Skip to main content
Have a project in mind? Let's talk
Book a call Tell us about your project Book a Call
Insights & Guides

MCP for Business: How Claude Connects to Your CRM, Email and Accounting

MCP is an open standard that lets Claude read and act in your business systems through defined tools. Here is how it works, what can go wrong and how to connect safely.

The Model Context Protocol (MCP) is an open-source standard for connecting AI applications such as Claude to external systems: your data, your tools and your workflows. For a business, it is the difference between pasting a spreadsheet into a chat window and letting Claude read from, and with your approval write to, the systems where the work actually lives, through a defined list of actions.

This guide explains MCP without jargon, how Claude connects to it, the security risks to plan for, and when a plain API is better. Devvista is a software development and growth agency that builds custom MCP servers and integrations for client systems, so we also say when you should not use one.

01 What MCP Is, in Plain Language

The MCP documentation compares the protocol to a USB-C port for AI applications: one standard way to plug an AI application into an external system. Before a standard existed, every pairing of an AI tool and a business system needed its own custom connection. With MCP, a system exposes itself once and any client that speaks the protocol can use it.

The protocol is open, so it is not owned by one vendor's product line. The MCP site lists Claude, ChatGPT, Visual Studio Code and Cursor among the clients that support it. That matters for you because a connection you build is not locked to a single AI product.

MCP only defines how an AI application and an external system talk to each other. In the words of the architecture page, it "does not dictate how AI applications use LLMs or manage the provided context". What the AI is allowed to do, and what you let it see, is decided by how the server and the client are configured. That is where the business risk lives, and most of this article is about it.

02 Hosts, Clients and Servers: Who Does What

MCP has three participants. Knowing them makes every security conversation clearer.

ParticipantWhat it isExample
MCP hostThe AI application you useClaude Code or Claude Desktop
MCP clientA component inside the host that keeps one connection to one serverCreated by the host for each server you connect
MCP serverA program that provides context and actions to clientsA server that exposes your CRM, inbox or accounting data

A server can run on your own machine, using the stdio transport, or remotely, using Streamable HTTP. A local server typically serves one client, while a remote server typically serves many. Claude Code documents HTTP as the recommended transport for remote servers and stdio for local processes.

03 Tools, Resources and Prompts: What a Server Can Offer

A server exposes three kinds of things, and each has a business meaning.

  • Tools are executable functions the AI can call to perform actions, such as running a query, creating a record or sending a request to another system. This is where write access lives.
  • Resources are data sources that give the AI context, such as records, files or API responses.
  • Prompts are reusable templates that structure how the AI works with the tools, for example a standard way to summarise an account.

The client first asks the server what tools exist, then calls one by name with arguments. The server describes each tool with a name, a description and an input schema, which is how the AI knows what a tool needs. The practical lesson: a tool is a decision about what your business lets an AI do. A server with a tool called "refund_order" and one without it are two very different systems, even if they connect to the same shop.

04 How Claude and Claude Code Connect

In Claude Code, you add a server with a command such as claude mcp add, choosing the transport and, for remote servers, signing in. Many remote servers require sign-in, and Claude Code supports OAuth 2.0 for them (some servers use tokens or API keys instead). A /mcp command inside a session shows the servers and lets you manage them. Servers can be scoped to a single project, to you across projects, or shared with a team through a project file that is checked into the repository.

In the Claude apps, Anthropic calls these connections connectors. Custom connectors use remote MCP servers that Claude reaches from Anthropic's cloud, so the server must be reachable over the public internet unless you allowlist Anthropic's IP ranges. Each connector has per-tool permissions where you can set a tool to Always allow, Needs approval or Blocked, and organisation owners can limit which actions a connected service can take.

The Claude API also has an MCP connector for reaching remote MCP servers from your own application, and the Agent SDK can use MCP servers inside agents you build. The same protocol sits under all of these, which is why one well-built server can serve several tools.

05 What MCP Makes Possible in a Business

Once Claude can use defined tools against your systems, tasks that used to need copy and paste become one request. The patterns we see are these, described as capabilities, not as results.

