[Cotlet](https://cotlet.dev/index.md) · [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Use cases](https://cotlet.dev/use-cases.md) · [Security](https://cotlet.dev/security.md) · [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) · [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [Contact](https://cotlet.dev/contact.md) · [Pricing](https://cotlet.dev/pricing.md) · [Sign up](https://cotlet.dev/signup) # Freshchat API and MCP server > Freshchat has a REST API (v2) but no official MCP server (checked 22 Oct 2026). Freshworks' MCP integration covers Freshdesk and Freshservice, and its docs do not list Freshchat. The API needs an admin-generated token that expires, and it has no endpoint that lists the inbox. Live chat and messaging inbox from Freshworks: conversations from your website and apps go to agents and groups, with bots, canned responses, labels and reports. ## What is the Freshchat API? Cotlet's Freshchat API exposes 11 endpoints for your own Freshchat account: list conversations, get conversation, list agents, list groups, list canned responses, list conversation labels, list assignment rules, get CSAT report, send reply, assign conversation and resolve conversation. The list_conversations endpoint returns conversations in the Inbox with status, waiting state, assignee and last message. Each endpoint takes simple JSON inputs like conversation_id, group_id or agent_id and works both as an operation of the freshchat_read or freshchat_write MCP tool for agents and as a REST call for scripts. - **Category:** [Customer support](https://cotlet.dev/integrations/category/customer-support.md) - **Endpoints:** 11 (8 read, 3 write) - **Updated:** 2026-10-21 Freshchat has a REST API (v2) but no official MCP server (checked 22 Oct 2026). Cotlet is a hosted MCP server and REST API for Freshchat with 11 endpoints (8 read, 3 write): you sign in once in your own cloud browser, your AI agent does the work. ## Does Freshchat have an official API? Freshchat has a REST API (v2) but no official MCP server (checked 22 Oct 2026). Freshworks' MCP integration covers Freshdesk and Freshservice, and its docs do not list Freshchat. The API needs an admin-generated token that expires, and it has no endpoint that lists the inbox. | Task | Freshchat official | Cotlet | |---|---|---| | List the inbox by status or waiting time | Partly: API gets one conversation by ID or a user's conversation IDs; no inbox list | Yes | | Read a conversation with its messages | Yes: API: conversation and messages endpoints, paged | Yes | | Send a reply to the customer | Yes: API: post a message to a conversation; no MCP server for agents | Yes | | Assign a conversation to an agent or group | Yes: API: assigned_agent_id and assigned_group_id on the conversation | Yes | | Resolve a conversation with a label | Partly: API sets the status; labels chosen at resolve are not among its update fields | Yes | | List agents and groups | Yes: API: agents and groups endpoints | Yes | | List canned responses | No: Not in the API endpoints we checked | Yes | | Read the CSAT report | Partly: API has a per-conversation CSAT endpoint and a raw report extract | Yes | Sources: [Freshchat API reference](https://developers.freshchat.com/api/), [Freshdesk Support: Model Context Protocol (MCP) integration in Freshdesk](https://support.freshdesk.com/support/solutions/articles/50000012670-model-context-protocol-mcp-integration-in-freshdesk-eap-), [Freshchat Help: Assign conversations to agents](https://support.freshchat.com/support/solutions/articles/50000000076-assign-conversations-to-agents), [Freshchat Help: Roles and permissions](https://support.freshchat.com/support/solutions/articles/50000000105-roles-and-permissions) ## For AI agents ```text Freshchat has a REST API (v2) but no official MCP server (checked 22 Oct 2026). Freshworks' MCP integration covers Freshdesk and Freshservice, and its docs do not list Freshchat. The API needs an admin-generated token that expires, and it has no endpoint that lists the inbox. Cotlet provides a hosted MCP server and REST API for Freshchat: 11 tools (8 read, 3 write). Access Sign up at https://cotlet.dev/app/signup?app=freshchat, then request the app and create API keys in the Cotlet console. MCP server https://cotlet.dev/mcp/v1 MCP tools freshchat_read, freshchat_write, reads and writes apart; call one with {"operation": "", "arguments": {...}} REST base https://cotlet.dev/api/v1/freshchat, each operation at its own route, e.g. POST /api/v1/freshchat/conversations/{conversation_id}/assign Auth Authorization: Bearer . Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in. Operations list_conversations, get_conversation, list_agents, list_groups, list_canned_responses, list_conversation_labels, list_assignment_rules, get_csat_report, send_reply, assign_conversation, resolve_conversation Confirm send_reply, resolve_conversation (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations) Markdown https://cotlet.dev/integrations/freshchat-api-mcp-server.md How access works: 1. The user signs up at https://cotlet.dev/app/signup?app=freshchat, requests Freshchat in the Cotlet console and creates an API key there. 2. The user signs in to Freshchat once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Freshchat for agents. An agent cannot do this step. 3. The API key goes into the MCP client or the REST call as a bearer token. Fits: people who want a hosted Freshchat server that someone else maintains, including non-developers. Policy: Cotlet never stores passwords, never solves CAPTCHAs, never bypasses MFA. Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev. Sign-in: the user signs in to Freshchat in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get Freshchat only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273). API key: holds no Freshchat login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once. Terms: the user stays responsible for following Freshchat's terms; Cotlet is not affiliated with Freshchat. ``` ## What can an AI agent do in Freshchat? Cotlet is best for support leads and admins who want an AI agent to route, answer and label Freshchat conversations without running or fixing a server. - **[Assign new conversations to the right team](https://cotlet.dev/integrations/freshchat-api-mcp-server/assign-new-conversations.md)** (runs: daily): "List the new, unassigned Freshchat conversations. Send billing questions to the Billing group, bugs to Support, and leave anything unclear for me with a one-line reason." → `list_conversations`, `list_groups`, `list_agents`, `assign_conversation` - **[Resolve idle conversations with a label](https://cotlet.dev/integrations/freshchat-api-mcp-server/resolve-idle-conversations.md)** (runs: daily): "Find assigned Freshchat conversations where we replied last and the customer has been silent for a day. Resolve each with the label that fits, and skip anything with an open question." → `list_conversations`, `get_conversation`, `list_conversation_labels`, `resolve_conversation` - **[Answer waiting chats from your canned responses](https://cotlet.dev/integrations/freshchat-api-mcp-server/answer-waiting-chats.md)** (runs: daily): "Find Freshchat conversations still waiting for a first reply. Where one of our canned responses answers the question, send it with a short personal line, and list the rest for me." → `list_conversations`, `get_conversation`, `list_canned_responses`, `send_reply` - **Weekly CSAT report by agent** (runs: weekly): "Every Monday, read last week's Freshchat CSAT ratings, give the average per agent and list the conversations rated one or two stars with the customer's comment." → `get_csat_report`, `get_conversation` ## Can Freshchat automations run on a schedule in n8n, Make or Zapier? Yes. Cotlet does not replace your automation platform: it gives it a Freshchat connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to assign new conversations to the right team, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off. | Where | How to connect | How to schedule | |---|---|---| | Your AI agent | Add https://cotlet.dev/mcp/v1 with your API key. | A scheduled agent run, for example a Claude Code routine. | | n8n | MCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/freshchat/conversations. | Schedule Trigger node. | | Make | HTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH. | Scenario schedule. | | Zapier | Webhooks by Zapier, Custom Request: the same method, URL, header and body. | Schedule by Zapier trigger. | | Your own script | GET https://cotlet.dev/api/v1/freshchat/conversations with your API key. | cron or GitHub Actions. | ## Tools **For AI agents:** Every endpoint and its schema is public. The 11 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to Freshchat. ### list_conversations Conversations in the Inbox with status, waiting state, assignee and last message. Access: read. REST: `GET /api/v1/freshchat/conversations`. MCP: `freshchat_read → list_conversations`. | Parameter | Type | Required | Description | |---|---|---|---| | `status` | enum | no | new, assigned, resolved or reopened. Default: all. | | `waiting` | enum | no | first_response_due, response_due or no_response_due. | | `group_id` | string | no | Only conversations assigned to this group, from list_groups. | | `agent_id` | string | no | Only conversations assigned to this agent, from list_agents. | | `limit` | integer | no | Conversations per page. | | `cursor` | string | no | Next page cursor from the previous call. | Returns conversations from the