mcp-binding

mcp-binding is a skill for Claude Code from kavo-labs/kavo. It costs 93 tokens per session (1,729 once invoked), scanned A, original, MIT.

Reference documentation for exposing Kavo data entities as MCP tools. MCP is a standard way for AI clients to call tools, and the binding maps common create, read, update, and delete operations to those tools.

In plain words
What is it for?
Use it when exposing entities to an MCP client or configuring Kavo's MCP module and routes.
Why use it?
It explains the available operations, argument shapes, error mapping, and authentication limitation so integrations can be wired correctly.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the kavo-skills plugin — 15 skills shipped together

Good fit Use it when exposing entities to an MCP client or configuring Kavo's MCP module and routes.

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

Made for: Claude Code.

Or install kavo-skills, the plugin that ships this one along with the rest of its 15 skills.

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-binding

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kavo-labs/kavo/mcp-binding"><img src="https://agentmods.dev/badge/skills/kavo-labs/kavo/mcp-binding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,729 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00093 $0.01729
Opus 5 $0.00046 $0.00864
Sonnet 5 $0.00019 $0.00346
Haiku 4.5 $0.00009 $0.00173

Measured 7d ago against content hash 7806cf73090b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-binding 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 7d 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.

extensions/skills/mcp-binding/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP binding reference

@kavo/mcp exposes a createCrud service's standard operations as MCP tools. Every tool handler calls directly into the same engine pipeline REST binds to — no parallel request path, no second copy of filter/sort/pagination validation, no separate error handling.

@kavo/mcp is host-framework-agnostic: it imports @kavo/core and the @modelcontextprotocol/sdk peer for types only, never @kavo/nest. @kavo/nest depends on @kavo/mcp, not the other way around (ADR-0016).

One entity's toolset

import { crudTools } from "@kavo/mcp";

const bindings = crudTools({
  name: "Owner",
  service: ownerService, // whatever createCrud(Owner, ...) returned
});

Each KavoMcpToolBinding pairs one MCP Tool definition with its handler. There is no per-entity configcrudTools always produces the full standard set:

Tool Args
owner.findOne { id }
owner.findMany { limit?, offset?, sort?, filter? }
owner.createOne any fields (forwarded straight to the create DTO)
owner.updateOne { id, ...anyFields }
owner.patchOne { id, ...anyFields }
owner.deleteOne { id }
owner.restoreOne { id }
owner.purgeOne { id }

This mirrors @Kavo enabling every standard operation by default. There is no cross-check against the OperationRegistry: an entity that never declared soft delete still gets restoreOne/purgeOne tools, and calling one returns an OperationDisabledException as a normal error result — exactly what calling the equivalent disabled REST route would do.

Read the full file on GitHub · 153 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. 7d ago First seen · 153 lines · 93 tokens per session scan A 7806cf73090b

Subscribe to this mod's changes

mcp-binding is a skill published in the GitHub repository kavo-labs/kavo (14 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 1,729 once invoked, about $0.0005 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 2026-09-02.

Related

Other skills, from other repositories

ocli-api

Turn any OpenAPI/Swagger API into CLI commands and call them. Search endpoints with BM25, check parameters, execute — no MCP server needed.

EvilFreelancer/openapi-to-cli · 34 tokens

procedure

Vovk.ts procedures — atomic unit of server-side logic in Vovk project. Use whenever user asks to build ANYTHING producing or consuming data on server — page loading data ("users page", "dashboard", "product list"), endpoint, API handler, server action, form submission, controller, validation with Zod / Valibot /…

finom/vovk · 342 tokens

rpc

Vovk.ts RPC client — how vovk generate turns controllers into type-safe client modules, composed vovk-client vs segmented clients, call shape (apiRoot, params, body, query, meta, init, disableClientValidation, validateOnClient, interpretAs, transform, fetcher), customizing generation via outputConfig.imports.fetcher +…

finom/vovk · 354 tokens

tools

Building LLM tools with Vovk.ts — deriveTools() (procedures → tools), createTool() (standalone tools, no controller/procedure needed), @operation.tool({ name, title, description, hidden }) decorator, x-tool metadata, ToModelOutput.DEFAULT vs ToModelOutput.MCP formatters, the tools + toolsByName return shape, the meta…

finom/vovk · 261 tokens

decorators

Vovk.ts decorators — built-in (@prefix, @operation, @get/@post/@put/@patch/@del, .auto()) and custom via createDecorator. Covers authorization / auth decorators, middleware-style wrapping (pre-handler + post-handler logic), req.vovk.meta() for cross-decorator state, stacking order, the decorate() alternative for…

finom/vovk · 228 tokens

mixins

Vovk.ts OpenAPI mixins — importing third-party OpenAPI 3.x schemas as typed client modules that share the same call signature as native Vovk RPC modules. Use whenever the user asks to "call a third-party API from my Vovk app", "mixin an OpenAPI schema", "import an OpenAPI spec as a client", "wrap an external service…

finom/vovk · 275 tokens