MCP servers for your product
A remote MCP endpoint (JSON-RPC over streamable HTTP) that exposes your app's features as well-described tools.
The Model Context Protocol lets AI assistants like Claude and ChatGPT use your software directly: look things up, create records, run workflows. We run two MCP servers in production, each with its own OAuth server, so we know how to make that useful without handing an AI the keys to everything.
How an MCP connection works
AI assistant
Claude, ChatGPT, Cursor or your own agent.
Your MCP server
OAuth 2.1 sign-in, scoped tools, limits and a log of every call.
Your application and data
The same business rules and permissions as your own interface.
From a read-only connector for your knowledge base to an agent that runs whole workflows in your product.
A remote MCP endpoint (JSON-RPC over streamable HTTP) that exposes your app's features as well-described tools.
Discovery, dynamic client registration, PKCE, consent screens, short-lived access tokens and rotating refresh tokens stored only as hashes.
Every tool runs with the connecting user's role and plan limits. Risky actions need explicit human approval, and the server refuses whatever breaks your rules.
On connect, the server hands the agent your playbook: how to work, which rules apply and what it must never do.
Every call is logged with who, what and when, so you can trace exactly what an agent did and why.
Multi-step work across tools, like researching, drafting, reviewing and queueing, with a person signing off at the right moments.
Our sales system runs on an MCP server with 35 tools. Claude handles prospect research, data enrichment, email verification, drafting and reply handling, and a person approves every email before it's sent.
Salestreak has an MCP connector for online sellers with 37 tools for catalogue, stock, photos, print on demand, webshops and orders. The agent works with the role of the user who approved it and within the limits of their plan.
A working day for our sales agent
Find and research
Search the CRM, look up companies and save research notes.
Verify
Check that an email address exists before any effort goes in.
Draft
Write a personal email that follows the campaign brief.
Human approval
Nothing is sent until a person has approved it.
Handle replies
Classify replies and draft answers. An opt-out is suppressed everywhere at once.
Let your customers work with your product from Claude or ChatGPT, right next to their other tools.
Give your team an assistant that searches the CRM, updates records and prepares work in your own systems, with the permissions they already have.
Agents that look up orders, customers and stock, and prepare actions for a person to confirm.
Research, enrichment, drafting and follow-up handled by an agent, with every outgoing message reviewed by a person.
An MCP server is an API designed for an AI. The design work is in deciding what that AI may do.
Which tasks should an agent handle end to end? We design the tools around those tasks, with names and descriptions an AI understands.
Reading is usually fine. Sending, spending and deleting get approval steps and hard limits on the server.
OAuth 2.1 with PKCE, dynamic client registration, consent screens and tokens bound to the right workspace and user.
Standing instructions the server sends on connect, so every session starts with your rules and your tone of voice.
We run the tools through Claude and other clients, and add server-side checks wherever an agent could get it wrong.
Audit logs, usage and error monitoring, then new tools as your team finds more work to hand over.
The open Model Context Protocol, OAuth 2.1 and the same application stack as the product itself, so the agent follows exactly the same business rules.
Less than most people expect when your application already has clean business logic, more when it doesn't. The estimate depends on:
MCP (Model Context Protocol) is an open standard that lets AI assistants such as Claude and ChatGPT use external tools. An MCP server exposes features of your software as tools the AI can call, like searching records or creating a draft, within the permissions you set.
It depends on the number of tools, whether they only read or also change data, the authentication and the approval flows you need. After a free intro call you get a written scope and estimate.
It can be, if the server is built for it. Our servers use OAuth 2.1, give the agent the same rights as the person who connected it, require human approval for risky actions and log every call.
Any client that supports remote MCP servers, including Claude and ChatGPT, developer tools such as Cursor, and agents you build yourself.
No. We can build the MCP server directly on your application's business logic. If you already have an API, the MCP tools can build on top of it.
Yes. Our own sales agent researches, verifies, drafts and handles replies through MCP tools every day, with a person approving every email it sends.
A CRM shaped around your sales process, with lead enrichment, verified contacts, AI drafts, human approval and reply handling.
Read moreAI image, video, voice, music and text features that are reliable, affordable and safe to put in front of customers.
Read moreFrom first version to a profitable product: billing, teams, multilingual UX, hosting and the growth tooling around it.
Read moreTell us what you'd like an agent to do and which systems it should touch. You'll get an honest view on what's safe to automate and what should stay with people.
Typically a reply within one business day.
Useful to mention