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.
npx skills add sailingnaturali/claude-skills --skill debug-mcp-agentgit clone --depth 1 https://github.com/sailingnaturali/claude-skillsWrote 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/skills/sailingnaturali/claude-skills/debug-mcp-agent)<a href="https://agentmods.dev/skills/sailingnaturali/claude-skills/debug-mcp-agent"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/debug-mcp-agent/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/skills/sailingnaturali/claude-skills/debug-mcp-agent"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/debug-mcp-agent.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 | $0.00070 | $0.00613 |
| Opus 5 | $0.00035 | $0.00307 |
| Sonnet 5 | $0.00014 | $0.00123 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
debug-mcp-agent 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 10d 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.
Hit the underlying API / DB / tool yourself (curl, the CLI, a direct query) for the exact How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug an MCP / tool-backed agent
The agent's own narration of what went wrong is often the bug. Probe ground truth directly, out of band, before trusting anything the agent said.
1. Ground truth — query the source directly, bypass the agent
Hit the underlying API / DB / tool yourself (curl, the CLI, a direct query) for the exact thing the agent claimed was missing.
- Data is there → the failure is in the MCP/tool/agent layer, not the source.
- Genuinely absent (404 / empty) → that's "not available," not an error. Agents and MCP clients routinely conflate the two; a burst of 404s can even trip a client's circuit breaker and swallow valid reads afterward.
- Connection refused / unreachable → the source or the MCP process is down — not a missing field. Confirm the process/container is up; restart it.
2. Which model is driving?
Confirm the configured model is the one you expect. A weaker or local model silently swapped in is a common root cause of: leaked chain-of-thought, leaked control tokens, skipped tool calls, replies truncated mid-sentence, and confident confabulation about things it can't see.
3. The tool / MCP layer
- "MCP server X unreachable after N attempts" = the MCP process or its backing service died mid-conversation — not a missing path. Different fix than "data absent."
- Wrong path / argument guessed (e.g.
sensors.depthvs the realenvironment.depth.belowTransducer): the agent is inventing the schema. Ground the real shape in the prompt, or give it a list/describe tool so it stops guessing identifiers. - Auth, not absence: a
401/403on a write or a privileged/admin route is a permissions problem, not missing data — check the token's scope, not the data.
4. Plausible-but-wrong values
If the numbers look reasonable but are wrong, suspect a mock / fixture / sandbox data source rather than a logic bug — confirm which environment the agent is actually pointed at.
Close out
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.
- 10d ago First seen · 48 lines · 70 tokens per session scan A e0e323da95fc
debug-mcp-agent is a skill published in the GitHub repository sailingnaturali/claude-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 70 tokens to every session and 613 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.