Inbox, newest activity first, in pages; pass next_cursor back as cursor for the next page. status filters by new, assigned, resolved or reopened. waiting filters by Freshchat's Priority Inbox state: first_response_due, response_due or no_response_due. group_id and agent_id narrow it to one team or person. Each row has the conversation_id the other tools take. It reads the Inbox as your account sees it. Example response: ```json { "conversations": [ { "conversation_id": "7c1e5a90-3b2d-4f68-a4c1-9e0d2b6f8a31", "customer": "Priya Nair", "status": "new", "waiting": "first_response_due", "assigned_group": null, "assigned_agent": null, "last_message": "Hi, I was charged twice for October.", "last_message_at": "2026-10-22T06:41:00Z" }, { "conversation_id": "e2a7c4b1-8d3f-4e59-b6a0-1f9c3d5e7a82", "customer": "Tom Becker", "status": "assigned", "waiting": "first_response_due", "assigned_group": "Support", "assigned_agent": "Dana Reed", "last_message": "How do I change my password?", "last_message_at": "2026-10-22T07:05:00Z" } ], "next_cursor": null } ``` ### get_conversation One conversation with its messages, assignee, labels and status. Access: read. REST: `GET /api/v1/freshchat/conversations/{conversation_id}`. MCP: `freshchat_read → get_conversation`. | Parameter | Type | Required | Description | |---|---|---|---| | `conversation_id` | string | yes | Conversation ID from list_conversations. | Returns the messages of one conversation in order, who wrote each (customer, agent or bot), the status, the assignee and any label already applied. Use it before you reply, assign or resolve, because the Inbox changes while you read it. Private notes between agents are marked as such. Images and files in messages come back as links, not content. Example response: ```json { "conversation_id": "b3d9f1a2-6c4e-4a8b-95d7-2e1f0c8a7b64", "customer": "Lena Ortiz", "status": "assigned", "assigned_group": "Support", "assigned_agent": "Dana Reed", "label": null, "messages": [ { "from": "customer", "text": "Can you add CSV export to reports?", "at": "2026-10-20T09:12:00Z" }, { "from": "agent", "text": "Thanks, Lena. I passed it to the product team.", "at": "2026-10-20T09:20:00Z" } ] } ``` ### list_agents Agents of the account with role, group and current status. Access: read. REST: `GET /api/v1/freshchat/agents`. MCP: `freshchat_read → list_agents`. | Parameter | Type | Required | Description | |---|---|---|---| | `group_id` | string | no | Only agents of this group, from list_groups. | Returns the agents you can assign conversations to, each with the agent_id other tools take, the role, the groups they belong to and the status they set in Freshchat. Freshchat's default statuses are "Active on IntelliAssign" and "Unavailable", and an Admin can add custom ones. Use group_id to list one team. Example response: ```json { "agents": [ { "agent_id": "2f8a1c3e-9b47-4d60-a5e2-7c1d0b9f3a45", "name": "Dana Reed", "role": "Agent", "groups": [ "Support" ], "status": "Active on IntelliAssign" }, { "agent_id": "9d4b6e21-0a3c-47f8-b1e5-3a6c8d2f1b70", "name": "Marcus Hale", "role": "Admin", "groups": [ "Billing" ], "status": "In a Meeting" } ] } ``` ### list_groups Groups (teams) with their ID and member count. Access: read. REST: `GET /api/v1/freshchat/groups`. MCP: `freshchat_read → list_groups`. No parameters. Returns the groups of the account. Use group_id from here in assign_conversation and in the filters of list_conversations and list_agents. Groups are what Freshchat calls teams when conversations are assigned. Example response: ```json { "groups": [ { "group_id": "4d5e6f70-1a2b-4c3d-8e9f-0a1b2c3d4e5f", "name": "Billing", "members": 3 }, { "group_id": "0b1c2d3e-4f50-4a6b-8c7d-9e0f1a2b3c4d", "name": "Support", "members": 6 } ] } ``` ### list_canned_responses Saved replies with title, shortcode, folder and body. Access: read. REST: `GET /api/v1/freshchat/canned-responses`. MCP: `freshchat_read → list_canned_responses`. | Parameter | Type | Required | Description | |---|---|---|---| | `query` | string | no | Text to find in titles and shortcodes. | Returns the canned responses your account can use: its personal folders and the shared folders. Each has the title, the shortcode an agent types after "/", the folder and the reply body. Use query to search titles and shortcodes. Freshchat shows the library under Admin > Canned Responses. Example response: ```json { "canned_responses": [ { "title": "How to change a password", "shortcode": "pswd", "folder": "Account (shared)", "body": "To change your password open Settings, choose Security and click Reset password." }, { "title": "Where is my invoice", "shortcode": "invoice", "folder": "Billing (shared)", "body": "You can download invoices under Billing > History." } ] } ``` ### list_conversation_labels