ToolsConnector: Skill for Claude Code

.agents/skills/mcp_generator/SKILL.md

mcp_generator is a skill for Claude Code, Codex from sachinshelke/ToolsConnector. It costs 10 tokens per session (258 once invoked), scanned A, original, Apache-2.0.

A development role for creating Model Context Protocol, or MCP, integrations that expose existing software capabilities to AI tools. It works on the MCP layer separately from the core library and individual connectors.

In plain words
What is it for?
Use it to build MCP servers, translate connector actions into MCP tools, optimize large tool schemas, and support paginated results.
Why use it?
It helps keep the integration layer independent while converting internal action metadata and pagination rules into MCP-compatible descriptions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is sachinshelke/ToolsConnector's own configuration. It tells Claude Code and Codex how to work on ToolsConnector 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 ToolsConnector configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sachinshelke/ToolsConnector. 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/sachinshelke/ToolsConnector/main/.agents/skills/mcp_generator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sachinshelke/ToolsConnector

Made for: Claude Code, 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_generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/sachinshelke/toolsconnector/mcp_generator/github.svg)](https://agentmods.dev/skills/sachinshelke/toolsconnector/mcp_generator)
Your own site
<a href="https://agentmods.dev/skills/sachinshelke/toolsconnector/mcp_generator"><img src="https://agentmods.dev/badge/skills/sachinshelke/toolsconnector/mcp_generator/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_generator

Your own site · 80×15
<a href="https://agentmods.dev/skills/sachinshelke/toolsconnector/mcp_generator"><img src="https://agentmods.dev/badge/skills/sachinshelke/toolsconnector/mcp_generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 258 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 $0.00010 $0.00258
Opus 5 $0.00005 $0.00129
Sonnet 5 $0.00002 $0.00052
Haiku 4.5 $0.00001 $0.00026

Measured 10d ago against content hash 31d8a6cd9d9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp_generator 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 10d 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.

.agents/skills/mcp_generator/SKILL.md · 20 lines

What it actually says

MCP Generator Persona

Overview

You are the MCP (Model Context Protocol) architect for ToolsConnector. Your sole domain is the toolsconnector-mcp layer. You do NOT touch the core library or the specific connectors. You only translate the internal capabilities of ToolsConnector into perfect, efficient MCP servers.

Rules

  1. Decoupled Architecture: The mcp/ logic must operate independently. It reads the metadata generated dynamically by BaseConnector and @action but should not force new requirements into the base library.
  2. Optimization: Standard JSON schema for 50 tools can consume half an LLM's context window. Your role is resolving "Prompt Tax." Build dynamic schema optimizers.
  3. MCP Specification Alignment: Your code must adhere perfectly to the latest Anthropic Model Context Protocol standards.

Execution Workflow

When asked to improve or build the MCP generation:

  1. Verify how toolsconnector extracts action metadata via Python's inspect and type hints.
  2. Build the translation layer that converts internal PaginatedList constraints into valid MCP pagination specifications.
  3. Ensure you provide examples of someone writing ONE line of code to deploy the server.
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. 10d ago First seen · 20 lines · 10 tokens per session scan A 31d8a6cd9d9a

Subscribe to this mod's changes

mcp_generator is a skill published in the GitHub repository sachinshelke/ToolsConnector (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 10 tokens to every session and 258 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

add-test

Use when adding unit or integration tests. Provides test patterns, naming conventions, and fixtures for Python (pytest), TypeScript (vitest), Java (JUnit/Mockito), and Rust.

open-metadata/ai-sdk · 40 tokens

validate-docs

Use when reviewing or validating documentation. Checks for clarity, completeness, broken links, undefined terms, and ensures beginners can follow guides without prior knowledge of the SDK.

open-metadata/ai-sdk · 36 tokens

debug-ci

Use when CI/CD pipeline fails. Provides systematic diagnosis for lint, type, test, and build failures across Python, TypeScript, Java, Rust, and n8n SDKs.

open-metadata/ai-sdk · 40 tokens

add-sdk-method

Use when adding a new method, function, or API endpoint to the SDK. Ensures consistent implementation across all SDKs (Python, TypeScript, Java, Rust CLI) with proper types, tests, and naming conventions.

open-metadata/ai-sdk · 49 tokens

run-integration

Use when running integration tests against a real Metadata instance. Guides setup of environment variables (AISDKHOST, AISDKTOKEN) and runs tests that make actual API calls.

open-metadata/ai-sdk · 40 tokens

dignified-python

Load ONLY for Python code Use when writing, reviewing, or refactoring Python to ensure adherence to LBYL exception handling patterns, modern type syntax (list[str], str | None), pathlib operations, ABC-based interfaces, absolute imports, and explicit error boundaries at CLI level. Also provides production-tested code…

open-metadata/ai-sdk · 92 tokens