mcp

mcp is a command for coding agents from vyuh-labs/dxkit. It costs 0 tokens per session (606 once invoked), scanned A, original, MIT.

A command that exposes dxkit's read-only code-repository tools through the Model Context Protocol. MCP is a standard connection that lets coding agents such as Claude Code, Cursor, or VS Code call tools from a repository.

In plain words
What is it for?
Finding which functions call or are called by other functions, seeing a file's affected symbols and tests, reviewing file history, checking ownership, and viewing recorded technical debt.
Why use it?
It lets an agent inspect code relationships and history without manually searching through every file or changing the repository.

Command

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/vyuh-labs/dxkit/mcp
Clone the repo
git clone --depth 1 https://github.com/vyuh-labs/dxkit

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/vyuh-labs/dxkit/mcp.svg)](https://agentmods.dev/commands/vyuh-labs/dxkit/mcp)
Your own site
<a href="https://agentmods.dev/commands/vyuh-labs/dxkit/mcp"><img src="https://agentmods.dev/badge/commands/vyuh-labs/dxkit/mcp.svg" alt="Measured on agentmods" 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 606 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00606
Opus 5 $0.00000 $0.00303
Sonnet 5 $0.00000 $0.00121
Haiku 4.5 $0.00000 $0.00061

Measured 3d ago against content hash d3bc6ac9341f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp 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 3d 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.

docs/commands/mcp.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vyuh-dxkit mcp

Serve dxkit's read-only repo tools over the Model Context Protocol, so any MCP-capable coding agent (Claude Code, Cursor, VS Code) can call them natively while working in your repo.

vyuh-dxkit mcp [path] [--no-names]

This is not a command you run by hand. You register it once with your agent, and the agent launches it on demand:

# Claude Code
claude mcp add dxkit -- npx vyuh-dxkit mcp

For other agents, add an entry to their MCP configuration with command npx and arguments vyuh-dxkit mcp (the repo the agent works in must have dxkit installed as a devDependency, or dxkit installed globally).

What the agent gets

The same read-only point-query tools the learn --serve assistant uses, from the same registry:

Tool Answers
function_callers Who calls this function/method (from the committed code graph)
function_callees What this function/method calls
file_blast_radius Symbols in a file + the test files that transitively exercise it
file_history Recent commits touching a file or line range
file_owners Active recency-weighted ownership + bus factor
debt_findings Grandfathered findings from the committed baseline, filtered by kind / file

An agent that asks "why is this safe to change?" gets dxkit's canonical computed answers instead of re-deriving them from file greps. When the code graph is absent, the tools answer with the exact enable command (vyuh-dxkit describe) rather than an error.

Scope and safety

  • Read-only, structurally. No write path exists on this surface: no tool mutates anything, executes a policy command, or touches configuration. The guardrail's verdicts never consume anything returned here.
  • stdio only. Newline-delimited JSON-RPC over stdin/stdout — no port, no network listener, nothing reachable from outside the process the agent spawned.
  • Path arguments are guarded against traversal, absolute paths, and option injection.
  • Contributor names: the consuming agent already has full git access in your repo, so file_history / file_owners include author names by default. Pass --no-names at registration time to suppress them (counts and dates only).

Read the full file on GitHub · 43 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. 3d ago First seen · 43 lines · 0 tokens per session scan A d3bc6ac9341f

Subscribe to this mod's changes

mcp is a command published in the GitHub repository vyuh-labs/dxkit (10 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 606 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 2026-08-31.