openrouter-deep-research-mcp: Command for Claude Code

.claude/commands/mcp-graph-explore.md

mcp-graph-explore is a command for Claude Code from wheattoast11/openrouter-deep-research-mcp. It costs 0 tokens per session (242 once invoked), scanned A, original, MIT.

A command for exploring a knowledge graph from a starting node. A knowledge graph stores things such as reports and concepts together with the relationships between them.

In plain words
What is it for?
Use it to trace connected nodes, discover topics, and show paths between related reports using a chosen search depth or traversal method.
Why use it?
It helps reveal connected information and relationships without manually checking each related report.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is wheattoast11/openrouter-deep-research-mcp's own configuration. It tells Claude Code how to work on openrouter-deep-research-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything openrouter-deep-research-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wheattoast11/openrouter-deep-research-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.

Copy the file
curl -O https://raw.githubusercontent.com/wheattoast11/openrouter-deep-research-mcp/main/.claude/commands/mcp-graph-explore.md
Clone the repo
git clone --depth 1 https://github.com/wheattoast11/openrouter-deep-research-mcp

Made for: Claude Code.

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.

agentmods badge for mcp-graph-explore

README.md
[![agentmods](https://agentmods.dev/badge/commands/wheattoast11/openrouter-deep-research-mcp/mcp-graph-explore/github.svg)](https://agentmods.dev/commands/wheattoast11/openrouter-deep-research-mcp/mcp-graph-explore)
Your own site
<a href="https://agentmods.dev/commands/wheattoast11/openrouter-deep-research-mcp/mcp-graph-explore"><img src="https://agentmods.dev/badge/commands/wheattoast11/openrouter-deep-research-mcp/mcp-graph-explore/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.

agentmods 80×15 button for mcp-graph-explore

Your own site · 80×15
<a href="https://agentmods.dev/commands/wheattoast11/openrouter-deep-research-mcp/mcp-graph-explore"><img src="https://agentmods.dev/badge/commands/wheattoast11/openrouter-deep-research-mcp/mcp-graph-explore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 242 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00242
Opus 5 $0.00000 $0.00121
Sonnet 5 $0.00000 $0.00048
Haiku 4.5 $0.00000 $0.00024

Measured 10d ago against content hash 66ef75b1d110, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-graph-explore 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 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.

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.

.claude/commands/mcp-graph-explore.md · 31 lines

What it actually says

MCP Graph Explorer

Explore the knowledge graph starting from a node using the OpenRouter Agents MCP server.

Instructions

  1. Parse the user's input for:

    • Node ID (e.g., "report:5") - required
    • Depth (optional, default 3)
    • Strategy (optional: "bfs", "dfs", or "semantic")
  2. If the user provides just a number, assume it's a report ID: "report:{number}"

  3. Run graph traversal using mcp__openrouter-agents__graph_traverse with:

    • startNode: The node identifier (e.g., "report:5")
    • depth: How many levels to explore (default 3)
    • strategy: "semantic" (default), "bfs", or "dfs"
  4. Present the graph structure showing:

    • Connected nodes and their relationships
    • Key concepts and topics discovered
    • Paths between related reports

Example Usage

/mcp-graph-explore report:5 /mcp-graph-explore 5 --depth=2 --strategy=bfs

User's Graph Query

$ARGUMENTS

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. 10d ago First seen · 31 lines · 0 tokens per session scan A 66ef75b1d110

Subscribe to this mod's changes

mcp-graph-explore is a command published in the GitHub repository wheattoast11/openrouter-deep-research-mcp (55 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 242 tokens. 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.