add-tool

add-tool is a skill for Claude Code from cyanheads/usda-mcp-server. It costs 35 tokens per session (18,701 once invoked), scanned A, a copy of add-tool, Apache-2.0.

A guide for adding an MCP tool, a function that an AI assistant can call through an MCP server.

In plain words
What is it for?
Use it when creating a tool definition, connecting it to the server, and checking the result with the project's development checks.
Why use it?
It gives the new tool the expected file structure, registration, input handling, and verification steps.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the usda-mcp-server plugin — 35 skills, 1 MCP server shipped together

Good fit Use it when creating a tool definition, connecting it to the server, and checking the result with the project's development checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cyanheads/usda-mcp-server/add-tool
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 cyanheads/usda-mcp-server --skill add-tool
Clone the repo
git clone --depth 1 https://github.com/cyanheads/usda-mcp-server

Made for: Claude Code.

Or install usda-mcp-server, the plugin that ships this one along with the rest of its 35 skills, 1 MCP server.

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 add-tool

README.md
[![agentmods](https://agentmods.dev/badge/skills/cyanheads/usda-mcp-server/add-tool/github.svg)](https://agentmods.dev/skills/cyanheads/usda-mcp-server/add-tool)
Your own site
<a href="https://agentmods.dev/skills/cyanheads/usda-mcp-server/add-tool"><img src="https://agentmods.dev/badge/skills/cyanheads/usda-mcp-server/add-tool/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 add-tool

Your own site · 80×15
<a href="https://agentmods.dev/skills/cyanheads/usda-mcp-server/add-tool"><img src="https://agentmods.dev/badge/skills/cyanheads/usda-mcp-server/add-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 18,701 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00035 $0.18701
Opus 5.5 $0.00014 $0.07480
Sonnet 5.5 $0.00007 $0.03740
Haiku 4.5 $0.00003 $0.01870

Measured 12d ago against content hash 677f061c4160, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

add-tool scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

const articles = await fetch(input.pmids);
Origin

This is a copy

100% identical to add-tool — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

framework-skills/add-tool/SKILL.md · 933 lines

How it starts

The opening of the file, as written. The whole thing — 933 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

Tools use the tool() builder from @cyanheads/mcp-ts-core. Each tool lives in src/mcp-server/tools/definitions/ with a .tool.ts suffix. The standard registration pattern uses a definitions/index.ts barrel that collects all tools into an allToolDefinitions array for createApp(). Fresh scaffolds from init start with direct imports in src/index.ts — the barrel is introduced as definitions grow. Match the pattern already used by the project you're editing.

Steps

  1. Gather the tool's name, purpose, and input/output shape from the user's request — ask only if genuinely absent
  2. Determine if it needs input the caller may not supply — a confirmation, a choice, the client's roots — which makes it a multi-round-trip handler (ctx.requestInput / ctx.inputs, see api-context)
  3. Create the file at src/mcp-server/tools/definitions/{{tool-name}}.tool.ts
  4. Register the tool in the project's existing createApp() tool list (directly in src/index.ts for fresh scaffolds, or via a barrel if the repo already has one)
  5. Run bun run devcheck to verify — it applies Biome's formatting fixes as it runs
  6. Smoke-test with bun run rebuild && bun run start:stdio < /dev/null (or start:http) — the Core services constructed log record must list the new tool in its tools field (the message text shows only counts); if it doesn't, the tool never reached createApp()

Naming

Tools use lowercase snake_case with a canonical server/domain prefix, {server}_{verb}_{noun} by default. Drop the noun only when the verb is a complete action on its own (git_pull, git_status): if {server}_{verb} leaves "…what?" unanswered — search what? connect to what? — the noun is missing. The full rule is the Name row of the design-mcp-server Design table.

Examples: pubmed_search_articles, pubmed_fetch_fulltext, clinicaltrials_find_eligible.

The server prefix is judged on clarity, not length: the brand name or the plain well-known word for the domain both pass (pubmed_, patents_); an abbreviation fails only when it reads as something else out of context (loc_, ct_). A fourth segment is fine when the noun is inherently two words (openfda_search_device_clearances). When a name resists the schema — can't pick a verb, noun feels generic, the verb wants a second word — that's usually a signal the scope is fuzzy; split the tool, rename, or reconsider.

Read the full file on GitHub · 933 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. 12d ago Changed · +7 lines 677f061c4160
  2. 14d ago Changed · +23 lines f19fd10d9330
  3. 1mo ago Changed · +21 lines 9210f47a1f51
  4. 1mo ago Changed · +46 lines 95ce1591e082
  5. 1mo ago Changed · +32 lines 631c1b8a21c0
  6. 2mo ago First seen · 804 lines · 35 tokens per session scan A 5ba100b246b6

Subscribe to this mod's changes

add-tool is a skill published in the GitHub repository cyanheads/usda-mcp-server (1 stars, last pushed 13d ago), licensed Apache-2.0. It adds 35 tokens to every session and 18,701 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to add-tool, differing in 0 lines, and is treated as a copy.

Related

add-tool compared with skills from other repositories

add-tool next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
add-toolcyanheads/usda-mcp-serverSkill113d agoApache-2.0A35Claude Code
openstreetmap-guidecyanheads/openstreetmap-mcp-serverSkill93d agoApache-2.0A50Claude Code
searchkalinbogatzevski/captain-memoSkill513d agoApache-2.0A49Claude Code
doctorkalinbogatzevski/captain-memoSkill513d agoApache-2.0A52Claude Code
socrata-guidecyanheads/socrata-mcp-serverSkill45d agoApache-2.0A51Claude Code
wikidata-guidecyanheads/wikidata-mcp-serverSkill311d agoApache-2.0A48Claude Code
treasury-fiscaldata-guidecyanheads/treasury-fiscaldata-mcp-serverSkill311d agoApache-2.0A38Claude Code