United States · Built by our team · used by your agents in Konnet Flow

MCP server for your ERP, CRM and API

Send us your API documentation. Our team turns it into a list of actions your AI agents can use, and you decide which agent may read, update or do nothing.
About 5 minutes with a documented API · logged calls · no tokens on lookups
What do I owe right now?9:12 a.m.
Your balance is $1,860.00 across 2 open invoices.9:12 a.m.
Can you raise my credit limit to $5,000?11:02 a.m.
Approved. Your credit limit is now $5,000.11:06 a.m.
AI on WhatsAppLive
 
get_account_balanceService agent · 1 row · account holder only
 
change_credit_limitCredit agent · needs approval
 
Karen, credit managerWaiting · Karen, credit manager
 
Audit trailWho asked · tool · permission · approver
 
Every call loggedWho asked, which tool, which permission, who approved
MCP server

What is an MCP server?

AI agentKonnet
An MCP server is the doorway an AI agent uses to work with a system. MCP, short for Model Context Protocol, is an open standard: the server lists the actions available, like checking a balance or creating an order, and the agent calls them with the permissions you grant. Your system doesn’t change.
Your vocabulary

MCP in business terms

Four words your IT lead will use, explained for everyone else.

Tools

Each action your system allows, published with a plain name and description: “get account balance”, “create sales order”, “update ticket status”.

Permissions

Per agent and per tool: read only, read and update, update with a person’s approval, or no access.

Source of truth

The number comes from your ERP or CRM on every call, not from the AI’s memory.

Audit trail

A record of who asked, which tool ran, on what data and who approved it.

Setup

How our team sets up your MCP server

Our team uses Konnet Core, our internal tool. You review and approve; you don’t write code.
StepWhat our team doesWhat you approve
1. DocumentationReads your API documentation (an OpenAPI file, a collection export or a PDF) and detects the available actions
2. Tool listProposes which actions to publish, each with a plain nameWhich tools go live
3. CredentialReceives a credential from you through a secure channel; it is stored encrypted and never shown again
4. Live testRuns a real call and shows you what each tool returnsThat the data is right
5. PermissionsSets what each agent may do, tool by toolWho sees and does what
6. ReadyYour agents in Konnet Flow start using the server
With a documented API, the connection takes about 5 minutes. Konnet needs an API to connect a system: if yours doesn’t have one, we tell you before you commit.
Example flow

Example flow: a credit limit request at a wholesale distributor

Three tools from the same MCP server, one approval.
Flow Copilot

When a customer asks for a higher credit limit, check their balance and payment history in our ERP, and send any increase to the credit manager for approval.

Done: 6 steps. 1 waits for a person's approval and the rest run on their own.

StepWhat the agent doesWhat a person approves
1. A buyer writes on WhatsApp “Can you raise our limit to $5,000?”Understands the request with a low-cost AI model
2. Checks the accountCalls get_account_balance and payment_history, by direct code, no tokens
3. Applies your ruleAny increase goes to credit, by policy
4. Prepares the casePuts balance, history and the amount requested in one viewThe credit manager approves, adjusts or declines
5. Updates your ERPCalls change_credit_limit with the approved amount
6. Replies and logsConfirms to the buyer; the call and the approval land in the audit trail

This flow is built in Konnet Flow: you describe the process, the Copilot builds it and you approve it before it goes live.

See Konnet Flow
Control

Control: the AI proposes, a person approves

Konnet helps you meet your security and privacy obligations. We’re not a law firm: review your setup with your counsel and your security team.

Checked against your real catalog

Every tool is validated field by field against your source. A field that doesn’t exist is rejected before any agent sees it.

Personal data, kept out

Personal data stays out of technical logs and out of answers to third parties unless you authorize it.

Encrypted credentials, isolated data

Credentials are encrypted and never shown again; each company’s data is isolated.

Revoke anytime

Ask us to pull an agent’s access and we do it without touching the rest.

Nothing destructive by default

When Flow Copilot proposes a change, it shows the plan and waits for a person to approve it.

Your system, powered by AI

Keep your system. Connect it to AI.

Your company already runs a billing, accounting, collections or core system. If it has an API, our team connects it to your AI agents in about 5 minutes: your customers talk to your system on WhatsApp, your website or email, and the agent creates the actions inside it, with your approval on anything sensitive.
  • WhatsApp
  • Website chat
  • Email
AI agentKonnet
  • Billing and accounts receivableRequests the invoice from your systemAllowed
  • ERP and accountingPosts the paymentWith a limit
  • Loan servicing or core bankingChecks the balanceRead only
  • CRMUpdates the contactAllowed
  • Orders and inventoryCreates the orderNeeds approval

For companies in New York, Los Angeles, Chicago, Houston, Miami and across the United States: setup and go-live happen remotely.

