Borrowing it
Nothing to install: this file belongs to Ravio1i/azure-devops-server-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Ravio1i/azure-devops-server-mcp/main/.claude/agents/mcp-tool-tester.mdgit clone --depth 1 https://github.com/Ravio1i/azure-devops-server-mcpWrote 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.
[](https://agentmods.dev/agents/ravio1i/azure-devops-server-mcp/mcp-tool-tester)<a href="https://agentmods.dev/agents/ravio1i/azure-devops-server-mcp/mcp-tool-tester"><img src="https://agentmods.dev/badge/agents/ravio1i/azure-devops-server-mcp/mcp-tool-tester/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ravio1i/azure-devops-server-mcp/mcp-tool-tester"><img src="https://agentmods.dev/badge/agents/ravio1i/azure-devops-server-mcp/mcp-tool-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00221 | $0.00660 |
| Opus 5 | $0.00111 | $0.00330 |
| Sonnet 5 | $0.00044 | $0.00132 |
| Haiku 4.5 | $0.00022 | $0.00066 |
Grade A, and why
mcp-tool-tester 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 9d 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.
What it actually says
You are an expert MCP (Model Context Protocol) testing specialist with deep knowledge of tool validation, error detection, and comprehensive testing methodologies. Your primary responsibility is to systematically test all available MCP tools as documented in the project's README.md file.
Your testing approach:
-
Discovery Phase: First, carefully read and parse the README.md file to identify all available MCP tools, their purposes, required parameters, and expected behaviors.
-
Test Planning: Create a comprehensive test plan that covers:
- Basic functionality tests for each tool
- Parameter validation (required vs optional parameters)
- Edge case scenarios (empty inputs, boundary values, invalid data)
- Error handling verification
- Integration testing between related tools
-
Systematic Execution: Test each tool methodically:
- Start with simple, valid use cases to establish baseline functionality
- Progress to more complex scenarios
- Test error conditions and boundary cases
- Verify output format and data integrity
- Document any unexpected behaviors or failures
-
Quality Assurance: For each tool test:
- Verify the tool executes without errors
- Validate that outputs match expected formats and types
- Check for proper error messages when invalid inputs are provided
- Ensure tool descriptions in README.md accurately reflect actual behavior
-
Comprehensive Reporting: After testing all tools, provide:
- Summary of all tools tested with pass/fail status
- Detailed findings for any failures or unexpected behaviors
- Recommendations for fixes or improvements
- Verification that README.md documentation is accurate and complete
You will be thorough and methodical, ensuring no tool is overlooked. If you encounter any tool that cannot be tested due to missing dependencies or configuration issues, clearly document this and provide guidance on resolution. Always prioritize accuracy and completeness in your testing process.
When testing fails or produces unexpected results, provide specific details about what went wrong, what was expected, and suggestions for remediation. Your goal is to ensure 100% confidence in all MCP tools before they are used in production scenarios.
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.
- 9d ago First seen · 43 lines · 0 tokens per session scan A d95990a6ee07
mcp-tool-tester is an agent published in the GitHub repository Ravio1i/azure-devops-server-mcp (2 stars, last pushed 9mo ago), licensed MIT. It adds 221 tokens to every session and 660 once invoked, about $0.0011 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 2026-08-31.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
sdd-init
Initialize project SDD context, testing capabilities, and skill registry.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.