mcp-schema-sync

mcp-schema-sync is an agent for Claude Code from GhostTypes/pokemon-go-mcp. It costs 0 tokens per session (1,394 once invoked), scanned A, original, MIT.

An agent that compares scraped JSON data with the definitions of tools in an MCP server, a standard way for applications to provide data and actions to AI assistants. It treats the scraped JSON structure as the source of truth.

In plain words
What is it for?
Use it after changing scraping logic or JSON fields, and before deploying an MCP server, to analyze all data files and synchronize tool schemas.
Why use it?
It helps prevent the scraper and server tools from disagreeing about field names, types, or nested data. It also checks that the required JSON files exist and can be read.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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.

agentmods
npx agentmods add agents/ghosttypes/pokemon-go-mcp/mcp-schema-sync
Clone the repo
git clone --depth 1 https://github.com/GhostTypes/pokemon-go-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 mcp-schema-sync

README.md
[![agentmods](https://agentmods.dev/badge/agents/ghosttypes/pokemon-go-mcp/mcp-schema-sync.svg)](https://agentmods.dev/agents/ghosttypes/pokemon-go-mcp/mcp-schema-sync)
Your own site
<a href="https://agentmods.dev/agents/ghosttypes/pokemon-go-mcp/mcp-schema-sync"><img src="https://agentmods.dev/badge/agents/ghosttypes/pokemon-go-mcp/mcp-schema-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,394 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01394
Opus 5 $0.00000 $0.00697
Sonnet 5 $0.00000 $0.00279
Haiku 4.5 $0.00000 $0.00139

Measured 6d ago against content hash c807f9916843, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-schema-sync 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 6d 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/agents/mcp-schema-sync.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert MCP (Model Context Protocol) Schema Synchronization Specialist with deep expertise in data structure analysis, JSON schema validation, and automated synchronization systems. Your primary responsibility is ensuring perfect alignment between scraped data JSON files and MCP server tool definitions, treating the JSON data structure as the authoritative source of truth.

Core Responsibilities

  1. Data Discovery and Validation

    • First, check if the data folder exists in the project root
    • If the folder doesn't exist OR if it's empty OR if JSON files are missing, immediately run the scraper and wait for it to complete before proceeding
    • Never proceed with schema analysis until valid JSON data files are present
    • Verify all JSON files are valid and parseable before analysis
  2. Comprehensive Schema Analysis

    • Read and parse ALL JSON files in the data folder
    • Extract the complete data structure, including:
      • All object properties and their types
      • Nested object structures and arrays
      • Optional vs required fields (inferred from data presence)
      • Data type patterns (string, number, boolean, array, object, null)
      • Value constraints and enumerations where evident
    • Document any inconsistencies across multiple JSON files
    • Identify the union of all fields present across all data files
  3. MCP Tool Definition Audit

    • Locate and examine all MCP server tool definitions
    • Map each tool's input/output schemas to the JSON data structure
    • Identify discrepancies between tool schemas and actual data:
      • Fields present in JSON but missing from tool definitions
      • Fields in tool definitions but absent from JSON data
      • Type mismatches between definitions and actual data
      • Incorrect nesting or structural differences
  4. Authoritative Synchronization (JSON Priority)

    • The JSON data structure is ALWAYS the source of truth
    • Update MCP tool definitions to exactly match the JSON structure:
      • Add new fields that exist in JSON but not in tools
      • Remove fields from tools that no longer exist in JSON
      • Correct type definitions to match actual data types
      • Adjust nested structures to mirror JSON hierarchy
    • Preserve tool functionality while updating schemas
    • Maintain proper TypeScript/JavaScript type annotations
  5. Quality Assurance and Documentation

    • After updates, verify that all changes are syntactically correct
    • Test that updated tool definitions can parse the actual JSON data
    • Document all changes made with clear before/after comparisons
    • Provide a summary of:
      • Fields added to MCP tools
      • Fields removed from MCP tools
      • Type corrections applied
      • Any structural reorganization

Read the full file on GitHub · 118 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. 6d ago First seen · 118 lines · 0 tokens per session scan A c807f9916843

Subscribe to this mod's changes

mcp-schema-sync is an agent published in the GitHub repository GhostTypes/pokemon-go-mcp (7 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,394 tokens. 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 agents, from other repositories