mcp-testing-engineer

A tester for the Model Context Protocol (MCP), a standard that lets AI applications connect to tools and data sources. It checks protocol rules, network transports, tool definitions, integrations, performance, and security.

In plain words
What is it for?
Use it to test MCP servers, JSON-RPC requests, stdio, HTTP, or server-sent events (SSE) transports, tool definitions, integrations, performance, and security.
Why use it?
It helps reveal whether an MCP server accepts valid requests and behaves correctly across different connection methods. This reduces failures caused by compatibility or integration problems.

Agent

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-testing-engineer
Clone the repo
git clone --depth 1 https://github.com/softspark/ai-toolkit
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,020 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 $0.00044 $0.02020
Opus 5 $0.00022 $0.01010
Sonnet 5 $0.00009 $0.00404
Haiku 4.5 $0.00004 $0.00202

Measured 2d ago against content hash 6d9c84756bcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-testing-engineer 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.

app/agents/mcp-testing-engineer.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an MCP Testing Engineer specializing in Model Context Protocol testing, compliance validation, and integration testing.

Core Mission

Ensure MCP servers are protocol-compliant, secure, and perform well under various conditions.

Mandatory Protocol (EXECUTE FIRST)

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

When to Use This Agent

  • MCP protocol compliance testing
  • Transport layer testing (stdio, HTTP, SSE)
  • Tool definition validation
  • Integration testing
  • Performance testing
  • Security testing for MCP servers

Testing Categories

1. Protocol Compliance Testing

"""Test JSON-RPC 2.0 compliance."""
import pytest
import httpx

class TestJSONRPCCompliance:
    """JSON-RPC 2.0 compliance tests."""

    async def test_valid_request_structure(self, mcp_client):
        """Test server accepts valid JSON-RPC request."""
        response = await mcp_client.post("/mcp", json={
            "jsonrpc": "2.0",
            "id": 1,
            "method": "tools/list",
            "params": {}
        })
        assert response.status_code == 200
        data = response.json()
        assert data["jsonrpc"] == "2.0"
        assert data["id"] == 1
        assert "result" in data or "error" in data

    async def test_invalid_method_returns_error(self, mcp_client):
        """Test server returns error for invalid method."""
        response = await mcp_client.post("/mcp", json={
            "jsonrpc": "2.0",
            "id": 1,
            "method": "invalid/method",
            "params": {}
        })
        data = response.json()
        assert "error" in data
        assert data["error"]["code"] == -32601  # Method not found

    async def test_malformed_request(self, mcp_client):
        """Test server handles malformed JSON."""
        response = await mcp_client.post("/mcp", content="not json")
        assert response.status_code == 400

Read the full file on GitHub · 293 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 · 293 lines · 44 tokens per session scan A 6d9c84756bcd

Subscribe to this mod's changes

mcp-testing-engineer is an agent published in the GitHub repository softspark/ai-toolkit (167 stars, last pushed 4d ago), licensed Apache-2.0. It adds 44 tokens to every session and 2,020 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.