Freshdesk MCP by usefulapi
io.usefulapi/freshdeskusefulapi.iostreamable-httpv1.41.5Scanned
Read tickets, contacts, companies, agents and groups; create, update and reply to tickets.
19 tools: 7 can delete or cancel things and 12 only read.
- Reads private data · 4
- Reads text others write · 5
- Can send data out · 1
- No findings
The remote endpoint did not answer the last look. Remote posture
Anlyon alternative
7 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Freshdesk MCP by usefulapi can do
The Freshdesk MCP by usefulapi is published by usefulapi.io, a domain the MCP Registry verified. It has 19 tools. It can delete or cancel things (7 tools: freshdesk_create_ticket, freshdesk_update_ticket, freshdesk_reply_ticket, freshdesk_add_note and 3 more). 12 tools only read.
4 tools read private data (freshdesk_list_ticket_conversations, freshdesk_list_contacts, freshdesk_get_contact and 1 more); 5 tools bring in text other people can write (freshdesk_list_tickets, freshdesk_get_ticket, freshdesk_search_tickets and 2 more); 1 tool can send data out of your system (freshdesk_reply_ticket). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Oct 25, 2026, version 1.41.5.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
19 tools
Deletes or cancels 7Claude Code: deny
freshdesk_add_noteAdd a note to a ticket.No findings
Why it is in this group
- The name "freshdesk_add_note" says "add": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Add a note to a ticket. Notes are internal (private) by default; set `private: false` for a public note. Freshdesk REST: POST /tickets/{id}/notes.
Annotations the server declares
- title: Add note to ticket
- destructiveHint: true
freshdesk_create_companyCreate a company.No findings
Why it is in this group
- The name "freshdesk_create_company" says "create": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Create a company. `name` is required. Freshdesk REST: POST /companies.
Annotations the server declares
- title: Create company
- destructiveHint: true
freshdesk_create_contactCreate a contact.No findings
Why it is in this group
- The name "freshdesk_create_contact" says "create": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Create a contact. `name` is required. Freshdesk REST: POST /contacts.
Annotations the server declares
- title: Create contact
- destructiveHint: true
freshdesk_create_ticketCreate a ticket.No findings
Why it is in this group
- The name "freshdesk_create_ticket" says "create": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Create a ticket. `subject` and `description` (HTML) are required, plus a requester — provide at least one of `email`, `requester_id`, or `phone`. status: 2=Open, 3=Pending, 4=Resolved, 5=Closed. priority: 1=Low, 2=Medium, 3=High, 4=Urgent. source: 1=Email, 2=Portal, 3=Phone, 7=Chat, 9=Feedbackwidget, 10=Outbound email. Freshdesk REST: POST /tickets.
Annotations the server declares
- title: Create ticket
- destructiveHint: true
freshdesk_reply_ticketAdd a public reply to a ticket (sent to the requester).Can send data outNo findings
Why it is in this group
- The name "freshdesk_reply_ticket" says "reply": a word for sending, and what is sent cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- outboundThe name "freshdesk_reply_ticket" says "reply": it sends or publishes something to other people.
Description, as the server wrote it Add a public reply to a ticket (sent to the requester). Freshdesk REST: POST /tickets/{id}/reply.
Annotations the server declares
- title: Reply to ticket
- destructiveHint: true
freshdesk_update_contactUpdate fields on an existing contact.No findings
Why it is in this group
- The name "freshdesk_update_contact" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Update fields on an existing contact. Only provided fields are changed. Freshdesk REST: PUT /contacts/{id}.
Annotations the server declares
- title: Update contact
- destructiveHint: true
freshdesk_update_ticketUpdate fields on an existing ticket.No findings
Why it is in this group
- The name "freshdesk_update_ticket" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Update fields on an existing ticket. Only provided fields are changed. status: 2=Open, 3=Pending, 4=Resolved, 5=Closed. priority: 1=Low, 2=Medium, 3=High, 4=Urgent. Freshdesk REST: PUT /tickets/{id}.
Annotations the server declares
- title: Update ticket
- destructiveHint: true
Only reads 12Show 12 read-only tools
freshdesk_get_agentGet a single agent by id.No findings
Why it is in this group
- The name "freshdesk_get_agent" says "get": a word for reading.
Description, as the server wrote it Get a single agent by id. Freshdesk REST: GET /agents/{id}.
Annotations the server declares
- title: Get agent
- readOnlyHint: true
freshdesk_get_companyGet a single company by id.No findings
Why it is in this group
- The name "freshdesk_get_company" says "get": a word for reading.
Description, as the server wrote it Get a single company by id. Freshdesk REST: GET /companies/{id}.
Annotations the server declares
- title: Get company
- readOnlyHint: true
freshdesk_get_contactGet a single contact by id.Reads private dataNo findings
Why it is in this group
- The name "freshdesk_get_contact" says "get": a word for reading.