Label categories with their sub-categories and which are mandatory. Access: read. REST: `GET /api/v1/freshchat/conversation-labels`. MCP: `freshchat_read → list_conversation_labels`. No parameters. Returns the conversation labels an agent picks when resolving, with each category's sub-categories and whether a sub-category is mandatory. Use the names from here as label and sub_category in resolve_conversation. Only an Account Owner or Admin creates labels, in Admin > Conversation Labels. Example response: ```json { "labels": [ { "label": "Feature Request", "sub_categories": [ "Export to CSV", "Dark mode" ], "mandatory": false }, { "label": "Bug Report", "sub_categories": [ "Login error", "Payment error" ], "mandatory": true }, { "label": "Happy Customer", "sub_categories": [], "mandatory": false } ] } ``` ### list_assignment_rules Assignment Rules in order, with their conditions and the agent or group they assign to. Access: read. REST: `GET /api/v1/freshchat/assignment-rules`. MCP: `freshchat_read → list_assignment_rules`. No parameters. Returns the rules from Admin > Assignment Rules in the order Freshchat applies them: the highest rule wins when several match, and rules run before IntelliAssign. Each rule shows its If conditions (message content, URL, source, visitor attributes, business hours or browser language) and its Then action. Use it to see what a rule already assigns before you route by hand. It needs an Admin or Account Owner. Example response: ```json { "rules": [ { "position": 1, "name": "Refunds and payments", "enabled": true, "conditions": [ "Message contains \"refund\" or \"payment\"" ], "assign_to": { "group": "Billing" } }, { "position": 2, "name": "French visitors", "enabled": true, "conditions": [ "Browser language is French" ], "assign_to": { "group": "Support FR" } } ] } ``` ### get_csat_report Customer ratings per conversation with the agent, the stars and the comment. Access: read. REST: `GET /api/v1/freshchat/csat-report`. MCP: `freshchat_read → get_csat_report`. | Parameter | Type | Required | Description | |---|---|---|---| | `from` | date | no | First day of the range. | | `to` | date | no | Last day of the range. | | `agent_id` | string | no | Only ratings for this agent, from list_agents. | | `cursor` | string | no | Next page cursor from the previous call. | Returns the rows of Reports > Customer Satisfaction for a date range: customer name, the agent who handled the conversation, the rating, the customer's comment if there is one and the conversation_id. The survey uses five stars. Freshchat limits Reports to Account Owner and Admin roles, so other accounts cannot call it. Example response: ```json { "ratings": [ { "conversation_id": "b3d9f1a2-6c4e-4a8b-95d7-2e1f0c8a7b64", "customer": "Lena Ortiz", "agent": "Dana Reed", "stars": 5, "comment": "Quick and clear." }, { "conversation_id": "5a9c3e71-2d4b-4f08-b6a1-8e0d7c2f9b13", "customer": "Sam Okafor", "agent": "Marcus Hale", "stars": 2, "comment": "Had to explain twice." } ], "next_cursor": null } ``` ### send_reply Send a text reply to the customer in a conversation. Access: write, asks the user first. REST: `POST /api/v1/freshchat/conversations/{conversation_id}/replies`. MCP: `freshchat_write → send_reply`. | Parameter | Type | Required | Description | |---|---|---|---| | `conversation_id` | string | yes | Conversation ID from list_conversations. | | `body` | string | yes | Text of the reply. | Posts one text message to the customer in the conversation, as the signed-in agent. It sends text only: images and files are not uploaded. A sent message cannot be deleted through Cotlet. Read the conversation with get_conversation right before, so you do not answer a chat a colleague already answered. By default you confirm each call; you can switch that off for this tool. Example response: ```json { "message_id": "3f6a8c1d-7e2b-4d95-a0c4-6b1e9d2f5a78", "conversation_id": "e2a7c4b1-8d3f-4e59-b6a0-1f9c3d5e7a82", "status": "sent", "sent_at": "2026-10-22T07:31:00Z" } ``` ### assign_conversation Assign a conversation to an agent or a group. Access: write. REST: `POST /api/v1/freshchat/conversations/{conversation_id}/assign`. MCP: `freshchat_write → assign_conversation`. | Parameter | Type | Required | Description | |---|---|---|---| | `conversation_id` | string | yes | Conversation ID from list_conversations. | | `agent_id` | string | no | Agent from list_agents. | | `group_id` | string | no | Group from list_groups. | Sets the assignee of one conversation to an agent_id, a group_id or both. It needs an Account Owner or Admin, because Freshchat limits assigning to those roles. Assigning reaches no customer and is undone with one call, so it does not wait for your OK. Assignment Rules and IntelliAssign still handle new conversations