Name: Freshdesk
Author: usefulapi

Freshdesk MCP

Read tickets, contacts, companies, agents and groups; create, update and reply to tickets.

Tool-list grade A Remote · Streamable HTTP No auth needed 19 tools v1.11.1

No reviews yet by usefulapiGitHub The publisher’s own endpoint — this marketplace is not in the path

93/100

tool-list score

tools declared

remote

at its publisher

—

calls last 7d

What it does

Read tickets, contacts, companies, agents and groups; create, update and reply to tickets.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http usefulapi-freshdesk-mcp https://freshdesk.usefulapi.io/mcp

# 2 — ask your agent for something these tools do
#   freshdesk_list_tickets, freshdesk_get_ticket, freshdesk_search_tickets and 16 more

Freshdesk costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

usefulapi334 servers

24 categories

All 334 servers

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

List/filter tickets (max page 300). Freshdesk REST: GET /tickets.

Parameter	Type	Required	Notes
filter	string	no	Predefined filter: new_and_my_open, watching, spam, or deleted.
requester_id	integer	no	Filter by requester (contact) id.
email	string	no	Filter by requester email.
company_id	integer	no	Filter by company id.
updated_since	string	no	Only tickets updated after this ISO 8601 timestamp.
order_by	string	no	Sort field: created_at, due_by, updated_at, or status.
order_type	string	no	Sort direction: asc or desc.
include	string	no	Embed extra data, comma-separated, e.g. "requester,stats,description".
per_page	integer	no	Results per page (1-100, max 100, default 30).
page	integer	no	Page number for pagination (1-based).

Get a single ticket by id. Freshdesk REST: GET /tickets/{id}.

Parameter	Type	Required	Notes
id	integer	yes	The ticket id.
include	string	no	Embed extra data, comma-separated: conversations, requester, company, stats.

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.

Parameter	Type	Required	Notes
query	string	yes	Freshdesk search query, e.g. "priority:3 AND status:2" (do NOT add surrounding quotes yourself — they are added for you).
page	integer	no	Page number (1-10; search endpoints return 30 results per page and ignore per_page).

List the conversations (replies and notes) on a ticket. Freshdesk REST: GET /tickets/{id}/conversations.

Parameter	Type	Required	Notes
id	integer	yes	The ticket id.
per_page	integer	no	Results per page (1-100, max 100, default 30).
page	integer	no	Page number for pagination (1-based).

List/filter contacts. Freshdesk REST: GET /contacts.

Parameter	Type	Required	Notes
email	string	no	Filter by email.
mobile	string	no	Filter by mobile number.
phone	string	no	Filter by phone number.
company_id	integer	no	Filter by company id.
updated_since	string	no	Only contacts updated after this ISO 8601 timestamp.
state	string	no	Filter by state: verified, unverified, blocked, or deleted.
per_page	integer	no	Results per page (1-100, max 100, default 30).
page	integer	no	Page number for pagination (1-based).

Get a single contact by id. Freshdesk REST: GET /contacts/{id}.

Parameter	Type	Required	Notes
id	integer	yes	The contact id.

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.

Parameter	Type	Required	Notes
query	string	yes	Freshdesk search query, e.g. "company_id:123" (do NOT add surrounding quotes yourself — they are added for you).
page	integer	no	Page number (1-10; search endpoints return 30 results per page and ignore per_page).

List companies. Freshdesk REST: GET /companies.

Parameter	Type	Required	Notes
per_page	integer	no	Results per page (1-100, max 100, default 30).
page	integer	no	Page number for pagination (1-based).

Get a single company by id. Freshdesk REST: GET /companies/{id}.

Parameter	Type	Required	Notes
id	integer	yes	The company id.

List/filter agents. Freshdesk REST: GET /agents.

Parameter	Type	Required	Notes
email	string	no	Filter by email.
mobile	string	no	Filter by mobile number.
phone	string	no	Filter by phone number.
state	string	no	Filter by state: fulltime or occasional.
per_page	integer	no	Results per page (1-100, max 100, default 30).
page	integer	no	Page number for pagination (1-based).

Get a single agent by id. Freshdesk REST: GET /agents/{id}.

Parameter	Type	Required	Notes
id	integer	yes	The agent id.

List groups (agent groups tickets are routed to). Freshdesk REST: GET /groups.

Parameter	Type	Required	Notes
per_page	integer	no	Results per page (1-100, max 100, default 30).
page	integer	no	Page number for pagination (1-based).

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.

Parameter	Type	Required	Notes
subject	string	yes	Ticket subject (required).
description	string	yes	Ticket description, HTML content (required).
email	string	no	Requester email (one of email/requester_id/phone required).
requester_id	integer	no	Requester (contact) id (one of email/requester_id/phone required).
phone	string	no	Requester phone (one of email/requester_id/phone required).
status	integer	no	Ticket status: 2=Open, 3=Pending, 4=Resolved, 5=Closed.
priority	integer	no	Ticket priority: 1=Low, 2=Medium, 3=High, 4=Urgent.
source	integer	no	Ticket source: 1=Email, 2=Portal, 3=Phone, 7=Chat, 9=Feedbackwidget, 10=Outbound email.
type	string	no	Ticket type (e.g. Question, Incident).
tags	array	no	Tags (array of strings).
cc_emails	array	no	Emails to CC on the ticket.
group_id	integer	no	Id of the group to assign the ticket to.
responder_id	integer	no	Id of the agent the ticket is assigned to.
company_id	integer	no	Id of the company the ticket belongs to.
custom_fields	object	no	Custom field values, keyed by field name.