What it can reach
- private-dataThe name "freshdesk_get_contact" says "get" and "contact": it reads contacts.
- private-dataThe description's first sentence says "get" and "contact": it reads contacts.
Description, as the server wrote it Get a single contact by id. Freshdesk REST: GET /contacts/{id}.
Annotations the server declares
- title: Get contact
- readOnlyHint: true
freshdesk_get_ticketGet a single ticket by id.Reads text others writeNo findings
Why it is in this group
- The name "freshdesk_get_ticket" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "freshdesk_get_ticket" says "get" and "ticket": it reads issues, which other people can write.
- untrusted-inputThe description's first sentence says "get" and "ticket": it reads issues, which other people can write.
Description, as the server wrote it Get a single ticket by id. Freshdesk REST: GET /tickets/{id}.
Annotations the server declares
- title: Get ticket
- readOnlyHint: true
freshdesk_list_agentsList/filter agents.No findings
Why it is in this group
- The name "freshdesk_list_agents" says "list": a word for reading.
Description, as the server wrote it List/filter agents. Freshdesk REST: GET /agents.
Annotations the server declares
- title: List agents
- readOnlyHint: true
freshdesk_list_companiesList companies.No findings
Why it is in this group
- The name "freshdesk_list_companies" says "list": a word for reading.
Description, as the server wrote it List companies. Freshdesk REST: GET /companies.
Annotations the server declares
- title: List companies
- readOnlyHint: true
freshdesk_list_contactsList/filter contacts.Reads private dataNo findings
Why it is in this group
- The name "freshdesk_list_contacts" says "list": a word for reading.
What it can reach
- private-dataThe name "freshdesk_list_contacts" says "list" and "contact": it reads contacts.
- private-dataThe description's first sentence says "list" and "contact": it reads contacts.
Description, as the server wrote it List/filter contacts. Freshdesk REST: GET /contacts.
Annotations the server declares
- title: List contacts
- readOnlyHint: true
freshdesk_list_groupsList groups (agent groups tickets are routed to).Reads text others writeNo findings
Why it is in this group
- The name "freshdesk_list_groups" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "list" and "ticket": it reads issues, which other people can write.
Description, as the server wrote it List groups (agent groups tickets are routed to). Freshdesk REST: GET /groups.
Annotations the server declares
- title: List groups
- readOnlyHint: true
freshdesk_list_ticket_conversationsList the conversations (replies and notes) on a ticket.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "freshdesk_list_ticket_conversations" says "list": a word for reading.
What it can reach
- private-dataThe name "freshdesk_list_ticket_conversations" says "list" and "conversation": it reads messages.
- private-dataThe description's first sentence says "list" and "conversation": it reads messages.
- untrusted-inputThe name "freshdesk_list_ticket_conversations" says "list" and "ticket": it reads issues, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "conversation": it reads messages, which other people can write.
Description, as the server wrote it List the conversations (replies and notes) on a ticket. Freshdesk REST: GET /tickets/{id}/conversations.
Annotations the server declares
- title: List ticket conversations
- readOnlyHint: true
freshdesk_list_ticketsList/filter tickets (max page 300).Reads text others writeNo findings
Why it is in this group
- The name "freshdesk_list_tickets" says "list": a word for reading.
What it can reach
- untrusted-inputThe name "freshdesk_list_tickets" says "list" and "ticket": it reads issues, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "ticket": it reads issues, which other people can write.
Description, as the server wrote it List/filter tickets (max page 300). Freshdesk REST: GET /tickets.
Annotations the server declares
- title: List tickets
- readOnlyHint: true
freshdesk_search_contactsSearch contacts with the Freshdesk query DSL.Reads private dataNo findings
Why it is in this group
- The name "freshdesk_search_contacts" says "search": a word for reading.
What it can reach
- private-dataThe name "freshdesk_search_contacts" says "search" and "contact": it reads contacts.
- private-dataThe description's first sentence says "search" and "contact": it reads contacts.
Description, as the server wrote it Search contacts with the Freshdesk query DSL. The query VALUE is wrapped in double quotes automatically. Examples: `name:'ada'`, `email:'ada@example.com'`, `company_id:123`. Freshdesk REST: GET /search/contacts.
Annotations the server declares
- title: Search contacts
- readOnlyHint: true
freshdesk_search_ticketsSearch tickets with the Freshdesk query DSL.Reads text others writeNo findings
Why it is in this group
- The name "freshdesk_search_tickets" says "search": a word for reading.
What it can reach
- untrusted-inputThe name "freshdesk_search_tickets" says "search" and "ticket": it reads issues, which other people can write.
- untrusted-inputThe description's first sentence says "search" and "ticket": it reads issues, which other people can write.