on their own; this call overrides the current assignee. Example response: ```json { "conversation_id": "7c1e5a90-3b2d-4f68-a4c1-9e0d2b6f8a31", "status": "assigned", "assigned_group": { "group_id": "4d5e6f70-1a2b-4c3d-8e9f-0a1b2c3d4e5f", "name": "Billing" }, "assigned_agent": null } ``` ### resolve_conversation Resolve a conversation and apply a label. Access: write, asks the user first. REST: `POST /api/v1/freshchat/conversations/{conversation_id}/resolve`. MCP: `freshchat_write → resolve_conversation`. | Parameter | Type | Required | Description | |---|---|---|---| | `conversation_id` | string | yes | Conversation ID from list_conversations. | | `label` | string | no | Label category from list_conversation_labels. | | `sub_category` | string | no | Sub-category of that label. | Sets the conversation to resolved, like the Resolve button in the Inbox, and applies the label and sub-category you pass. A label that is mandatory in Freshchat needs its sub-category here too. When Customer Satisfaction is enabled, Freshchat shows the survey to the customer as the conversation closes, so this call can reach the customer. By default you confirm each call; you can switch that off for this tool. Example response: ```json { "conversation_id": "b3d9f1a2-6c4e-4a8b-95d7-2e1f0c8a7b64", "status": "resolved", "label": "Feature Request", "sub_category": "Export to CSV", "resolved_at": "2026-10-22T07:40:00Z" } ``` ## How do I connect Freshchat to Claude Code, Codex or Cursor? Connecting Freshchat takes three steps: sign up, sign in to Freshchat once in your Cloud Browser and enable it for agents, then add one MCP server or call the REST API with the same key. ### Connect Freshchat to your agent. 1. **Create an account** Sign up and add Freshchat in the console. Your API key is there too. 2. **Sign in to Freshchat in your Cloud Browser** Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Freshchat there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off. 3. **Add Cotlet to your agent** Paste the snippet for your client. The same server and key serve every app you connect, so you do this once. Claude Code: ``` claude mcp add --transport http cotlet \ https://cotlet.dev/mcp/v1 \ --header "Authorization: Bearer $COTLET_API_KEY" ``` Cursor: ``` { "mcpServers": { "cotlet": { "url": "https://cotlet.dev/mcp/v1", "headers": { "Authorization": "Bearer ${COTLET_API_KEY}" } } } } ``` Codex: ``` # ~/.codex/config.toml [mcp_servers.cotlet] url = "https://cotlet.dev/mcp/v1" bearer_token_env_var = "COTLET_API_KEY" ``` 4. **Ask your agent** Ask in plain words. Your agent finds the Freshchat tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool. ``` List the new, unassigned Freshchat conversations. Send billing questions to the Billing group, bugs to Support, and leave anything unclear for me with a one-line reason. ``` ### Call Freshchat from your scripts. 1. **Export your API key** Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code. ``` export COTLET_API_KEY="cotlet_..." ``` 2. **Call a tool** Every tool is an endpoint under /api/v1/freshchat with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise. ``` curl -X POST https://cotlet.dev/api/v1/freshchat/conversations/1a4d7c0e-5b8f-4e23-9c6a-0d3f6b9e2a51/assign \ -H "Authorization: Bearer $COTLET_API_KEY" \ -H "Content-Type: application/json" \ -d '{"agent_id":"2f8a1c3e-9b47-4d60-a5e2-7c1d0b9f3a45"}' ``` 3. **Read the result** You get plain JSON back, ready for your script. A failed call costs nothing. ``` { "conversation_id": "1a4d7c0e-5b8f-4e23-9c6a-0d3f6b9e2a51", "status": "assigned", "assigned_group": null, "assigned_agent": { "agent_id": "2f8a1c3e-9b47-4d60-a5e2-7c1d0b9f3a45", "name": "Dana Reed" } } ``` ## Why use Cotlet for Freshchat? **Built for agents** - One MCP server for every app you connect. - The same tools as a REST API for scripts and cron jobs. - Works with Claude Code, Codex and Cursor. **Your login stays yours** - You sign in to Freshchat yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses. - A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory. - The model never sees a login. - No stored passwords, no CAPTCHA solving, no MFA bypass. **You stay in control** - Scope each API key: its apps, its tools, read only or read and write. - Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you. - Every background request listed in your Background activity. Disable for agents in one click. **Kept working for you** - We test every integration every 6 hours. - When Freshchat changes, the tool pauses until we fix it. - Failed calls cost nothing. ## Is it safe to connect Freshchat to Cotlet? Yes. You sign in to Freshchat yourself, in your own Cloud Browser, and we never save your password. Your agents only get Freshchat once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself. - **A+ on Qualys SSL Labs**: Encryption in transit: TLS setup and certificates, on all four server addresses. [Live result](https://www.ssllabs.com/ssltest/analyze.html?d=cotlet.dev) - **A+ on securityheaders.com**: Browser protections sent with every page, all six headers present. [Live result](https://securityheaders.com/?q=cotlet.dev&followRedirects=on) - **A+ on Mozilla Observatory**: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. [Live result](https://developer.mozilla.org/en-US/observatory/analyze?host=cotlet.dev) - **Clean on Sucuri SiteCheck**: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. [Live result](https://sitecheck.sucuri.net/results/cotlet.dev) [How Cotlet protects your access](https://cotlet.dev/security.md) ### Common concerns **Who runs Cotlet?** Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet. **Is this an official Freshchat integration?** No, Cotlet is independent of Freshchat. Freshchat's own API is too limited for this work. Cotlet works through your own Freshchat account, the way you use Freshchat in the browser, so you need no partner approval and no developer setup. **What about client data and GDPR?** Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it. **Can I start with read only?** Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool. **Is it reliable?** Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev. **How do I stop?** Press Disable for agents next to Freshchat in your console: your agents lose access at once and you stay signed in. Signing out of Freshchat in the browser works too, and Reset browser deletes the whole profile. ## Is there a Freshchat MCP server on GitHub? No community MCP server for Freshchat turned up in our check on 22 Oct 2026. The realistic option is to wrap the REST API yourself or through a hosted API connector: you generate an admin token, build the inbox listing the API lacks, and fix it when the API changes. Cotlet works in the signed-in app, so the inbox, canned responses and labels are covered, and our team maintains it. | | API wrapper | Cotlet | |---|---|---| | Setup | Generate an admin API token, build or install the MCP wrapper, add it to each MCP client | Sign up, sign in to Freshchat once, add one MCP server or API key | | When Freshchat changes | You or the wrapper's maintainer fix it | Our team tests it daily and fixes it for you; failed calls are free | | Your Freshchat access | An API token stored in your config; Freshchat tokens expire and need a new one | Your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click | | When access expires | Calls return 401 until you generate a new token | Your Cloud Browser keeps you signed in; if Freshchat logs you out, your agent gets a link to sign in again | | Upkeep | You run, monitor and update the wrapper | Nothing to host or update | | Where it runs | Wherever you host the wrapper | Hosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule | | Price | Free for the open parts, paid for with your time | Free 7-day trial, then pay-as-you-go credit packs, no subscription | ### Which one fits you **Pick Cotlet if** - you are not a developer, or you do not want to maintain a server - you need it to keep working when Freshchat changes, without checking it yourself - your agent or a script should run it on a schedule, also while your computer is off **Pick an open-source server if** - you are comfortable installing, updating and fixing it yourself - you want your sign-in to stay on your own computer - you only need it now and then, from one MCP client ## How much does the Freshchat API cost? Free 7-day trial with 2,000 credits, no card needed. After that, the Freshchat API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 20 to 30 credits (25 for most tools, about $0.10 to $0.15), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over. | Credits | Price, one time | Calls at 25 credits | Per 1,000 credits | |---|---|---|---| | 5,000 | $29 | 200 | $5.80 | | 15,000 | $79 | 600 | $5.27 | | 32,000 | $149 | 1,280 | $4.66 | | 60,000 | $249 | 2,400 | $4.15 | Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the `Authorization: Bearer` header. [See full pricing](https://cotlet.dev/pricing.md) ## How Cotlet holds your access Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Freshchat account. - **Company details:** Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. [Terms of service](https://cotlet.dev/terms) - **Your sign-in:** You sign in to Freshchat yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get Freshchat only after you enable it. When Freshchat signs you out, your agent gives you a link to sign in again. [Security](https://cotlet.dev/security.md) - **Revoking access:** Press Disable for agents next to Freshchat, sign out of Freshchat in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool. - **What we never do:** Store passwords, solve CAPTCHAs or bypass MFA. - **Freshchat's terms:** You use your own Freshchat account and stay responsible for following Freshchat's terms. Cotlet is independent and not affiliated with Freshchat. [Terms](https://cotlet.dev/terms) - **Contact:** Questions about the company, security or an app: [contact@cotlet.dev](mailto:contact@cotlet.dev) ## Frequently asked questions **How do I get access?