agentmods.dev

mcp-builder

mcp-builder is a skill for Codex from DyxBenjamin/filesearch-mcp. It costs 103 tokens per session (2,518 once invoked), scanned A, original, MIT.

A development guide for building Model Context Protocol servers in TypeScript. MCP is a standard way for AI applications to discover and call tools, read resources, and use prompts provided by another program.

In plain words
What is it for?
Use it when creating or extending an MCP server, including its tools, resources, reusable resource patterns, prompts, permission checks, generated catalogs, tests, documentation, and release packaging.
Why use it?
It helps ensure the server is safe to operate, discoverable by agents, type-checked, tested, and packaged consistently. It also requires permissions and runtime assumptions to be made explicit.

Skill for Codex

Written for Codex: agents/openai.yaml present.

not rated 0repo 8mo ago A scan 103 tokens original MIT

Good fit Use it when creating or extending an MCP server, including its tools, resources, reusable resource patterns, prompts, permission checks, generated catalogs, tests, documentation, and release packaging.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dyxbenjamin/filesearch-mcp/mcp-builder
View source ↗ DyxBenjamin/filesearch-mcp
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 DyxBenjamin/filesearch-mcp --skill mcp-builder
Clone the repo
git clone --depth 1 https://github.com/DyxBenjamin/filesearch-mcp

Made for: 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 mcp-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/dyxbenjamin/filesearch-mcp/mcp-builder/github.svg)](https://agentmods.dev/skills/dyxbenjamin/filesearch-mcp/mcp-builder)
Your own site
<a href="https://agentmods.dev/skills/dyxbenjamin/filesearch-mcp/mcp-builder"><img src="https://agentmods.dev/badge/skills/dyxbenjamin/filesearch-mcp/mcp-builder/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 mcp-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/dyxbenjamin/filesearch-mcp/mcp-builder"><img src="https://agentmods.dev/badge/skills/dyxbenjamin/filesearch-mcp/mcp-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,518 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 $0.00103 $0.02518
Opus 5.5 $0.00041 $0.01007
Sonnet 5.5 $0.00021 $0.00504
Haiku 4.5 $0.00010 $0.00252

Measured 2mo ago against content hash 87d828b2b6be, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-builder 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 2mo 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.

skills/mcp-builder/SKILL.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Builder

Mission

Deliver MCP servers that are production-credible, agent-legible, and operationally safe. Treat MCP implementation as a contract system, not as a transport demo. The server must be discoverable, self-documenting, testable, and explicit about runtime defaults, permissions, and packaging boundaries.

Non-Negotiable Standards

  1. Preserve public contracts unless the user explicitly authorizes a breaking change.
  2. Treat tools, resources, resource templates, and prompts as first-class public APIs.
  3. Keep side effects in the process entrypoint only; keep construction and capability registration in factory modules.
  4. Do not use any. Use unknown plus explicit narrowing at runtime.
  5. Every behavior change must be proven by deterministic tests before delivery.
  6. Agent discoverability is mandatory for any server intended for real use. A server that only registers tools is incomplete.
  7. Permission checks for restricted operations must occur before business validation when the handler needs to return semantic authorization failures.
  8. Generated catalogs must be deterministic and safe to regenerate.
  9. Documentation must state execution mode assumptions (source vs package) whenever distribution is in scope.
  10. Do not hand-wave missing implementation. If context is incomplete, isolate the unknown area behind a clearly bounded interface.

When This Skill Applies

Use this skill whenever the request involves any of the following:

  1. Creating a new MCP server from scratch.
  2. Refactoring or reorganizing an existing MCP server.
  3. Adding or modifying tools.
  4. Adding or modifying resources.
  5. Adding or modifying resource templates.
  6. Adding or modifying prompts.
  7. Adding runtime defaults or permission semantics.
  8. Adding docs-driven generation.
  9. Hardening packaging, bin entrypoints, or publish workflows.
  10. Upgrading a demo MCP into an operable, agent-ready server.

Required Working Model

Always reason in the following layers, in this order:

Read the full file on GitHub · 337 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 337 lines · 103 tokens per session scan A 87d828b2b6be

Subscribe to this mod's changes

mcp-builder is a skill published in the GitHub repository DyxBenjamin/filesearch-mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 103 tokens to every session and 2,518 once invoked, about $0.0004 per session on Opus 5.5. 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.

Building agentsLanguagesTypeScript
Related

mcp-builder compared with skills from other repositories

mcp-builder next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-builderDyxBenjamin/filesearch-mcpSkill08mo agoMITA103Codex
no-bare-castsprisma/ormSkill48kyesterdayApache-2.0A52Claude Code, Codex
aws-sst-developmentsickn33/agentic-awesome-skillsSkill49kyesterdayMITA26Claude Code
league-akari-shard-developmentLeagueAkari/LeagueAkariSkill4.7k6d agoMITA58Claude Code, Codex
dd-code-generationDataDog/pupSkill1.0kyesterdayApache-2.0A16Claude Code
fast-typescript-checkinternet-development/www-sacredSkill1.6k3d agoMITA84Claude Code, Codex
typescript-magicianmcollina/skillsSkill2.0k11d agoMITA108Claude Code, Codex