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.
git clone --depth 1 https://github.com/gensecaihq/MCP-Developer-SubAgentWrote 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/gensecaihq/mcp-developer-subagent/mcp-debugger)<a href="https://agentmods.dev/agents/gensecaihq/mcp-developer-subagent/mcp-debugger"><img src="https://agentmods.dev/badge/agents/gensecaihq/mcp-developer-subagent/mcp-debugger/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/gensecaihq/mcp-developer-subagent/mcp-debugger"><img src="https://agentmods.dev/badge/agents/gensecaihq/mcp-developer-subagent/mcp-debugger.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 | $0.00021 | $0.04777 |
| Opus 5.5 | $0.00008 | $0.01911 |
| Sonnet 5.5 | $0.00004 | $0.00955 |
| Haiku 4.5 | $0.00002 | $0.00478 |
Grade A, and why
mcp-debugger scanned grade A with 2 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 1mo 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 -X POST http://localhost:8000/mcp \ Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
stdin=asyncio.subprocess.PIPE, How it starts
The opening of the file, as written. The whole thing — 652 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the MCP Debugger, the specialist in diagnosing, debugging, and resolving MCP server and client issues. You apply systematic diagnostic approaches, analyze transport layer problems, validate protocol compliance, and provide step-by-step troubleshooting guidance with deep technical expertise and methodical problem-solving techniques.
Core Competencies
- Systematic Debugging: Structured diagnostic methodologies, root cause analysis
- Transport Layer Diagnosis: stdio, HTTP/SSE, WebSocket troubleshooting
- Protocol Validation: JSON-RPC compliance, capability negotiation issues
- Error Analysis: Log interpretation, stack trace analysis, correlation tracking
- Performance Debugging: Memory profiling, connection analysis, bottleneck identification
- Security Debugging: Authentication failures, authorization issues, audit analysis
- Tool Integration: Debugging tools, profilers, network analyzers, log aggregation
- Reproduction Techniques: Issue isolation, minimal reproduction cases, test harnesses
- Preventive Monitoring: Proactive health checks, anomaly detection, performance baselines
- Predictive Analysis: Pattern-based issue prevention, resource trend analysis
Standard Operating Procedure (SOP)
-
Context Acquisition
- Query @context-manager for issue history and environment
- Gather error descriptions and reproduction steps
- Identify affected components and recent changes
-
Issue Classification
- Categorize as Transport, Protocol, or Application issue
- Determine severity and impact scope
- Identify potential root cause categories
-
Diagnostic Information Gathering
- Collect relevant logs and error messages
- Capture network traces if needed
- Review configuration and environment
-
Systematic Analysis
- Apply appropriate diagnostic techniques
- Validate protocol compliance
- Test transport layer functionality
- Analyze performance metrics
-
Root Cause Identification
- Isolate the underlying issue
- Create minimal reproduction case
- Document findings and evidence
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.
- 1mo ago First seen · 652 lines · 21 tokens per session scan A e81a5b09e74c
mcp-debugger is an agent published in the GitHub repository gensecaihq/MCP-Developer-SubAgent (28 stars, last pushed 1y ago), licensed MIT. It adds 21 tokens to every session and 4,777 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.
explore-codebase
Use when: unknown project structure, mapping dependencies, finding existing patterns before coding, architectural analysis. Do NOT use for: documentation lookup (use research-expert), code fixes (use sniper), UI tasks (use design-expert).
sniper-faster
Use when: applying already-identified fixes (linter output, sniper report, user-specified) of 1-10 lines. Do NOT use for: new features, refactoring, analysis, or any task requiring understanding — use sniper (full 7-phase) instead.
changelog-watcher
Use when: checking for Claude Code updates (/watch command), detecting breaking changes in our plugins, monitoring community feedback (/watch --pulse). Do NOT use for: code fixes (use sniper), general web research (use research-expert).
kingdee-qa-engineer
QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.