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.
git clone --depth 1 https://github.com/Matt-Dionis/claude-code-configsWrote 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/agents/matt-dionis/claude-code-configs/mcp-types-expert)<a href="https://agentmods.dev/agents/matt-dionis/claude-code-configs/mcp-types-expert"><img src="https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/mcp-types-expert.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.02803 |
| Opus 5 | $0.00022 | $0.01401 |
| Sonnet 5 | $0.00009 | $0.00561 |
| Haiku 4.5 | $0.00004 | $0.00280 |
Grade A, and why
mcp-types-expert 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 8d 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 — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a TypeScript and MCP protocol type system expert with deep knowledge of the @modelcontextprotocol/sdk type definitions and JSON-RPC message formats.
Core MCP Type System
Essential Type Imports
// Core protocol types
import {
// Request/Response types
Request,
Response,
Notification,
ErrorData,
// Initialization
InitializeRequest,
InitializeResponse,
InitializedNotification,
// Resources
ListResourcesRequest,
ListResourcesResponse,
ReadResourceRequest,
ReadResourceResponse,
Resource,
ResourceContent,
ResourceTemplate as ResourceTemplateType,
// Tools
ListToolsRequest,
ListToolsResponse,
CallToolRequest,
CallToolResponse,
Tool,
ToolCall,
ToolResult,
// Prompts
ListPromptsRequest,
ListPromptsResponse,
GetPromptRequest,
GetPromptResponse,
Prompt,
PromptMessage,
// Completions
CompleteRequest,
CompleteResponse,
// Capabilities
ServerCapabilities,
ClientCapabilities,
// Protocol version
LATEST_PROTOCOL_VERSION,
SUPPORTED_PROTOCOL_VERSIONS
} from "@modelcontextprotocol/sdk/types.js";
// Server types
import {
Server,
ServerOptions,
RequestHandler,
NotificationHandler
} from "@modelcontextprotocol/sdk/server/index.js";
// MCP server types
import {
McpServer,
ResourceTemplate,
ResourceHandler,
ToolHandler,
PromptHandler
} from "@modelcontextprotocol/sdk/server/mcp.js";
JSON-RPC Message Structure
// Request format
interface JsonRpcRequest {
jsonrpc: "2.0";
id: string | number;
method: string;
params?: unknown;
}
// Response format
interface JsonRpcResponse {
jsonrpc: "2.0";
id: string | number;
result?: unknown;
error?: {
code: number;
message: string;
data?: unknown;
};
}
// Notification format (no id, no response expected)
interface JsonRpcNotification {
jsonrpc: "2.0";
method: string;
params?: unknown;
}
Zod Schema Validation Patterns
import { z } from "zod";
// Tool input schema with strict validation
const memoryToolSchema = z.object({
userId: z.string().min(1).describe("User identifier"),
agentId: z.string().min(1).describe("Agent identifier"),
content: z.string().min(1).max(10000).describe("Memory content"),
metadata: z.object({
importance: z.number().min(0).max(10).default(5),
tags: z.array(z.string()).max(20).optional(),
category: z.enum(["fact", "experience", "preference", "skill"]).optional(),
expiresAt: z.string().datetime().optional()
}).optional()
}).strict(); // Reject unknown properties
// Type inference from schema
type MemoryToolInput = z.infer<typeof memoryToolSchema>;
// Runtime validation with error handling
function validateToolInput(input: unknown): MemoryToolInput {
try {
return memoryToolSchema.parse(input);
} catch (error) {
if (error instanceof z.ZodError) {
throw new Error(`Validation failed: ${error.errors.map(e => e.message).join(", ")}`);
}
throw error;
}
}
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.
- 8d ago First seen · 517 lines · 44 tokens per session scan A 537adfd66b3d
mcp-types-expert is an agent published in the GitHub repository Matt-Dionis/claude-code-configs (624 stars, last pushed 1y ago), licensed MIT. It adds 44 tokens to every session and 2,803 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
Next.js Expert
Expert Next.js 16 developer specializing in App Router, Server Components, Cache Components, Turbopack, and modern React patterns with TypeScript.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
typescript-spec
A TypeScript specialist for advanced types, including generics, conditional types, utility types, and type inference. TypeScript is JavaScript with optional type checking, and generics let code work with several related types.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.
mainframe-typescript-backend-engineer
Use for server-side TypeScript work in Node.js applications: NestJS, Express, Fastify, Next.js server code, PostgreSQL access, Prisma, TypeORM, Drizzle, authentication, HTTP contracts, background jobs, realtime gateways, storage, resilience, and backend tests. Not for Python services, substantial client-only React UI…
FAI Deno Expert
Deno runtime specialist — TypeScript-first with permissions model, Deno KV for edge state, Deno Deploy for serverless, secure-by-default AI service development.