Connectors · Service desk & support

Freshworks Freshchat MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Freshworks Freshchat and the rest of your systems. It gives your agent 32 Freshworks Freshchat actions (19 reads, 11 writes and 2 that wait for a confirmation) and holds the Freshworks Freshchat credential itself, so the agent never does. It paces Freshworks Freshchat's limits and records every call.

Connect Freshworks Freshchat free See pricing

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp

32actionsin one signed file
19readlook, never change
11writecreate and update
2wait for a yesdestructive, confirmed first

Set up

Connect Freshworks Freshchat in three steps.

01
Add actionlake to Claude.
Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.
https://connect.actionlake.com/mcp
02
Connect Freshworks Freshchat.
Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.
- api_tokenFreshchat API token (Admin > Configure > API Tokens > Generate token)
- hostWhere your Freshworks Freshchat lives: your host
```
account { op: "connections.requirements", service: "freshchat" }
# free: exactly what to paste, and what is found for you
```

Make the first call. Check before a write.

Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

do    { action: "freshchat.agents.list" }# list agents · read · 1 upstream callcheck { action: "freshchat.agents.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Freshworks Freshchat at a glance

Sign-in: Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide: api_token
Setup fields: host
Limits we pace to: 1,000 calls an hour, per connection
API covered: Freshchat API v2, at your Freshworks Freshchat instance's API base URL, which you enter when connecting
Built from: Freshworks Freshchat's documentation, read 23 October 2026developers.freshchat.com
Service file: Version 1.0.0, signed (Ed25519)
Cached reads: 19 of 19 reads, for up to 1 minute; a write clears what it affects
Shared entities: 5, so ask can line Freshworks Freshchat up with your other systems
Data: Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Freshworks Freshchat.

32 actions in 13 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

19readlook, never change
11writecreate and update
2destructivewait for a confirmation

Users
7
4 read · 2 write · 1 destructive
List users by criteria · Create a user · Retrieve a user · Update a user
Agents
6
2 read · 3 write · 1 destructive
List agents · Create an agent · Retrieve an agent · Update an agent
Conversations
6
3 read · 3 write · 0 destructive
List messages in a conversation · Create a conversation · Send a message to a conversation · Retrieve a conversation
Metrics
2
2 read · 0 write · 0 destructive
Retrieve historical metrics · Retrieve instant metrics
Outbound messages
2
1 read · 1 write · 0 destructive
List outbound messages · Send WhatsApp outbound messages
Reports
2
1 read · 1 write · 0 destructive
Extract a raw report · Retrieve a raw report
Accounts
1
1 read · 0 write · 0 destructive
Retrieve account configuration
Agent statuses
1
1 read · 0 write · 0 destructive
List agent statuses

5 more areas · 5 actions

Business hours 1
Channels 1
Csat 1
Groups 1
Roles 1

Top actions

The Freshworks Freshchat API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 18 of Freshworks Freshchat's 18 action names are shared with at least one other connector, so an agent learns them once.

Action	What it does	Effect	Same name in
`freshchat.agents.list`List agents	List agents.	read	`identity.user.list`474 connectors
`freshchat.groups.list`List groups	List groups.	read	`identity.group.list`262 connectors
`freshchat.roles.list`List roles	List roles.	read	`identity.role.list`184 connectors
`freshchat.users.list`List users by criteria	List users by criteria.	read	`crm.contact.list`177 connectors
`freshchat.agents.create`Create an agent	Create an agent.	write	`identity.user.create`262 connectors
`freshchat.agents.delete`Delete an agent	Delete an agent.	destructive	`identity.user.delete`253 connectors
`freshchat.users.create`Create a user	Create a user.	write	`crm.contact.create`161 connectors
`freshchat.channels.list`List channels (topics)	List channels (topics).	read	`comm.channel.list`27 connectors
`freshchat.conversations.messages.list`List messages in a conversation	List messages in a conversation.	read	`comm.message.list`42 connectors
`freshchat.conversations.create`Create a conversation	Create a conversation.	write	`service.conversation.create`13 connectors
`freshchat.conversations.messages.create`Send a message to a conversation	Send a message to a conversation.	write	`comm.message.create`25 connectors
`freshchat.csat.create`Create a CSAT rating	Create a CSAT rating.	write	this connector

Try it

Prompts to paste into Claude.

Each one names the Freshworks Freshchat actions it will call, so you know what it reads and what it changes before you send it.

Readread
Find the Freshworks Freshchat contacts with no email address, so we can clean them up.
callsfreshchat.users.list
Writewrite
Create an agent in Freshworks Freshchat. Show me exactly what you will send before you save it.
callsfreshchat.agents.create
Across systemsread
Which contacts are in both Freshworks Freshchat and HaloPSA, and how many are in only one of them?
callsfreshchat.users.listhalopsa.users.list

Across your systems

Freshworks Freshchat, joined to the rest of your business.

One ask fetches from Freshworks Freshchat and another system, joins the rows on the same customer on our side, and hands your agent the answer, not every row.

Which contacts are in both Freshworks Freshchat and HaloPSA, and how many are in only one of them?
freshchat.users.list + halopsa.users.list, on crm.contact · HaloPSA
Which contacts are in both Freshworks Freshchat and NetSuite, and how many are in only one of them?
freshchat.users.list + netsuite.views.contacts, on crm.contact · NetSuite

Also mapped by other connectorsidentity.user 517identity.group 239crm.contact 192identity.role 107comm.channel 21

ask

ask {  intent: "which contacts are in both Freshworks Freshchat and HaloPSA, and how many are in only one of them",  steps: [    { action: "freshchat.users.list", as: "people", input: {}, limit: 100, max_pages: 5 },    { action: "halopsa.users.list", as: "people2", input: {}, limit: 100, max_pages: 5 },    { join: {        left: "people",        right: "people2",        on: "crm.contact",        group_by: "people.email",        select: ["people.email", "count(people2.id) as in_halopsa"]    } }  ]}

Example. Run it through check first: it validates the steps and prices them, and it is free.

Governance for Freshworks Freshchat

Destructive actions wait for a yes.

2 Freshworks Freshchat actions are destructive. These are all of them:

Delete an agentfreshchat.agents.delete
Delete a userfreshchat.users.delete

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

dofreshchat.agents.deleteconfirm_policy: human

Delete an agent?

intent: the user asked me to delete an agent

run suspended · waiting for a named person · key freshchat-agent cannot confirm itself

In the console, or from an emailed signed link.

a key for this connector

account {  op: "keys.create", name: "freshchat-agent",  allowed_actions: ["freshchat.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "freshchat.agents.delete", approver: "[email protected]" },    { match: "freshchat.users.delete", approver: "[email protected]" }  ]}

Illustrative. Scoped to Freshworks Freshchat only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Freshworks Freshchat costs on actionlake.

Every Freshworks Freshchat action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Freshworks Freshchat refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

1upstream call per actionall 32 Freshworks Freshchat actions
32actions pageeach page of a long list is one call
19reads can be cacheda cache hit costs nothing
100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every Freshworks Freshchat action.

32 actions by area: the id your agent calls, what it does, and its effect.

Users7

freshchat.users.conversations.listList a user's conversationsread
freshchat.users.createCreate a userwrite
freshchat.users.deleteDelete a userdestructive
freshchat.users.fetchRetrieve a subset of users by IDread
freshchat.users.getRetrieve a userread
freshchat.users.listList users by criteriaread
freshchat.users.updateUpdate a userwrite

Agents6

freshchat.agents.createCreate an agentwrite
freshchat.agents.deleteDelete an agentdestructive
freshchat.agents.getRetrieve an agentread
freshchat.agents.listList agentsread
freshchat.agents.status.updateUpdate an agent's statuswrite
freshchat.agents.updateUpdate an agentwrite

Conversations6

freshchat.conversations.createCreate a conversationwrite
freshchat.conversations.fields.listList conversation propertiesread
freshchat.conversations.getRetrieve a conversationread
freshchat.conversations.messages.createSend a message to a conversationwrite
freshchat.conversations.messages.listList messages in a conversationread
freshchat.conversations.updateUpdate a conversationwrite

Metrics2

freshchat.metrics.historical.getRetrieve historical metricsread
freshchat.metrics.instant.getRetrieve instant metricsread

Outbound messages2

freshchat.outbound_messages.listList outbound messagesread
freshchat.outbound_messages.whatsapp.sendSend WhatsApp outbound messageswrite

Reports2

freshchat.reports.raw.createExtract a raw reportwrite
freshchat.reports.raw.getRetrieve a raw reportread

Accounts1

freshchat.accounts.configuration.getRetrieve account configurationread

Agent statuses1

freshchat.agent_statuses.listList agent statusesread

Business hours1

freshchat.business_hours.within.getCheck business hoursread

Channels1

freshchat.channels.listList channels (topics)read

Csat1

freshchat.csat.createCreate a CSAT ratingwrite

Groups1

freshchat.groups.listList groupsread

Roles1

freshchat.roles.listList rolesread

Questions

The Freshworks Freshchat MCP server, answered.

Is there a Freshworks Freshchat MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 32 Freshworks Freshchat actions across users, agents, conversations and metrics, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Freshworks Freshchat.

What do I need to connect Freshworks Freshchat?

Freshchat API token (Admin > Configure > API Tokens > Generate token). Plus your host. The free call account { op: "connections.requirements", service: "freshchat" } lists exactly what to paste.

Can an AI agent delete or change things in Freshworks Freshchat?

Only if its key allows it, and only with an explicit confirmation. 2 Freshworks Freshchat actions are destructive, including delete an agent and delete a user. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my Freshworks Freshchat API limit?

actionlake paces every call to the limits in the Freshworks Freshchat service file: 1,000 calls an hour per connection. Repeated reads are answered from cache (19 Freshworks Freshchat actions can be), which never reaches Freshworks Freshchat.

What does a Freshworks Freshchat action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (32 Freshworks Freshchat actions page). Cache hits, searches, dry runs and calls Freshworks Freshchat refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which Freshworks Freshchat API does it cover?

The Freshchat API v2 at your Freshworks Freshchat instance's API base URL, which you enter when connecting. It is built from Freshworks Freshchat's documentation as read on 23 October 2026. 32 actions in 13 areas, each one in the signed service file (version 1.0.0).

Can I combine Freshworks Freshchat with my other systems?

Yes. ask joins Freshworks Freshchat to HaloPSA or NetSuite on the same customer and returns the answer rather than every row. Freshworks Freshchat maps crm.contact, which 192 other connectors also map.

Does actionlake keep my Freshworks Freshchat data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 1 minute, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Freshworks Freshchat credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

Give your agent Freshworks Freshchat today.

Connect Freshworks Freshchat free See pricing

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.

Freshworks Freshchat MCP server for AI agents.

Connect Freshworks Freshchat in three steps.

Add actionlake to Claude.

Connect Freshworks Freshchat.

Make the first call. Check before a write.

What an AI agent can do in Freshworks Freshchat.

Users

Agents

Conversations

Metrics

Outbound messages

Reports

Accounts

Agent statuses