mcp-tool-patterns

A coding-agent skill that documents patterns for adding and changing MCP tools in Akashic Context. MCP is a standard way for an AI agent to call external tools through defined inputs and outputs.

In plain words
What is it for?
Use it when modifying the MCP server, especially when adding tools, changing tool inputs, or registering handlers in the server code.
Why use it?
It reduces mistakes in tool schemas, input validation, error handling, response formatting, and registration.

Skill for Claude CodeCodex

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 skills/tostechbr/memoryclaw/mcp-tool-patterns
Any agent
npx skills add tostechbr/memoryClaw --skill mcp-tool-patterns
Clone the repo
git clone --depth 1 https://github.com/tostechbr/memoryClaw

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 999 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 $0.00045 $0.00999
Opus 5 $0.00023 $0.00500
Sonnet 5 $0.00009 $0.00200
Haiku 4.5 $0.00005 $0.00100

Measured 2d ago against content hash 23e079d718ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-tool-patterns 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 2d 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/skills/mcp-tool-patterns/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Tool Patterns — Akashic Context

Tool Registration Pattern

Tools are registered in setupToolHandlers() inside ListToolsRequestSchema handler. Each tool needs: name, description, inputSchema (JSON Schema).

{
  name: "memory_context",
  description: "Get or set working memory (context.json) for a user.",
  inputSchema: {
    type: "object",
    properties: {
      userId: {
        type: "string",
        description: "User identifier (default: 'default')",
      },
      action: {
        type: "string",
        enum: ["get", "set"],
        description: "Get or set working memory",
      },
      data: {
        type: "object",
        description: "Data to set (only for action='set')",
      },
    },
    required: ["action"],
  },
},

Handler Pattern (Zod validation)

All handlers use Zod for input validation:

private async handleMemoryContext(args: unknown) {
  const schema = z.object({
    userId: z.string().optional().default("default"),
    action: z.enum(["get", "set"]),
    data: z.record(z.unknown()).optional(),
  });

  const { userId, action, data } = schema.parse(args);

  // implementation...
}

Adding userId to Existing Tools

Before (hardcoded):

// In constructor
this.manager = new MemoryManager({
  dataDir,
  userId: "mcp-user",   // hardcoded
  workspaceDir: config.workspaceDir,
  // ...
});

After (per-call userId): The manager must be created per-call (or use a manager factory/cache). Pattern: create MemoryManager per userId on demand, cache by userId.

private managers = new Map<string, MemoryManager>();

private getManager(userId: string): MemoryManager {
  if (!this.managers.has(userId)) {
    const manager = new MemoryManager({
      dataDir: this.dataDir,
      userId,
      workspaceDir: this.workspaceDir,  // base dir, manager appends users/{userId}
      memory: this.memoryConfig,
    });
    if (this.embeddingConfig) {
      this.setupEmbeddingProviderForManager(manager, this.embeddingConfig);
    }
    this.managers.set(userId, manager);
  }
  return this.managers.get(userId)!;
}

Read the full file on GitHub · 166 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. 2d ago First seen · 166 lines · 45 tokens per session scan A 23e079d718ad

Subscribe to this mod's changes

mcp-tool-patterns is a skill published in the GitHub repository tostechbr/memoryClaw (8 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 999 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 2026-08-31.