MCP Tool Design

A design guide for MCP tools and gateway interfaces in the dotcontext server. MCP is a standard way for AI tools to call application functions and exchange data.

In plain words
What is it for?
Use it when adding or changing MCP tools, gateway actions, Zod input schemas, resource templates, or workflow interfaces.
Why use it?
It helps keep the server’s tool surface organized and its input schemas, resources, and gateway handlers consistent.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/vinilana/dotcontext/api-design
Any agent
npx skills add vinilana/dotcontext --skill api-design
Clone the repo
git clone --depth 1 https://github.com/vinilana/dotcontext

Made for: Claude Code, Codex.

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.01493
Opus 5 $0.00008 $0.00746
Sonnet 5 $0.00003 $0.00299
Haiku 4.5 $0.00002 $0.00149

Measured 2d ago against content hash 99b962fce5e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

MCP Tool Design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.context/skills/api-design/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Tool Design

Guidance for designing and extending MCP (Model Context Protocol) tools exposed by AIContextMCPServer in src/services/mcp/mcpServer.ts.

When to Use

  • Adding a new MCP tool or gateway action to the server
  • Refactoring the existing 9-tool surface (5 consolidated gateways + 4 dedicated workflow tools)
  • Changing Zod input schemas for existing tools
  • Adding new resource templates (e.g., context://, file://, workflow://)
  • Designing a new gateway handler in src/services/mcp/gateway/

Architecture Overview

The MCP server follows a consolidated gateway pattern to minimize cognitive load for AI agents:

AIContextMCPServer (mcpServer.ts)
  registerGatewayTools()
    -> explore     (read, list, analyze, search, getStructure)
    -> context     (check, init, fill, fillSingle, listToFill, getMap, buildSemantic, scaffoldPlan)
    -> sync        (exportRules, exportDocs, exportAgents, exportContext, exportSkills, reverseSync, importDocs, importAgents, importSkills)
    -> plan        (link, getLinked, getDetails, getForPhase, updatePhase, recordDecision, updateStep, getStatus, syncMarkdown, commitPhase)
    -> agent       (discover, getInfo, orchestrate, getSequence, getDocs, getPhaseDocs, listTypes)
    -> skill       (list, getContent, getForPhase, scaffold, export, fill)
    -> workflow-init / workflow-status / workflow-advance / workflow-manage

Each gateway dispatches to a handler in src/services/mcp/gateway/<name>.ts. The handler receives typed params and an options object with repoPath.

Instructions

1. Decide: New Gateway vs. New Action

  • New action on existing gateway: Preferred. Add an action variant to the existing z.enum([...]) and extend the handler switch.
  • New dedicated tool: Only when the domain is distinct enough to warrant its own tool (like workflow-* was split out for clarity).
  • Rule of thumb: Keep the total tool count under 12 to avoid overwhelming AI agent tool selection.

Read the full file on GitHub · 159 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 159 lines · 16 tokens per session scan A 99b962fce5e3

Subscribe to this mod's changes

MCP Tool Design is a skill published in the GitHub repository vinilana/dotcontext (561 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,493 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens