mcp-developer

Guidance for building and debugging Model Context Protocol systems, which let AI hosts communicate with tools, data sources, and prompts.

In plain words
What is it for?
Use it when inspecting or testing MCP servers and clients, configuring hosts, checking transports, listing tools, calling tools, or tracing communication.
Why use it?
It helps preserve the protocol’s exact message structure, capabilities, transports, identifiers, and error behavior across different implementations.

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/leehack/mcp_dart/mcp-developer
Any agent
npx skills add leehack/mcp_dart --skill mcp-developer
Clone the repo
git clone --depth 1 https://github.com/leehack/mcp_dart

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 672 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 $0.00035 $0.00672
Opus 5 $0.00017 $0.00336
Sonnet 5 $0.00007 $0.00134
Haiku 4.5 $0.00003 $0.00067

Measured 2d ago against content hash b5aa26c4ba22, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-developer 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.

packages/mcp_dart_cli/lib/src/skills/mcp-developer/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Developer

Use this skill when the work involves MCP protocol behavior, cross-SDK interop, server/client debugging, or host configuration.

Workflow

  1. Identify the transport first: stdio, Streamable HTTP, SSE, or a host-specific adapter.
  2. Preserve wire-level MCP semantics. Keep JSON-RPC ids, method names, capability flags, metadata, and error codes in their original spec-compatible shape.
  3. Check advertised capabilities before calling capability-specific methods.
  4. Reproduce with a protocol-level tool before editing app code:
    • mcp_dart inspect-server --json -- <server-command> ...
    • Configure a client/agent host to launch mcp_dart inspect-client --report /tmp/mcp-client-report.json
    • Configure a client/agent host to launch mcp_dart trace --report /tmp/mcp-trace.json -- <real-server-command> ...
    • mcp_dart list-tools -- <server-command> ...
    • mcp_dart call-tool <tool> --json-args '{"key":"value"}' -- <server-command> ...
    • mcp_dart inspect --url http://localhost:3000/mcp
  5. Use --probe-config with inspect-server when a server needs real tool arguments, resource URIs, prompt arguments, completion values, or task behavior. Keep destructive app actions out of default probes.
  6. Treat inspect-server, inspect-client, and trace as the live debugging workflow. They return protocol checks or traffic evidence for real targets; there is no separate live validation command to prefer.
  7. If changing this Dart SDK/CLI package itself, also run mcp_dart conformance --suite all --json for the built-in protocol regression fixtures.
  8. For cross-language issues, test at least one non-Dart peer. Prefer the official TypeScript or Python MCP SDK when a reproduction can be made small, and use published servers such as filesystem/time when the bug depends on real package behavior.
  9. When changing protocol behavior, add regression coverage for the raw wire shape or interop edge case, not only a convenience API test.

Host Configuration Checks

Read the full file on GitHub · 41 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 · 41 lines · 35 tokens per session scan A b5aa26c4ba22

Subscribe to this mod's changes

mcp-developer is a skill published in the GitHub repository leehack/mcp_dart (114 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 672 once invoked, about $0.0002 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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens