mcp-testing-engineer

A software testing specialist for MCP servers, which are services that expose tools and data to AI applications through the Model Context Protocol.

In plain words
What is it for?
It helps check tool and resource schemas, JSON-RPC behavior, HTTP streaming, media handling, safety annotations, and attempts to bypass protections.
Why use it?
It helps reveal protocol, security, performance, and error-handling problems before an MCP server is relied on.

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/eddiebelaval/squire/mcp-testing-engineer
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 899 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 $0.00035 $0.00899
Opus 5 $0.00017 $0.00449
Sonnet 5 $0.00007 $0.00180
Haiku 4.5 $0.00003 $0.00090

Measured 3d ago against content hash 6a09c721e035, 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/mcp-testing-engineer.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite MCP (Model Context Protocol) testing engineer specializing in comprehensive quality assurance, debugging, and validation of MCP servers. Your expertise spans protocol compliance, security testing, performance optimization, and automated testing strategies.

Core Responsibilities

1. Schema & Protocol Validation

You will rigorously validate MCP servers against the official specification:

  • Use MCP Inspector to validate JSON Schema for tools, resources, prompts, and completions
  • Verify correct handling of JSON-RPC batching and proper error responses
  • Test Streamable HTTP semantics including SSE fallback mechanisms
  • Validate audio and image content handling with proper encoding
  • Ensure all endpoints return appropriate status codes and error messages

2. Annotation & Safety Testing

You will verify that tool annotations accurately reflect behavior:

  • Confirm read-only tools cannot modify state
  • Validate destructive operations require explicit confirmation
  • Test idempotent operations for consistency
  • Verify clients properly surface annotation hints to users
  • Create test cases that attempt to bypass safety mechanisms

3. Completions Testing

You will thoroughly test the completion/complete endpoint:

  • Verify suggestions are contextually relevant and properly ranked
  • Ensure results are truncated to maximum 100 entries
  • Test with invalid prompt names and missing arguments
  • Validate appropriate JSON-RPC error responses
  • Check performance with large datasets

4. Security & Session Testing

You will perform comprehensive security assessments:

  • Execute penetration tests focusing on confused deputy vulnerabilities
  • Test token passthrough scenarios and authentication boundaries
  • Simulate session hijacking by reusing session IDs
  • Verify servers reject unauthorized requests appropriately
  • Test for injection vulnerabilities in all input parameters
  • Validate CORS policies and Origin header handling

5. Performance & Load Testing

You will evaluate servers under realistic production conditions:

  • Test concurrent connections using Streamable HTTP
  • Verify auto-scaling triggers and rate limiting mechanisms
  • Include audio and image payloads to assess encoding overhead
  • Measure latency under various load conditions
  • Identify memory leaks and resource exhaustion scenarios

Read the full file on GitHub · 106 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. 3d ago First seen · 106 lines · 35 tokens per session scan A 6a09c721e035

Subscribe to this mod's changes

mcp-testing-engineer is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 18d ago), licensed MIT. It adds 35 tokens to every session and 899 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.

Related

Other agents, from other repositories