Skip to content
Model Context Protocol AI workflow planning workspace.

MCP servers designed for the caller you actually have

MCP lets agents call your tools. Good MCP design is API design for a model caller.

What this is

Tool focus: Model Context Protocol

Design Model Context Protocol (MCP) servers and integrations for agentic AI: tool surface, scopes, secrets, transport choice and review patterns.

Focus 01

Tool surface design

Expose the few tools the model can call accurately, with clear names, arguments and failure modes.

Focus 02

Scopes, secrets, and identity

Authentication, per-user scopes, secret storage and agent-host identity are designed before the server is useful.

Focus 03

Transport choice

stdio, HTTP or SSE is chosen deliberately, with notes on what would justify changing it later.

Engagement

How the work runs

  1. 01

    Week 1

    Tool inventory

    Which internal tools exist, which the agent should reach, what the existing API surface already does, and what new shape the MCP server needs.

  2. 02

    Week 2

    Design and skeleton

    Tool naming, argument schema, scopes, transport and error model. First tools go live in a skeleton server.

  3. 03

    Week 3

    Real integration

    Codex, Claude Code or an internal agent calls the server on real tasks. Logs shape the tool surface.

  4. 04

    Week 4

    Hardening and handover

    Secrets in the right vault, observability live, runbook written, and a written review of the design decisions and what would trigger a revisit.

FAQ

Questions teams ask first

Both, depending on the tool. Off-the-shelf servers exist for common things and there is no point reimplementing them. Custom servers are worth it when the tool is specifically yours: an internal API, a domain-specific search, a private dataset.

stdio for local single-developer integration, HTTP for shared internal services, SSE where the tool produces a stream the agent should react to. The choice is decided early because changing it later is expensive.

The MCP server should look like any other API to the identity layer: it is a client of the same SSO, it respects the same scopes, and its calls show up in the same audit trail. The agent does not get a parallel identity universe.

Next step

Book an MCP design call

Most useful where the team has internal tools they want an agent to reach. If the only goal is using off-the-shelf MCP servers in Claude Code, the Claude Code workshop is a better starting point.