  • What works stays
  • Repetitive work goes to the agent
  • Not a chatbot, not a fixed script
  • AI that costs what it should
AI under control, with live context
  • Hallucinations under control
  • Live context in one platform
  • Learns without code

What your agent does in your system

In the chat

Business answers in the chat

The number someone digs up by hand today, your agent answers in the conversation.

Ask in plain English

“How much did we sell this week by branch?” or “Which accounts are more than one cycle past due?” The agent answers on WhatsApp or web chat with the figure from your system.

Who sees which number

A service agent sees the balance of the customer who is writing; an analysis agent sees sales but can’t create orders.

Dashboards, coming

AI-generated dashboards are a capability our team already uses internally and is preparing for clients.

Technical

For your technical team

Standard protocol

Konnet publishes your systems as a standard MCP server (JSON-RPC) for your agents in Konnet Flow.

Your own agents, on request

If your team wants to use the same tools from agents you build yourselves, or through a REST API, we enable it on request.

Other MCP servers

Konnet Flow can also use third-party MCP servers as one more source, with the same permissions and logging.

No integration project

Each new source is configuration on the same platform, not a development project.

Pricing and contact

Pricing and contact for US companies

Setup is part of your implementation
Our team connects your system as part of your Konnet Flow implementation, quoted as a fixed proposal after the demo.
Then, pay per resolved action
Plans start at USD 100 a month: Inicia USD 100 with 400 actions, Crece USD 550 with 2,200 and Prime USD 1,500 with 6,000. Each resolved action is USD 0.25.
Remote, nationwide
For businesses in New York, Los Angeles, Chicago, Houston, Miami and across the United States, remotely.
Talk to us
WhatsApp +593 96 258 0683.
FAQ

Questions about MCP servers

What’s an MCP server, in plain terms?

An MCP server is the doorway an AI agent uses to work with one of your systems. MCP stands for Model Context Protocol, an open standard that defines how an agent discovers the actions available, calls them and gets the data back. For a business, it means your ERP, CRM or billing system can be used by AI agents without a custom integration for each one. With Konnet, our team sets up the server and your agents in Konnet Flow use it with the permissions you grant.

What is the difference between an MCP server and an API?

An API is how your system takes orders from other software, and someone has to read its documentation and code each call. An MCP server sits on top of that API and presents it as a list of tools, each with a name, a description and a permission, that an AI agent understands and uses without custom code. It isn’t one or the other: our team reads your API documentation with Konnet Core, our internal tool, and publishes the MCP server on top of it.

How long does it take to set up an MCP server for my system?

With a documented API, our team has the connection ready in about 5 minutes. You share the link or file with your API documentation, we detect the available actions and propose which ones to publish, you send a credential through a secure channel, and a live test confirms the data comes back right. Then you approve what each agent may do. You don’t write code. Konnet needs an API to connect a system; if yours has none, we tell you before you commit.

Can I control what each AI agent sees and does?

Yes, and that control is the core of how Konnet sets up your MCP server. Before an agent goes live, you decide tool by tool what it may do: read only, read and update, update with a person’s approval, or nothing. A service agent can see the balance of the customer who is writing but not your sales; an analysis agent can see sales but can’t create orders. If you ask, we revoke an agent’s access at any time without affecting the others.

Is it safe to connect my ERP to AI through MCP?

It is when every action has an owner and a record, and that is how Konnet works. Your system’s credentials are stored encrypted and never shown again, each company’s data is isolated, and each agent uses only the tools you authorized. Personal data stays out of technical logs and out of answers to third parties unless you allow it. Every call is logged with who, what, when and on which data. Konnet helps you meet your obligations; review the setup with your counsel.

How does the agent avoid making up numbers?

The number doesn’t come from the AI’s memory; it comes from your system. When someone asks for a balance or this week’s sales, the agent calls the authorized tool and your system answers by direct code, on every request. Each tool is validated field by field against the real catalog of your source, so a field that doesn’t exist is rejected before an agent can use it. The AI only understands the question and writes the reply around that data, and every call is logged.

Can we use the MCP server from our own AI agents?

Konnet publishes your systems as a standard MCP server for your agents in Konnet Flow. If your technical team wants to use the same tools from agents you build yourselves, or through a REST API, we enable it on request, with the same permissions and audit trail. Konnet Flow can also use third-party MCP servers as one more source. Our team configures each connection, so you get one set of tools with one set of rules, whichever agent is calling.

How much does it cost to connect my system through MCP?

Our team sets up the connection as part of your Konnet Flow implementation, which is quoted as a fixed proposal after the demo. After that, Konnet charges USD 0.25 per resolved action, with plans from USD 100 a month. AI spending stays low because checking a balance, reading weekly sales or logging a payment runs as direct code against your system, without tokens. The AI works only where it adds value, with low-cost models and narrow tasks.

Bring your API docs to the demo. Leave with a connected agent.