A diagnostic command for a video-research add-on that checks its setup, connections to an MCP server, and API access. MCP is a way for an assistant to connect to external tools.

Running quick or detailed checks of selected configuration files, environment settings, manifests, and the video-research service connection.

It finds configuration or connection problems while keeping the normal health-check output short and readable.

doctor — Command for Claude Code by Galbaz1

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.

Clone the repo

git clone --depth 1 https://github.com/Galbaz1/video-research-mcp

Made for: Claude Code.

Or install gr, the plugin that ships this one along with the rest of its 12 skills, 17 commands, 7 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/galbaz1/video-research-mcp/doctor/github.svg)](https://agentmods.dev/commands/galbaz1/video-research-mcp/doctor)

Your own site

<a href="https://agentmods.dev/commands/galbaz1/video-research-mcp/doctor"><img src="https://agentmods.dev/badge/commands/galbaz1/video-research-mcp/doctor/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/galbaz1/video-research-mcp/doctor"><img src="https://agentmods.dev/badge/commands/galbaz1/video-research-mcp/doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,362 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.01362
Opus 5	$0.00006	$0.00681
Sonnet 5	$0.00003	$0.00272
Haiku 4.5	$0.00001	$0.00136

Measured 11d ago against content hash 1e7d9ea0c4e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

doctor 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 11d 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.

commands/doctor.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doctor: $ARGUMENTS

Run a deterministic health check for the video-research plugin and MCP server.

Mode

Default mode is quick.
If $ARGUMENTS contains full, run extra checks for agent/manifest drift.

Context Discipline (mandatory)

Keep quick mode output compact: target <= 220 tokens.
Never print raw tool payloads, JSON blobs, full file contents, or stack traces.
Never run broad repository searches. Only inspect exact paths listed below.
Extract only the required keys from config/env files.
If you need details, include one short line: Run /gr:doctor full for deep diagnostics.

Tool discipline (mandatory)

Only use the tools listed in allowed-tools. In particular:

File reading: use Read (Claude Code built-in), never plugin:serena:serena - Read File or any other MCP file-reading tool.
File search: use Glob (Claude Code built-in), never Serena's find_file or list_dir.
Shell: use Bash (Claude Code built-in), never Serena's execute_shell_command.

1) Discover active config

Use Glob + Read to inspect:

./.mcp.json
~/.claude/.mcp.json
~/.config/video-research-mcp/.env
./.env (optional)

Determine active server config:

If ./.mcp.json has mcpServers.video-research, treat it as active.
Otherwise use ~/.claude/.mcp.json.

Capture and report:

Active config path
video-research command + args
Whether an env block exists under mcpServers.video-research
Whether shared config file exists and contains:
- GEMINI_API_KEY
- YOUTUBE_API_KEY (optional)
- WEAVIATE_URL (optional)

If the active .mcp.json contains unresolved placeholders (for example ${WEAVIATE_URL}), flag it as a warning and recommend removing the env block in favor of ~/.config/video-research-mcp/.env.

2) Runtime config check

Call infra_configure() with no arguments to inspect live server settings. Never pass preset unless it is exactly one of: best, stable, budget. Do not call infra_configure(preset="").

Read the full file on GitHub · 144 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.

11d ago First seen · 144 lines · 13 tokens per session scan A 1e7d9ea0c4e8

Subscribe to this mod's changes

doctor is a command published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 1,362 once invoked, about $0.0001 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.

Claude Code Debugging ai-tools gemini mcp mcp-server

doctor

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Doctor: $ARGUMENTS

Mode

Context Discipline (mandatory)

Tool discipline (mandatory)

1) Discover active config

2) Runtime config check

What this file has done since we first saw it

Other commands, from other repositories

eg-fix-bug

safe-decompile

latent-fix

setup-video-vision

debug

troubleshoot-user