Skip to content
Agentmart
Submit a tool

mcp-server

Create high-quality MCP (Model Context Protocol) servers that extend DAX's tool capabilities.

Skill by ShaileshRawat1403

IndexedMIT★ 5
Write a review

Chalk Labs

Need help deploying mcp-server?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/shaileshrawat1403-mcp-server

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Create high-quality MCP (Model Context Protocol) servers that extend DAX's tool capabilities. Use when building MCP servers to integrate external APIs, services, or custom tools into DAX. Supports Python (FastMCP) and TypeScript (MCP SDK). Aligns with DAX's governance model - MCP tools will go through DAX's approval system.

Use cases: backend, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/mcp-server

What's inside

Skill name
mcp-server
Description
Create high-quality MCP (Model Context Protocol) servers that extend DAX's tool capabilities. Use when building MCP servers to integrate external APIs, services, or custom tools into DAX. Supports Python (FastMCP) and TypeScript (MCP SDK). Aligns with DAX's governance model - MCP tools will go through DAX's approval system.
License
MIT
Instructions
244 lines in SKILL.md · view on GitHub

Files (7)

  • SKILL.md
  • mcp-config.md · docs/
  • permissions.md · docs/
  • evaluation.md · reference/
  • mcp_best_practices.md · reference/
  • node_mcp_server.md · reference/
  • python_mcp_server.md · reference/

SKILL.md (first lines)

# MCP Server Development Guide for DAX

## Overview

MCP (Model Context Protocol) servers extend DAX's capabilities by adding custom tools that connect to external APIs and services. This skill guides you through creating high-quality MCP servers that integrate seamlessly with DAX's governance and execution model.

When you create an MCP server for DAX:

- Tools automatically integrate with DAX's tool pipeline
- Each tool call goes through DAX's approval system (RAO contract)
- Tool usage is tracked in the audit ledger
- You can configure per-tool permissions in `dax.json`

---

## Process

### Phase 1: Research and Planning

#### 1.1 Understand MCP Design Principles

**API Coverage vs. Workflow Tools:**

- Prioritize comprehensive API coverage for flexibility
- Add specialized workflow tools for common tasks
- DAX agents can compose operations across multiple tools

**Tool Naming:**

- Use clear, descriptive names with consistent prefixes
- Example: `github_create_issue`, `filesystem_read_file`
- Helps DAX's intent classification match tools to user needs

**Tool Descriptions:**

- Write concise descriptions (1-2 sentences)
- Include parameter descriptions
- DAX uses descriptions for tool selection

**Error Handling:**

- Provide actionable error messages with specific suggestions
- DAX will surface errors through its verification system

#### 1.2 Study MCP Protocol

**Key Resources:**

- MCP Specification: `https://modelcontextprotocol.io/specification/draft.md`
- Best Practices: [MCP Best Practices](./reference/mcp_best_practices.md)

#### 1.3 Choose Your Stack

| Language       | SDK                       | Best For                           |
| -------------- | ------------------------- | ---------------------------------- |
| **TypeScript** | @modelcontextprotocol/sdk | Node.js projects, type safety      |
| **Python**     | mcp                       | FastMCP, data science integrations |

**Transport Selection:**

- **stdio**: Local servers, testing
- **streamable-http**: Production, remote servers

---

### Phase 2: Implementation

#### 2.1 Project Setup

**TypeScript:**

```bash
mkdir my-mcp-server && cd my-mcp-server
npm init -y
npm install @modelcontextprotocol/sdk @modelcontextprotocol/server-filesystem
```

**Python:**

```bash
pip install mcp fastmcp
```

#### 2.2 Core Infrastructure

Create utilities for:

- API client with authentication
- Error handling
- Response formatting
- Pagination

#### 2.3 Implement Tools

For each tool, define:

**Input Schema (TypeScript with Zod):**

```typescript
{
  name: "create_issue",
  description: "Create a new GitHub issue",
  inputSchema: z.object({
    title: z.string().describe("Issue title"),
    body: z.string().optional().describe("Issue body"),
    labels: z.array(z.string()).optional().describe("Labels to apply"),
  })
}
```

**Annotations (important for DAX governance):**

- `readOnlyHint`: true/false - Read-only vs mutating operations
- `destructiveHint`: true/false - Potentially destructive actions
- `idempotentHint`: true/false - Safe to retry

DAX uses these hints to determine approval requirements.

---

From ShaileshRawat1403/dax, MIT.

More from ShaileshRawat1403/dax

Signals

Stars
5
Forks
0
Open issues
0
Last commit (this folder)
Apr 19, 2026 (6 months ago)
Last release
Oct 8, 2026 (23 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ShaileshRawat1403

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get mcp-server running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying mcp-server?

CallGet help
Cite this page

mcp-server skill. Agent Mart. https://agentmart.dev/skills/shaileshrawat1403-mcp-server (last updated 2026-10-24)