Laurigates Claude Plugins MCP Code Execution

MCP Code Execution Pattern

Expert knowledge for designing agent systems that generate and execute code to interact with MCP servers, instead of calling tools directly.

When to Use This Pattern

Core Architecture

How It Works

Instead of loading all MCP tool definitions into the model context upfront, the agent:

1. Discovers available tools by navigating a typed file tree
2. Generates TypeScript/Python code that imports and calls typed wrapper functions
3. Executes the code in a sandboxed environment
4. Returns only filtered/summarized results to the model

This reduces token usage from O(all_tool_definitions) to O(only_relevant_imports).

File Tree Structure

project/
├── servers/
│   ├── google-drive/
│   │   ├── getDocument.ts
│   │   ├── getSheet.ts
│   │   ├── listFiles.ts
│   │   └── index.ts          # Re-exports all tools
│   ├── salesforce/
│   │   ├── query.ts
│   │   ├── updateRecord.ts
│   │   └── index.ts
│   └── slack/
│       ├── sendMessage.ts
│       ├── getChannelHistory.ts
│       └── index.ts
├── skills/                    # Agent-accumulated reusable functions
│   └── save-sheet-as-csv.ts
├── workspace/                 # Persistent state between executions
├── client.ts                  # MCP client that routes calls to servers
└── sandbox.config.ts          # Execution environment configuration

Typed Wrapper Pattern

Each MCP tool gets a typed wrapper function that the agent imports:

// servers/google-drive/getDocument.ts
import { callMCPTool } from "../../client.js";

interface GetDocumentInput {
  documentId: string;
}

interface GetDocumentResponse {
  content: string;
}

/** Read a document from Google Drive */
export async function getDocument(
  input: GetDocumentInput
): Promise<GetDocumentResponse> {
  return callMCPTool<GetDocumentResponse>("google_drive__get_document", input);
}

The agent then writes code that uses these wrappers naturally:

import * as gdrive from "./servers/google-drive";
import * as salesforce from "./servers/salesforce";

const transcript = (
  await gdrive.getDocument({ documentId: "abc123" })
).content;

await salesforce.updateRecord({
  objectType: "SalesMeeting",
  recordId: "00Q5f000001abcXYZ",
  data: { Notes: transcript },
});

Key Patterns

1. Progressive Tool Discovery

The agent navigates the filesystem to find relevant tools on demand, instead of loading all definitions upfront.

Agent: "I need to read from Google Drive"
  → ls servers/
  → ls servers/google-drive/
  → cat servers/google-drive/getDocument.ts  (reads signature + JSDoc)
  → generates code importing only getDocument

Token impact: 150,000 tokens (all definitions) reduced to ~2,000 tokens (one definition). 98.7% reduction.

2. Context-Efficient Data Filtering

Filter large datasets in the execution environment before results reach the model:

// Filter in the sandbox — only summary reaches the model
const allRows = await gdrive.getSheet({ sheetId: "abc123" });
const pending = allRows.filter((row) => row["Status"] === "pending");
console.log(`Found ${pending.length} pending orders`);
console.log(pending.slice(0, 5)); // Only first 5 for model review

3. Native Control Flow

Replace chained tool calls with code-native loops and conditionals:

// Polling loop — runs entirely in sandbox
let found = false;
while (!found) {
  const messages = await slack.getChannelHistory({ channel: "C123456" });
  found = messages.some((m) => m.text.includes("deployment complete"));
  if (!found) await new Promise((r) => setTimeout(r, 5000));
}
console.log("Deployment notification received");

4. PII Tokenization

The MCP client intercepts responses and tokenizes sensitive data before it reaches the model:

// Agent writes this code
for (const row of sheet.rows) {
  await salesforce.updateRecord({
    objectType: "Lead",
    recordId: row.salesforceId,
    data: { Email: row.email, Phone: row.phone, Name: row.name },
  });
}
console.log(`Updated ${sheet.rows.length} leads`);

What the model sees in the execution output:

[
  { salesforceId: "00Q...", email: "[EMAIL_1]", phone: "[PHONE_1]", name: "[NAME_1]" },
  { salesforceId: "00Q...", email: "[EMAIL_2]", phone: "[PHONE_2]", name: "[NAME_2]" }
]
Updated 247 leads

The actual PII flows between external systems without entering model context.

5. State Persistence

Save intermediate results to the workspace for cross-execution continuity:

// Execution 1: fetch and save
const leads = await salesforce.query({
  query: "SELECT Id, Email FROM Lead LIMIT 1000",
});
await fs.writeFile("./workspace/leads.csv", leads.map((l) => `${l.Id},${l.Email}`).join("\n"));

// Execution 2: resume from saved state
const saved = await fs.readFile("./workspace/leads.csv", "utf-8");

6. Skill Accumulation

Agents persist reusable functions as skills for future executions:

// skills/save-sheet-as-csv.ts
import * as gdrive from "../servers/google-drive";
import * as fs from "fs/promises";

export async function saveSheetAsCsv(sheetId: string): Promise<string> {
  const data = await gdrive.getSheet({ sheetId });
  const csv = data.map((row) => row.join(",")).join("\n");
  const path = `./workspace/sheet-${sheetId}.csv`;
  await fs.writeFile(path, csv);
  return path;
}

Later executions import the skill directly:

import { saveSheetAsCsv } from "./skills/save-sheet-as-csv";
const csvPath = await saveSheetAsCsv("abc123");

Scaffolding a New Project

Step 1: Identify MCP Servers

List the MCP servers the agent needs to interact with. Check .mcp.json or the project's MCP configuration:

cat .mcp.json 2>/dev/null || echo "No MCP config found"

Step 2: Generate Server Directory

For each MCP server, create a directory with typed wrappers. Each tool gets its own file with:

• Input interface
• Output interface
• JSDoc comment describing the tool
• Async function wrapping callMCPTool

Step 3: Create the MCP Client

The client routes callMCPTool calls to the appropriate MCP server:

// client.ts
import { Client } from "@modelcontextprotocol/sdk/client/index.js";

const clients = new Map<string, Client>();

export async function callMCPTool<T>(
  toolName: string,
  input: Record<string, unknown>
): Promise<T> {
  const serverName = toolName.split("__")[0];
  const client = clients.get(serverName);
  if (!client) throw new Error(`No MCP client for server: ${serverName}`);

  const result = await client.callTool({ name: toolName, arguments: input });
  return result.content as T;
}

Step 4: Configure the Sandbox

The execution environment needs:

Step 5: Wire Up the Agent Loop

The agent loop becomes:

1. Receive user request
2. Agent explores servers/ tree to find relevant tools
3. Agent generates TypeScript code using typed wrappers
4. Code executes in sandbox
5. Filtered output returns to agent
6. Agent decides: done, or generate more code?

Security Checklist

Agentic Optimizations

Quick Reference

Token Impact

When NOT to Use This Pattern

• Simple integrations with 1-3 MCP servers
• All tool responses are small and needed by the model
• No sensitive data in tool responses
• Infrastructure complexity isn't justified (sandbox setup, monitoring)
• Prototype or proof-of-concept stage

Reference

• Anthropic Engineering: Code Execution with MCP
• Cloudflare "Code Mode" — independent validation of the same pattern

Converted and distributed by TomeVault — claim your Tome and manage your conversions.