Your product is invisible to AI agents.
Claude has a vetted connectors directory. ChatGPT launched with 1,400+ connectable apps. When a customer asks their AI assistant to use your product and nothing happens, they end up on whichever competitor built the integration. I build MCP servers with the auth, logging, and directory-approval work it takes to get listed and stay reliable.
Sound familiar?
- Customers keep asking for a ChatGPT or Claude integration and it’s sitting unowned in the backlog.
- Competitors are already listed in the Claude connectors directory and you’re not.
- You have a great REST API, but agents fumble it — wrong endpoints, hallucinated parameters, abandoned sessions.
- Someone built an internal MCP prototype and it can’t survive real auth, rate limits, or multi-tenancy.
- Security keeps blocking the project because nobody can answer what an agent is allowed to do on a user’s behalf.
- You’re not sure whether you need MCP, a ChatGPT app, or both — and don’t want to build the wrong one.
I did this work at ZeroClick, where the agents were the customer.
Why me
I spent two years at ZeroClick, a company whose pitch is “the OS for selling to agents,” writing the agent-facing side of the stack: the APIs and MCP servers that AI agents consume, the developer documentation that integrators build against, and Activation Ads, an agent-native ad format I originated that provisions third-party services inside an agent’s workflow. Before that I spent a decade building consumer-scale infrastructure at Honey and Pie. Most agencies selling MCP work learned the protocol from the docs. I learned it shipping to agents in production, and I use agent tooling every day, so I know a badly designed tool surface when an agent trips over one.
Start small: know exactly what agents need from you
MCP Readiness Audit
$2,000- Review of your API and product for agent consumption — what agents need that your API doesn’t expose
- Designed MCP tool surface: the tools, their schemas, and the descriptions that make agents use them correctly
- Auth architecture recommendation (OAuth flows, scopes, what an agent may do on a user’s behalf)
- Claude connectors directory & ChatGPT apps requirements gap list — exactly what stands between you and listing
- Build-vs-buy recommendation and a fixed-bid quote for the implementation
If we continue to a full engagement, the entire fee is credited toward the project.
Start with the mcp readiness auditHow working with me goes
- Audit
Fixed price, one week. You get the tool-surface design, auth plan, and directory gap list — useful even if you build in-house.
- The build
Fixed bid. I implement the MCP server — remote-hosted with OAuth, rate limiting, logging, and tests — in your infrastructure, in your repos.
- Listing & handoff
I drive directory submission (Claude connectors / ChatGPT apps), document everything, and train your team to extend the tool surface themselves.
Questions clients ask
What does a production MCP server cost?
Published market rates for production-grade MCP implementations run $25,000–$120,000 through agencies. My builds typically land well under agency pricing because there’s no bench and no project-manager layer — the audit gives you a fixed number for your scope.
MCP, ChatGPT apps, or both?
They share most of their design thinking, and MCP increasingly works across both ecosystems. The audit answers this concretely for your product — including whether one well-designed MCP server covers you everywhere, which it often does.
How do we keep an agent from doing something destructive with a user’s account?
Scoped OAuth, capability-level permissions, human confirmation for irreversible actions, and audit logging. This is the part prototype integrations skip and security teams block. I design it in from the first day.
Can’t we just point agents at our existing REST API?
You can. Agents will fumble it. Tool design for agents is different from API design for developers: fewer tools with clearer purposes, descriptions the model can follow, and responses shaped for reasoning instead of parsing. Most failed integrations fail on that design gap.
Who owns the code? Will you sign an NDA?
Everything is work-for-hire, in your repos, on your infrastructure. You own all of it. NDAs are fine.
Your customers are already asking their assistants for this.
Send me a link to your API docs and a sentence about what your customers want their AI assistants to do. I'll tell you within a day what an MCP integration would look like.