building-an-mcp-server

building-an-mcp-server is a skill for Claude Code, Codex from New1Direction/korgex. It costs 20 tokens per session (385 once invoked), scanned A, original, MIT.

A guide for connecting or creating an MCP server. MCP, or Model Context Protocol, lets an agent gain tools from services, databases, or internal APIs.

In plain words
What is it for?
Use it to add existing servers, configure command or remote connections, design single-purpose tools, implement the protocol, validate inputs, and test handlers.
Why use it?
It explains how to make external tools available to an agent while keeping credentials and tool inputs safer.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to add existing servers, configure command or remote connections, design single-purpose tools, implement the protocol, validate inputs, and test handlers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/new1direction/korgex/building-an-mcp-server
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.

Any agent
npx skills add New1Direction/korgex --skill building-an-mcp-server
Clone the repo
git clone --depth 1 https://github.com/New1Direction/korgex

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for building-an-mcp-server

README.md
[![agentmods](https://agentmods.dev/badge/skills/new1direction/korgex/building-an-mcp-server/github.svg)](https://agentmods.dev/skills/new1direction/korgex/building-an-mcp-server)
Your own site
<a href="https://agentmods.dev/skills/new1direction/korgex/building-an-mcp-server"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/building-an-mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for building-an-mcp-server

Your own site · 80×15
<a href="https://agentmods.dev/skills/new1direction/korgex/building-an-mcp-server"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/building-an-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 385 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00020 $0.00385
Opus 5 $0.00010 $0.00192
Sonnet 5 $0.00004 $0.00077
Haiku 4.5 $0.00002 $0.00038

Measured 9d ago against content hash 9565305f4eae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

building-an-mcp-server 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 9d 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.

src/skills_builtin/building-an-mcp-server/SKILL.md · 30 lines

What it actually says

MCP is how an agent gains capabilities it doesn't have natively (a service, a database, an internal API). korgex is MCP-native — it can both consume servers and act as one.

Connecting an existing server (most common)

  1. korgex mcp catalog to see curated presets; korgex mcp add <alias> [--global] to add one. For a custom server: --command <cmd> --args "…" (stdio) or --url <url> --header "Authorization: Bearer ${TOKEN}" (remote).
  2. Put secrets in env and reference them as ${VAR} in the config — never inline a token.
  3. korgex auto-connects configured servers at startup; tools appear namespaced as server__tool.

Authoring a server

  1. Decide the tools: each gets a name, a one-line description (this is what the model sees), and a JSON-Schema inputSchema. Keep each tool single-purpose.
  2. Implement the protocol: handle initializetools/listtools/call over JSON-RPC (stdio or HTTP). Return results as content blocks; surface tool faults as an error result, not a crash.
  3. Validate inputs at the boundary and treat all args as untrusted (see security-review). Don't expose destructive operations without a guard.
  4. Test the handler purely (feed it requests, assert responses) before wiring a host.
  5. Register it with korgex mcp add and confirm tools list + a sample call work.
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. 9d ago First seen · 30 lines · 20 tokens per session scan A 9565305f4eae

Subscribe to this mod's changes

building-an-mcp-server is a skill published in the GitHub repository New1Direction/korgex (5 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 385 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 2026-08-31.