Live 43 Actions

Freshchat MCP Server
for AI Agents

Q: What AI frameworks and AI clients does the StackOne Freshchat MCP server support?

The StackOne Freshchat 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.

Connect your AI agent to StackOne's Freshchat MCP server and give it 43 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →

Freshchat MCP Server

Built by

StackOne

Coverage

43 Agent Actions

Agents can read, write, delete and run operations in Freshchat. Extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Freshchat MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Freshchat tool response scanned for prompt injection in milliseconds, with 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 Freshchat call.

Tools Discovery →

What is the Freshchat MCP Server?

A Freshchat MCP server lets AI agents read and write Freshchat data through the Model Context Protocol, Anthropic's open standard for connecting LLMs to external tools. StackOne's Freshchat MCP server ships with 43 pre-built actions, fully extensible via the Connector Builder, plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Freshchat MCP Tools

Every StackOne action for Freshchat, ready for your agent. Read, write, delete and run operations, scoped to exactly what you need.

Agents

Create Agent
Add an agent to the Freshchat account.
List Agents
List agents in the Freshchat account.
Get Agent
Get a single Freshchat agent by ID.
Update Agent
Update a Freshchat agent's profile, role or groups.
Delete Agent
Permanently delete a Freshchat agent.

Conversations

Create Conversation
Start a Freshchat conversation for a user in a channel, with its first messages.
Get Conversation
Get a Freshchat conversation by id.
Update Conversation
Change a Freshchat conversation's status, assignment or properties.

Unified Groups

List Unified Groups
List unified groups in a Freshchat account.
Get Unified Group
Get a unified Freshchat group by ID.

Unified Organizations

List Unified Organizations
List unified organizations in a Freshchat account.
Get Unified Organization
Get a unified Freshchat organization by ID.

Unified Roles

List Unified Roles
List unified roles in a Freshchat account.
Get Unified Role
Get a unified Freshchat role by ID.

Unified Users

List Unified Users
List unified users in a Freshchat account.
Get Unified User
Get a unified Freshchat user by ID.

Messages

Send Message
Send a message to a Freshchat conversation as a user, agent or bot.
List Messages
List the messages in a Freshchat conversation.

Users

Create User
Create a Freshchat user (customer) record.
List Users
Search Freshchat users (customers) by name, email, phone, reference id or time range.
Get User
Get a single Freshchat user by id.
Update User
Update a Freshchat user's email, name or phone.
Delete User
Permanently delete a Freshchat user and their data.

Other (20)

Create CSAT Rating
Record a customer satisfaction (CSAT) rating for a Freshchat conversation.
Upload File
Upload a file to Freshchat to attach to a message.
Upload Image
Upload an image to Freshchat to use in a message.
Send WhatsApp Outbound Message
Send an approved WhatsApp template message from the business number to one or more recipients.
Get Account Configuration
Get the Freshchat account's configuration.
List Agent Statuses
List the custom agent statuses configured in Freshchat.
List Channels
List the channels (topics) in the Freshchat account.
List Conversation Properties
List the conversation properties configured in Freshchat (Freshsales Suite chat only).
List Groups
List groups in the Freshchat account.
Get Unified Credentials
Get the current Freshchat connection's unified credentials and identity.
List Outbound Messages
Get the delivery status of the messages in one WhatsApp outbound request.
Get Raw Report
Get the status and download links of a raw report.
Get Historical Metrics
Get historical Freshchat CSAT, conversation and team performance metrics for a time range.
Get Instant Metrics
Get real-time Freshchat team presence counts.
List Roles
List roles in the Freshchat account.
List User Conversations
List the conversations of a Freshchat user.
Update Agent Status
Set a Freshchat agent's current status to a custom status.
Check Group Business Hours
Check whether a Freshchat group is currently within its business hours.
Extract Raw Report
Request a raw CSV report of Freshchat events for a time range.
Fetch Users By IDs
Get several Freshchat users at once by their user ids.

Set Up Your Freshchat MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Freshchat in under 10 lines of code.

MCP Clients

Agent Frameworks

Claude Desktop-

JSON

Claude Desktop Docs

{
  "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>"
      ]
    }
  }
}

Check More developer MCP Servers

Wiz

696+ actions

IONOS

501+ actions

266+ actions

259+ actions

251+ actions

234+ actions

232+ actions

All developer MCP Servers →

Platform Resources

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

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, the security risks they share, and when to use one, both or a hybrid.

12 min

MCP vs API: What Hundreds of Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building hundreds of connectors that serve both, here's when each approach wins.

14 min read

Freshchat MCP Server FAQ

Does StackOne have a Freshchat MCP server?

Yes. StackOne offers a managed Freshchat MCP server with 43 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.

Freshchat MCP server vs direct API integration: what's the difference?

A Freshchat MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software work, where backend code calls Freshchat. A Freshchat MCP server is for AI agents that discover and call Freshchat at runtime, such as MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI. StackOne provides both.

How does Freshchat authentication work for AI agents?

Freshchat authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK to get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Freshchat account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.

Are Freshchat MCP tools vulnerable to prompt injection?

Yes. Freshchat MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content, such as 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. It runs regex patterns in ~1ms, then a MiniLM classifier in ~4ms. Accuracy is 88.7%, and it runs entirely on CPU.

What is the context bloat of a Freshchat agent and how do I avoid it?

Context bloat happens when Freshchat tool schemas and API responses eat your Freshchat agent's memory, preventing it from reasoning effectively. A single Freshchat query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery reduces it by loading only the tools relevant to each query.

Can I limit which actions my Freshchat agent can access?

Yes. You can limit which actions your Freshchat 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 Freshchat MCP server?

Yes. You can create custom agent actions for your Freshchat MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Freshchat's API, generate production-ready connector YAML, test against the live API, and validate before you ship.

When should I NOT use a Freshchat MCP server?

Skip a Freshchat MCP server if your integration is purely software-to-software, because direct Freshchat 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 Freshchat actions at runtime.

What AI frameworks and AI clients does the StackOne Freshchat MCP server support?

The StackOne Freshchat 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

Connect AI to every company system and control what it can do in each one, down to the field.

Start Free Book Demo

Freshchat MCP Serverfor AI Agents