** Sign up free, open Freshchat in the console and press Request access. Then you create your API key and connect Freshchat there. **Do I need to be technical?** No. You sign in to Freshchat once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix. **Is it safe to connect Freshchat to Cotlet?** Yes. You sign in to Freshchat yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Freshchat once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security. **Is a hosted server safer than a local one? My Freshchat sign-in would leave my computer.** On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your Freshchat cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off. **Why does Cotlet send requests instead of clicking in my browser?** To be fast, Cotlet doesn't click through Freshchat's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Freshchat sees the same browser and IP you signed in with, and every request is listed in your Background activity. **What if someone gets my Cotlet API key?** The key holds no Freshchat login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once. **Why a signed-in browser and not OAuth, like other integration platforms?** Freshchat offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273). **Which Freshchat role does my agent need?** It follows your role. Freshchat limits assigning conversations to the Account Owner and Admin roles, and limits Reports to those roles too. The Agent role can work conversations and open the People section. A call your role may not make is refused and the agent says so. **Does the Freshworks MCP server cover Freshchat?** No. Freshworks' MCP integration documents Freshdesk and Freshservice, and its docs do not list Freshchat (checked 22 Oct 2026). Freshchat conversations need their own connection, which is what Cotlet provides. **Can my agent post or send messages in Freshchat without asking me?** No. Every call to send_reply or resolve_conversation waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. assign_conversation runs without asking, because it sends nothing to anyone and one call undoes it. **Can I use the Freshchat API in n8n?** Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/freshchat from the HTTP Request node. --- Give your AI agents your signed-in browser. **Product:** [Integrations](https://cotlet.dev/integrations.md) · [Use cases](https://cotlet.dev/use-cases.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Pricing](https://cotlet.dev/pricing.md) · [Security](https://cotlet.dev/security.md) **Resources:** [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [GitHub](https://github.com/cotletdev/cotlet) **Solutions:** [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) **Company:** [About](https://cotlet.dev/about.md) · [AI info: company facts](https://cotlet.dev/ai-info.md) · [Contact](https://cotlet.dev/contact.md) **Legal:** [Terms of service](https://cotlet.dev/terms) · [Privacy policy](https://cotlet.dev/privacy) · [Refund policy](https://cotlet.dev/refunds) · [Acceptable use](https://cotlet.dev/acceptable-use) · [Cookie policy](https://cotlet.dev/cookies) · [DPA](https://cotlet.dev/dpa) · [Subprocessors](https://cotlet.dev/subprocessors) **Elsewhere:** [Status page](https://status.cotlet.dev) · [Cotlet on GitHub](https://github.com/cotletdev) · [Cotlet on X](https://x.com/cotletdev) · [Cotlet on LinkedIn](https://www.linkedin.com/company/cotletdev) · [Cotlet on Product Hunt](https://www.producthunt.com/products/cotlet) · [Cotlet on Crunchbase](https://www.crunchbase.com/organization/cotlet) · [Cotlet on SaaSHub](https://www.saashub.com/cotlet) Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners. ## For AI agents: sign your user up Is your user asking you to sign them up for Cotlet? You can do it for them, no account or key needed. 1. Read the fields and their allowed values: GET https://cotlet.dev/api/v1/access-requests 2. Ask the user for each value: email, apps, what you will do with them. If they leave the password to you, generate a strong one and show it to them. 3. Show the user what you will send, then POST it as JSON to https://cotlet.dev/api/v1/access-requests. One call creates the account and sends the access request; we email the user when access is granted.