PatternWhat the connection allowsSafe starting point
Look up and summariseRead customer, order or ticket data and answer a questionRead-only tools, no write access
Prepare, then askDraft an email, an invoice or a CRM note for a person to approveA "create draft" tool, never "send"
Update with approvalChange a record after a person confirms the exact changeWrite tools set to Needs approval
Cross-system checksCompare data across the CRM, inbox and accounting systemRead-only on each system, with a report as output
Run an existing workflowTrigger a workflow you already trustExpose a scenario as a tool

The last row already exists in the workflow platforms. Make documents a hosted MCP server that lets AI clients such as Claude run active and on-demand scenarios, and n8n documents both an MCP server trigger and an MCP client node. If you already automate with those tools, MCP can give Claude a controlled way to start what you have already built. Our guide to automating business processes with AI explains how to choose the process first.

We have not opened the documentation for individual CRM, email or accounting vendors' MCP servers, so we do not name them here. Check your vendor's own documentation to see whether an official server exists, and read what it can do before you connect it.

06 The Risks: Why Connecting Claude to a Live System Needs Care

Reading a spreadsheet and changing a customer record are very different powers. Four risks deserve a plan before you connect anything.

  1. Too much access. A tool or a token that can do everything will eventually do the wrong thing, by mistake or by manipulation. The MCP security guidance recommends a least-privilege approach with minimal initial scopes and warns against wildcard or omnibus scopes such as full-access.
  2. Prompt injection from outside content. Anything the AI reads can contain instructions: an email, a web page, a support ticket, a PDF. Claude Code's documentation warns: "Servers that fetch external content can expose you to prompt injection risk." If the AI can both read untrusted content and write to your systems, a hostile message could try to steer it.
  3. Untrusted servers. A server you did not write runs with real access. Anthropic's security page encourages writing your own MCP servers or using servers from providers you trust, and states that Anthropic does not security-audit or manage any MCP server, though it reviews connectors against its listing criteria before adding them to its Directory. The MCP security guidance also describes risks of local servers that run commands on your machine.
  4. Silent failure. With no logging, you will not know what the AI changed or why.

No safeguard removes these risks completely. Anthropic's own security page says: "no system is completely immune to all attacks." Plan for containment, not perfection.

07 Security Controls That Work: Permissions, Least Privilege, Approvals and Logs

The MCP specification states that there "SHOULD always be a human in the loop with the ability to deny tool invocations". For a business, that translates into controls you can check.

ControlWhat it means in practice
Least privilegeA dedicated service account for the AI, with only the permissions the task needs. Read-only unless there is a reason to write
Narrow toolsSeveral small, specific tools ("create draft reply") instead of one general "run any query" tool
Validation on the serverThe specification says servers must validate all tool inputs, implement access controls, rate limit and sanitize outputs. Do not rely on the AI to behave
ApprovalsWrite and delete tools set to require approval. The specification advises clients to show tool inputs before a call so a person sees exactly what will happen
Separate reading from actingDo not give one session both unreviewed external content and powerful write tools
Hard blocks outside the promptClaude Code documents that CLAUDE.md is context, not enforced configuration, and recommends a PreToolUse hook to block an action regardless of what Claude decides
Audit logsThe specification advises clients to log tool usage for audit. Keep logs of who, what, when and the result, on your side as well
CredentialsKeep keys in a secrets manager, rotate them, and never paste them into prompts or files in a repository

In manual mode Claude Code asks before it runs commands or edits files (your default mode may be different, so check), and project-level server definitions need approval before they load in an interactive session. Treat these as one layer, not the only one.

08 MCP or a Plain API Integration?

MCP is not always the right answer. A standard API integration, a webhook or a workflow platform is often simpler, cheaper to run and easier to audit.

ChooseWhen
Plain API or webhook integrationThe steps are fixed and known: when X happens, do Y. No judgement is needed, and the task runs the same way every time
Workflow platform (Make, n8n)You want visible, editable steps and the connectors already exist
MCP serverA person or agent needs to ask open-ended questions across a system, or the AI must pick which action to take from a defined list
Custom code with the Claude APIOne judgement step sits inside a larger product, and you want full control of data flow and errors

Anthropic's guidance on building agents advises using the simplest solution that works. If your process is "when an order arrives, create an invoice", you do not need an AI choosing tools. Our post on webhooks versus APIs covers the fixed-step case, and business process automation shows what rule-based automation already handles well.

09 What Devvista Builds Around MCP

Devvista builds custom MCP servers and integrations for client systems. As a capability, that means:

  • A server that exposes a defined set of read tools and approval-gated write tools for a system you already run, with the access rules written into the server, not only into a prompt.
  • Connections between Claude, your workflow platform and your internal systems, using your accounts.
  • Logging, alerts and a staging environment so changes are tested before they touch live data.
  • Handover: documentation, credentials in your name and a walkthrough for your team.

