freshservice MCP server if your integration is purely software-to-software — direct Freshservice API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Freshservice actions at runtime.
What AI frameworks and AI clients does the StackOne Freshservice MCP server support?
The StackOne Freshservice MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.