upv-mcp: Skill for Claude Code

.claude/skills/add-mcp-tool/SKILL.md

add-mcp-tool is a skill for Claude Code from pgomsan/upv-mcp. It costs 100 tokens per session (1,127 once invoked), scanned A, original, MIT.

Development instructions for adding or changing tools in upv-mcp, an MCP server for academic information. They cover output models, database queries, migrations, tool modules, and descriptions.

In plain words
What is it for?
Use them when adding a new MCP tool, changing its inputs or outputs, updating academic database queries, or changing its description.
Why use it?
They provide a consistent process for exposing new capabilities while reporting incomplete or truncated data honestly.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is pgomsan/upv-mcp's own configuration. It tells Claude Code how to work on upv-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything upv-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pgomsan/upv-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pgomsan/upv-mcp/master/.claude/skills/add-mcp-tool/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pgomsan/upv-mcp

Made for: Claude Code.

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-mcp-tool

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/pgomsan/upv-mcp/add-mcp-tool"><img src="https://agentmods.dev/badge/skills/pgomsan/upv-mcp/add-mcp-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,127 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 $0.00100 $0.01127
Opus 5.5 $0.00040 $0.00451
Sonnet 5.5 $0.00020 $0.00225
Haiku 4.5 $0.00010 $0.00113

Measured 2mo ago against content hash f26ebf00c07c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

add-mcp-tool 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.

.claude/skills/add-mcp-tool/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anadir una tool a upv-mcp

Una tool nueva son cinco ficheros. Sigue el orden: el modelo de salida primero, la descripcion al final (es lo que mas se reescribe).

1. Modelo de salida en src/upv_mcp/models.py

Un modelo pydantic con Field(description=...) en cada campo: el SDK los convierte en el output schema que ve el cliente.

Envuelvelo en un ...Result que incluya meta: ResultMeta. No es opcional: meta lleva truncated, stale y coverage_note, que son lo que evita que el modelo presente datos recortados o incompletos como si fueran la verdad completa.

2. Consulta en src/upv_mcp/cache/db.py

Filtra en SQL, no en Python. Anade el metodo ..._between(...) y su count_..._between(...) hermano: hacen falta los dos, porque el contador es lo que permite reportar el truncado con honestidad.

Si cambias el esquema: edita schema.sql, sube SCHEMA_VERSION y anade la rama de migracion en migrate().

3. Modulo en src/upv_mcp/tools/<nombre>.py

Una tool por modulo. Exporta dos cosas: DESCRIPTION (constante) y una funcion async que recibe repo: AcademicRepository primero y limit: int como keyword.

async def mi_tool(repo: AcademicRepository, param: str, *, limit: int) -> MiResult:
    if <parametro invalido>:
        raise ValueError("mensaje que el usuario final pueda entender")
    await repo.ensure_fresh()
    total = repo.cache.count_...(...)
    items = repo.cache....(..., limit=limit)
    return MiResult(items=items, meta=build_meta(repo, total_matching=total, returned=len(items)))

Prohibido en este fichero: importar mcp, httpx2 o icalendar. Si crees que los necesitas, el trabajo va en sources/, no aqui.

4. Registro en src/upv_mcp/server.py

Unico sitio que toca el SDK. El Context se recibe por parametro (en el SDK 2.x no existe get_context()):

@mcp.tool(title="Titulo corto", description=mi_tool_module.DESCRIPTION)
async def mi_tool(param: str, ctx: Context[AppContext]) -> MiResult:
    app = ctx.request_context.lifespan_context
    return await mi_tool_module.mi_tool(app.repo, param, limit=app.settings.max_results)

Read the full file on GitHub · 104 lines

Files

What ships with it

1 file 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 · 104 lines · 100 tokens per session scan A f26ebf00c07c

Subscribe to this mod's changes

add-mcp-tool is a skill published in the GitHub repository pgomsan/upv-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,127 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.

Related

add-mcp-tool compared with skills from other repositories

add-mcp-tool next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
add-mcp-toolpgomsan/upv-mcpSkill11mo agoMITA100Claude Code
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA78Claude Code
fastapi-router-pymicrosoft/skillsSkill3.2kyesterdayMITA46Claude Code
dev-runtimelangwatch/langwatchSkill5.0kyesterdayApache-2.0A172Claude Code
api-designericrisco/rsc-harnessSkill5032d agoMITA105Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1Skill252yesterdayMITA106Claude Code