debug-mcp

A troubleshooting command for diagnosing why the Terror MCP server cannot connect. MCP is a standard way for an AI assistant to connect to external tools.

In plain words
What is it for?
Use it to check Terror installation files and the project’s .mcp.json configuration, and to identify common connection mistakes.
Why use it?
It helps find setup errors such as missing files, an incorrect Bun path, or the wrong server entry file.

Command for Claude Code

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 commands/lazorgurl/terror/debug-mcp
Clone the repo
git clone --depth 1 https://github.com/lazorgurl/terror

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 757 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00011 $0.00757
Opus 5 $0.00005 $0.00378
Sonnet 5 $0.00002 $0.00151
Haiku 4.5 $0.00001 $0.00076

Measured yesterday against content hash 7b8149767d05, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

debug-mcp scanned grade B 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 yesterday.

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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

cat .mcp.json
.claude/plugins/terror/commands/debug-mcp.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug Terror MCP Connection

Systematically diagnose why the Terror MCP server isn't connecting.

Step 1: Check if Terror source is installed

ls ~/.terror/src/packages/core/dist/bin.js

If the file doesn't exist:

  • Check if ~/.terror/src exists at all — if not, Terror was never installed. Run the install steps from https://raw.githubusercontent.com/lazorgurl/terror/main/docs/install.md.
  • If ~/.terror/src exists but dist/bin.js doesn't, it needs building: cd ~/.terror/src && bun install && bun run build

Step 2: Check .mcp.json in the current project

cat .mcp.json

Verify:

  • command must be the absolute path to bun (e.g. /Users/you/.bun/bin/bun), NOT node or bun. Run which bun to get the correct path.
  • args must point to bin.js (NOT index.js). The path must be absolute (no ~).
  • If .mcp.json doesn't exist, offer to create it using the AskUserQuestion tool to gather the project ID and region.

Common mistakes to check:

  • Using node instead of bun — dependencies are in Bun's module store
  • Using index.js instead of bin.jsindex.js only exports modules, it doesn't start a server
  • Using ~ in paths — .mcp.json doesn't expand tilde
  • Using relative paths — must be absolute

Step 3: Test the server directly

Run the server to see if it starts:

echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' | <bun-path> <bin.js-path> 2>&1

Expected output: a JSON-RPC response with "serverInfo":{"name":"terror","version":"0.1.0"}.

If you see errors:

  • "Cannot find module" — run cd ~/.terror/src && bun install
  • stderr output before the JSON — the log level may be too verbose. Set TERROR_LOG_LEVEL=error in the .mcp.json env.
  • No output at all — the entrypoint is wrong. Must be bin.js.

Step 4: Check for conflicting configs

find . -name ".mcp.json" -maxdepth 3

Read the full file on GitHub · 77 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. yesterday First seen · 77 lines · 11 tokens per session scan B 7b8149767d05

Subscribe to this mod's changes

debug-mcp is a command published in the GitHub repository lazorgurl/terror (0 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 757 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.