Description, as the server wrote it Search tickets with the Freshdesk query DSL. The query VALUE is wrapped in double quotes automatically. Examples: `status:2 AND priority:3`, `created_at:>'2026-01-01'`, `agent_id:123`, `group_id:45`, `tag:'urgent'`. Freshdesk REST: GET /search/tickets.
Annotations the server declares
- title: Search tickets
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
20 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data4
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write5
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__freshdesk__freshdesk_reply_ticket"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:36 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- no
- HTTP status of an anonymous initialize
- not observed
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
The probe stopped: The server redirected a POST to a different request.
Posture changes
- Oct 29, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 7 to 0
- Protocol version: 2025-06-18 to none
- RFC 9728 protected resource metadata: https://freshdesk.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
- Authorization servers: https://freshdesk.usefulapi.io to none
- Dynamic client registration: yes to not observed
- Client ID metadata documents: no to not observed
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 6 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 7 to 0
- Protocol version: 2025-06-18 to none
- RFC 9728 protected resource metadata: https://freshdesk.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
- Authorization servers: https://freshdesk.usefulapi.io to none
- Dynamic client registration: yes to not observed
- Client ID metadata documents: no to not observed
Install
Pinned to version 1.41.5. Values in angle brackets are yours to fill in.
claude mcp add --transport http freshdesk https://freshdesk.usefulapi.io/mcpclaude mcp add --transport http freshdesk https://freshdesk.usefulapi.io/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__freshdesk__freshdesk_list_tickets",
"mcp__freshdesk__freshdesk_get_ticket",
"mcp__freshdesk__freshdesk_search_tickets",
"mcp__freshdesk__freshdesk_list_ticket_conversations",
"mcp__freshdesk__freshdesk_list_contacts",
"mcp__freshdesk__freshdesk_get_contact",
"mcp__freshdesk__freshdesk_search_contacts",
"mcp__freshdesk__freshdesk_list_companies",
"mcp__freshdesk__freshdesk_get_company",
"mcp__freshdesk__freshdesk_list_agents",
"mcp__freshdesk__freshdesk_get_agent",
"mcp__freshdesk__freshdesk_list_groups"
],
"ask": [],
"deny": [
"mcp__freshdesk__freshdesk_create_ticket",
"mcp__freshdesk__freshdesk_update_ticket",
"mcp__freshdesk__freshdesk_reply_ticket",
"mcp__freshdesk__freshdesk_add_note",
"mcp__freshdesk__freshdesk_create_contact",
"mcp__freshdesk__freshdesk_update_contact",
"mcp__freshdesk__freshdesk_create_company"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as freshdesk. Review it before you use it.
Capability tags behind 9 rules
- mcp__freshdesk__freshdesk_list_tickets untrusted-input
- mcp__freshdesk__freshdesk_get_ticket untrusted-input
- mcp__freshdesk__freshdesk_search_tickets untrusted-input
- mcp__freshdesk__freshdesk_list_ticket_conversations private-data, untrusted-input
- mcp__freshdesk__freshdesk_list_contacts private-data
- mcp__freshdesk__freshdesk_get_contact private-data
- mcp__freshdesk__freshdesk_search_contacts private-data
- mcp__freshdesk__freshdesk_list_groups untrusted-input
- mcp__freshdesk__freshdesk_reply_ticket outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.usefulapi/freshdesk/verify?hash=aef8c9618a09418b3c7f68ef2c6c375a6844e0b230e71e1a0ad0341757b08872" | jq -e '.changed == false'Pinned hash aef8c9618a09, from Oct 25, 2026, 23:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.usefulapi/freshdesk/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.usefulapi/freshdesk)Source: MCP Registry · repository. Synced Nov 20, 2026, 20:18 UTC.
Freshdesk MCP by usefulapi: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Freshdesk MCP by usefulapi safe?
- No scan can promise that. What its definitions show: 19 tools, 7 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Freshdesk MCP by usefulapi delete data?
- Yes. 7 tools can delete, cancel or revoke something: freshdesk_create_ticket, freshdesk_update_ticket, freshdesk_reply_ticket, freshdesk_add_note, freshdesk_create_contact, freshdesk_update_contact and 1 more.
Can the Freshdesk MCP by usefulapi do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Freshdesk MCP by usefulapi have?
- 19 tools: 7 destructive, 12 read. freshdesk_create_ticket, freshdesk_update_ticket, freshdesk_reply_ticket, freshdesk_add_note, freshdesk_create_contact, freshdesk_update_contact, freshdesk_create_company, freshdesk_list_tickets and 11 more.
Does the Freshdesk MCP by usefulapi need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Freshdesk MCP by usefulapi send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): freshdesk_reply_ticket.
Has the Freshdesk MCP by usefulapi changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 25, 2026.