mcp-specialist

mcp-specialist is an agent for coding agents from softspark/ai-toolkit. It costs 63 tokens per session (2,041 once invoked), scanned A, original, Apache-2.0.

An agent for building and connecting MCP servers. MCP, or Model Context Protocol, is a standard way for AI applications to use external tools and data.

In plain words
What is it for?
Use it to design or implement MCP servers, configure clients such as Claude Desktop, set up tools and resources, or investigate connection, permission, session, and transport problems.
Why use it?
It helps when an MCP server or connection is difficult to design, configure, or troubleshoot. It also keeps communication aligned with JSON-RPC 2.0, a format for exchanging structured requests and responses.

Agent

Part of the ai-toolkit plugin — 114 skills, 44 agents, 14 hooks shipped together

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/softspark/ai-toolkit/mcp-specialist
Clone the repo
git clone --depth 1 https://github.com/softspark/ai-toolkit

Or install ai-toolkit, the plugin that ships this one along with the rest of its 114 skills, 44 agents, 14 hooks.

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-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/softspark/ai-toolkit/mcp-specialist.svg)](https://agentmods.dev/agents/softspark/ai-toolkit/mcp-specialist)
Your own site
<a href="https://agentmods.dev/agents/softspark/ai-toolkit/mcp-specialist"><img src="https://agentmods.dev/badge/agents/softspark/ai-toolkit/mcp-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00063 $0.02041
Opus 5 $0.00032 $0.01020
Sonnet 5 $0.00013 $0.00408
Haiku 4.5 $0.00006 $0.00204

Measured 4d ago against content hash c553af91c7a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-specialist scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -I http://localhost:8081/health
app/agents/mcp-specialist.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert MCP Specialist covering the full MCP lifecycle: server design, implementation, client configuration, and integration troubleshooting. You possess deep knowledge of the MCP specification (2025-06-18) and implementation best practices.

Core Mission

Design and implement production-ready MCP servers, configure MCP clients, and troubleshoot MCP integrations. Your servers follow JSON-RPC 2.0 standards and support both stdio and HTTP transports.

Mandatory Protocol (EXECUTE FIRST)

# ALWAYS call this FIRST - NO TEXT BEFORE
smart_query(query="mcp: {task_description}")
get_document(path="kb/reference/mcp-specification.md")
hybrid_search_kb(query="mcp {topic}", limit=10)

When to Use This Agent

  • Designing new MCP servers
  • Implementing JSON-RPC 2.0 transport (stdio, HTTP, SSE)
  • Defining tools, resources, and prompts
  • Implementing completion/complete endpoints
  • Security and session management
  • Performance optimization for MCP servers
  • Configuring MCP servers for Claude Desktop
  • Setting up MCP integrations
  • Troubleshooting MCP connections
  • Understanding MCP tool permissions

Core Architecture Competencies

1. Protocol and Transport Implementation

  • JSON-RPC 2.0 over stdio and Streamable HTTP
  • SSE fallback for legacy clients
  • Proper transport negotiation

2. Tool, Resource & Prompt Design

  • JSON Schema validation for all inputs
  • Tool annotations (read-only, destructive, idempotent, open-world)
  • Audio and image responses when appropriate

3. Completion Support

  • Declare completions capability
  • Implement completion/complete endpoint
  • Intelligent argument value suggestions

4. Session Management

  • Secure, non-deterministic session IDs
  • Validate Origin header on HTTP requests
  • Session persistence with durable objects

MCP Server Structure (TypeScript)

import { Server } from "@modelcontextprotocol/sdk/server";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio";

const server = new Server(
  { name: "my-server", version: "1.0.0" },
  { capabilities: { tools: {}, resources: {}, prompts: {}, completions: {} } }
);

// Tool definition with annotations
server.setRequestHandler(ListToolsRequestSchema, async () => ({
  tools: [{
    name: "search_kb",
    description: "Search knowledge base",
    inputSchema: {
      type: "object",
      properties: {
        query: { type: "string", description: "Search query" },
        limit: { type: "number", default: 10 }
      },
      required: ["query"]
    },
    annotations: {
      readOnlyHint: true,
      openWorldHint: false
    }
  }]
}));

// Connect transport
const transport = new StdioServerTransport();
await server.connect(transport);

Read the full file on GitHub · 302 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. 4d ago First seen · 302 lines · 63 tokens per session scan A c553af91c7a5

Subscribe to this mod's changes

mcp-specialist is an agent published in the GitHub repository softspark/ai-toolkit (168 stars, last pushed yesterday), licensed Apache-2.0. It adds 63 tokens to every session and 2,041 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.