The work sits within our API development and integration, AI automation and AI agents services, and our workflow automation practice covers the Make and n8n side. For examples of the kind of integration work we do, see our case studies. For instance, one automation build joins Make.com, an AI analysis layer, a CRM and a database with error logging and human checkpoints on high-risk cases (see the credit repair automation case study).

Thinking about connecting Claude to a system you run? Contact us. The form has a budget range field, and we quote after a short call.

10 A Cautious Rollout Plan for Your First Connection

  1. Choose one system and one question. For example, "find overdue invoices and summarise them".
  2. Start read-only with a dedicated account that cannot write.
  3. Use a copy of your data or a test account for the first trial.
  4. Review the tools list and remove any tool you do not need.
  5. Add one write tool at a time, set to need approval, and test with real examples.
  6. Turn on logging and read the first week of logs.
  7. Review access monthly and disconnect anything you no longer use.

Canada, Pakistan and Saudi Arabia are covered on their own pages: Canada, Pakistan (WhatsApp automation) and Saudi Arabia (chatbots).

? Frequently Asked Questions

MCP, the Model Context Protocol, is an open-source standard for connecting AI applications such as Claude to external systems like databases, files, tools and workflows. A system exposes itself once as an MCP server, and any compatible AI application can connect to it. The documentation compares it to a USB-C port for AI.

No. It is an open standard, and the MCP site lists several clients that support it, including Claude, ChatGPT, Visual Studio Code and Cursor. A server you build is therefore not tied to one AI product, though each client has its own settings and controls for what it will allow.

It can if there is an MCP server for the system, either an official one from the vendor or one that is built for you, and you connect it. Check your vendor's own documentation for an official server and read what it can do first. If none exists, a custom server or a plain API integration can do the job.

It can be, with controls, but no system is completely immune to attack. Use a dedicated account with least privilege, narrow tools, approval on write actions, server-side validation and audit logs. Keep untrusted content away from sessions that can write. Start read-only and add write tools one at a time.

Prompt injection is when text the AI reads, such as an email, web page or ticket, contains instructions meant to manipulate it. Claude Code's documentation warns that servers that fetch external content can expose you to this risk. It matters most when the same AI can also write to your systems, so separate reading from acting and require approvals.

Be careful. Anthropic's security page encourages writing your own MCP servers or using servers from providers you trust, and says Anthropic does not security-audit or manage any MCP server, though it reviews connectors against its listing criteria before adding them to its Directory. A server runs with real access, so review what it does, run it with minimal permissions and prefer official or well-reviewed ones.

When the steps are fixed and need no judgement: when something happens, do a defined action. APIs, webhooks and workflow platforms are simpler to test and audit for that. MCP fits when a person or agent needs to ask open-ended questions across a system or choose among defined actions.

Both document MCP support. Make documents a hosted MCP server that lets AI clients such as Claude run active and on-demand scenarios. n8n documents an MCP server trigger and an MCP client node. Check each platform's current documentation and plan terms before you rely on a feature.

Only if no existing server gives you the narrow, safe set of tools you need. A custom server lets you decide exactly which actions exist, what they validate and how they log. For a simple read-only question over one system, an existing official server may be enough.

Devvista builds custom MCP servers and integrations for client systems, with approval-gated write tools, logging, a staging environment, accounts in the client's name and handover. We scope the work first and quote after a short call. We do not claim a particular result, because it depends on your systems.

→ Related Resources

More on connecting Claude to the systems you run, and the services behind it:

→ Sources

Opened on 11 November 2026. Documentation changes, so check the current page before you rely on a detail.

SA
Written by
Samowal Faiz
Chief Executive Officer, Co-Founder, Devvista

Samowal Faiz is the Chief Executive Officer and co-founder of Devvista, a custom software agency that has delivered 195+ projects across healthcare, fintech, SaaS, and e-commerce. He leads strategy, client relationships, and business development with 7+ years of industry experience.

Devvista on LinkedIn
Ready to start?

Have a project in mind? Let's talk about it.

Book a discovery call with Devvista. We'll scope your project honestly, ask the right questions, and tell you what you need to hear, not what you want to hear.

  • 30-minute consultation
  • No commitment required
  • Response within 24 hours
  1. Book a call30 minutes, no pitch. Tell us what you want to build.
  2. Get a straight answerHonest feedback on fit, scope and timeline.
  3. Decide with no pressureMove ahead only if it feels right. No commitment required.
Chat on WhatsApp