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}.

Parameter	Type	Required	Notes
id	integer	yes	The ticket id to update.
subject	string	no	Ticket subject.
description	string	no	Ticket description, HTML content.
status	integer	no	Ticket status: 2=Open, 3=Pending, 4=Resolved, 5=Closed.
priority	integer	no	Ticket priority: 1=Low, 2=Medium, 3=High, 4=Urgent.
source	integer	no	Ticket source: 1=Email, 2=Portal, 3=Phone, 7=Chat, 9=Feedbackwidget, 10=Outbound email.
type	string	no	Ticket type.
tags	array	no	Tags (array of strings).
group_id	integer	no	Id of the group to assign the ticket to.
responder_id	integer	no	Id of the agent the ticket is assigned to.
company_id	integer	no	Id of the company the ticket belongs to.
requester_id	integer	no	Requester (contact) id.
custom_fields	object	no	Custom field values, keyed by field name.

Add a public reply to a ticket (sent to the requester). Freshdesk REST: POST /tickets/{id}/reply.

Parameter	Type	Required	Notes
id	integer	yes	The ticket id to reply to.
body	string	yes	The reply content, HTML (required).
cc_emails	array	no	Emails to CC on the reply.
bcc_emails	array	no	Emails to BCC on the reply.

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.

Parameter	Type	Required	Notes
id	integer	yes	The ticket id to add a note to.
body	string	yes	The note content, HTML (required).
private	boolean	no	Whether the note is internal/private (default true). Set false for a public note.
notify_emails	array	no	Agent emails to notify about this note.

Create a contact. name is required. Freshdesk REST: POST /contacts.

Parameter	Type	Required	Notes
name	string	yes	The contact's full name (required).
email	string	no	Email address.
phone	string	no	Phone number.
mobile	string	no	Mobile number.
company_id	integer	no	Id of the company the contact belongs to.
job_title	string	no	Job title.
address	string	no	Postal address.
description	string	no	Freeform description / notes.
tags	array	no	Tags (array of strings).
twitter_id	string	no	Twitter handle.
unique_external_id	string	no	External id from your own system.
custom_fields	object	no	Custom field values, keyed by field name.

Update fields on an existing contact. Only provided fields are changed. Freshdesk REST: PUT /contacts/{id}.

Parameter	Type	Required	Notes
id	integer	yes	The contact id to update.
name	string	no	The contact's full name.
email	string	no	Email address.
phone	string	no	Phone number.
mobile	string	no	Mobile number.
company_id	integer	no	Id of the company the contact belongs to.
job_title	string	no	Job title.
address	string	no	Postal address.
description	string	no	Freeform description / notes.
tags	array	no	Tags (array of strings).
custom_fields	object	no	Custom field values, keyed by field name.

Create a company. name is required. Freshdesk REST: POST /companies.

Parameter	Type	Required	Notes
name	string	yes	The company name (required).
description	string	no	Freeform description / notes.
domains	array	no	Email domains associated with the company.
note	string	no	A note about the company.
custom_fields	object	no	Custom field values, keyed by field name.

Free

$0 forever

Every tool — any call limit is its publisher’s, not ours
No card, and mcprush charges nothing for it
Runs at its publisher’s own address — this marketplace is not in the path
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Freshdesk or to call it, at any volume.

ATool-list grade · score 93 / 100

Release 1.11.1 · scanned 20 Oct 2026

Graded from the tools this server lists, not from its source code.

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score93

Findings0 threat · 0 capability

Capabilitymoderate

Coveragemanifest

Verificationnot in this report

Surface digestd820a9b603dd2253d922b4d48ae52e7061c4c3209546a72a1d18c78739f7c09d

Score vectorthreat 100 → client 93

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
coverage-honesty	manifest	inspection depth (manifest) — how much of the target the scan could see	−4

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.

Tool surfaceread

Implementation sourcenot available

Package metadatanot available

Live transportnot available

The implementation source was not read — this reflects the declared tool metadata only.

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
freshdesk_list_tickets	no tags
freshdesk_get_ticket	no tags
freshdesk_search_tickets	no tags
freshdesk_list_ticket_conversations	no tags
freshdesk_list_contacts	no tags
freshdesk_get_contact	no tags
freshdesk_search_contacts	no tags
freshdesk_list_companies	no tags
freshdesk_get_company	no tags
freshdesk_list_agents	no tags
freshdesk_get_agent	no tags
freshdesk_list_groups	no tags
freshdesk_create_ticket	state-write	state-write: declares destructiveHint: true
freshdesk_update_ticket	state-write	state-write: declares destructiveHint: true
freshdesk_reply_ticket	state-write	state-write: declares destructiveHint: true
freshdesk_add_note	state-write	state-write: declares destructiveHint: true
freshdesk_create_contact	state-write	state-write: declares destructiveHint: true
freshdesk_update_contact	state-write	state-write: declares destructiveHint: true
freshdesk_create_company	state-write	state-write: declares destructiveHint: true

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digestd820a9b603dd2253

Scanned2026-10-20

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.

Where are you running it?

Tool surface

Release history

Freshdesk MCP

What it does

Quickstart

Where are you running it?

Tool surface

What counts against your monthly calls

What the scan could actually read

Capability — what it could do if the model were manipulated

Toxic-flow graph

Supply chain and provenance

Release history

See also