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.
npx skills add NeoNexAI/presto-mcp-server --skill presto-usagegit clone --depth 1 https://github.com/NeoNexAI/presto-mcp-serverWrote 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.
[](https://agentmods.dev/skills/neonexai/presto-mcp-server/presto-usage)<a href="https://agentmods.dev/skills/neonexai/presto-mcp-server/presto-usage"><img src="https://agentmods.dev/badge/skills/neonexai/presto-mcp-server/presto-usage/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.
<a href="https://agentmods.dev/skills/neonexai/presto-mcp-server/presto-usage"><img src="https://agentmods.dev/badge/skills/neonexai/presto-mcp-server/presto-usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00183 | $0.01561 |
| Opus 5.5 | $0.00073 | $0.00624 |
| Sonnet 5.5 | $0.00037 | $0.00312 |
| Haiku 4.5 | $0.00018 | $0.00156 |
Grade A, and why
presto-usage 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Presto — cómo usar el MCP bien
Hay dos vías y elegir la correcta evita el 90% de los problemas:
- COM (en vivo): controla la obra abierta en Presto. Es la mayoría de tools. Requiere Presto 2025 instalado Y ABIERTO en este mismo equipo, con la obra abierta para operar sobre ella.
- BC3 (ficheros): las tools
presto_bc3_*leen/analizan ficheros.bc3(FIEBDC-3) sin Presto. Úsalas para auditar/consultar un presupuesto que te pasan como fichero, aunque Presto no esté instalado.
Flujo correcto (COM)
- Empieza SIEMPRE con
presto_status. Confirma que Presto responde por COM y el ProgID activo. Si falla: Presto no está abierto, o la versión no casa con el ProgID (Presto 2025 =Presto.App.25; otra versión → variablePRESTO_PROGID). - Asegúrate de que la obra correcta está abierta (
presto_open_obrasi hace falta abrir un.Prestoconcreto). - Lee/opera con las tools.
Si algo falla o vas a reportar un bug: presto_selftest primero
Antes de ir probando tools sueltas (o de pedirle al cliente que pruebe una a una
por chat), ejecuta presto_selftest. Es de solo lectura, no toca la obra, y
en una sola llamada comprueba: conexión, abrir la tabla Conceptos, leer los
primeros registros, buscar por código y buscar por resumen — exactamente las
rutas donde han aparecido los bugs reales hasta ahora. Devuelve un informe con
OK/FALLO paso a paso; pégalo entero al reportar un problema, ahorra varias idas
y vueltas.
Modelo de datos: Tabla.Campo
Presto organiza todo en tablas con campos. Los nombres exactos se ven en Presto con
Ver: Lista de campos; si una instalación difiere, ajusta el nombre. Los clave:
- Tabla
Conceptos:Conceptos.Código(clave única),Conceptos.Resumen,Conceptos.Ud, y precios por escenario:Conceptos.PrPres(presupuesto),PrCert(certificación),PrReal,PrObj(objetivo),PrPlan(planificado). - El filtro usa comodines de Presto:
"E04*","*hormigón*","*".
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.
- 2mo ago First seen · 107 lines · 183 tokens per session scan A 551191ac8b1e
presto-usage is a skill published in the GitHub repository NeoNexAI/presto-mcp-server (1 stars, last pushed 4mo ago), licensed MIT. It adds 183 tokens to every session and 1,561 once invoked, about $0.0007 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.
Other skills, from other repositories
buildwindow
Deterministic go/no-go verdicts for weather-dependent work, checked by the BuildWindow MCP server against weather limits the user supplies. Use when asked "can we paint the facade tomorrow?", "is it warm enough to pour concrete?", "can I fly the drone on Friday?" or "plan these jobs around the forecast".
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
dcc-blender-assembly-pitfalls
Read this BEFORE writing any Blender geometry code through MCP, whenever you are about to (1) create or size mesh primitives - bpy.ops.mesh.primitivecubeadd, primitivecylinderadd, primitiveuvsphereadd, primitiveconeadd - or set scale / dimensions on a part; (2) orient a part with rotationeuler or rotationquaternion…
color-theory
Use when constructing a reusable palette for a visual system: choose a harmony, assign semantic roles and light/dark token values, account for brand and cultural meaning plus color-vision deficiency, and ensure interaction states never rely on hue alone. Not for measuring an existing interface against an accessibility…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.