dfns-mcp: Instructions file for Claude Code

CLAUDE.md

dfns-mcp CLAUDE.md is an instructions file for Claude Code from jhubbardsf/dfns-mcp. It costs 934 tokens per session, scanned A, original, MIT.

Project instructions for dfns-mcp, a server that gives AI agents access to DFNS documentation and software-development-kit reference material. It explains the project structure, startup commands, document downloading, caching, and publishing.

In plain words
What is it for?
Use it when starting the DFNS MCP server, developing it with automatic file watching, inspecting it, understanding its documentation cache, or publishing the package.
Why use it?
It gives contributors the project-specific information needed to run and develop the server without guessing where files come from or how updates work.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is jhubbardsf/dfns-mcp's own configuration. It tells Claude Code how to work on dfns-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 dfns-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jhubbardsf/dfns-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/jhubbardsf/dfns-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jhubbardsf/dfns-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 dfns-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jhubbardsf/dfns-mcp/claude-md.svg)](https://agentmods.dev/instructions/jhubbardsf/dfns-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jhubbardsf/dfns-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jhubbardsf/dfns-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 934 This file is loaded in full into every session.
When invoked 934 The same file — it is already loaded in full.
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 $0.00934 $0.00934
Opus 5 $0.00467 $0.00467
Sonnet 5 $0.00187 $0.00187
Haiku 4.5 $0.00093 $0.00093

Measured 7d ago against content hash 37caa8d63c70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dfns-mcp CLAUDE.md 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 7d 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.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DFNS MCP Server

MCP (Model Context Protocol) server that provides AI agents with access to DFNS documentation and SDK reference.

Project Structure

dfns-mcp/
├── src/
│   ├── index.ts         # Main MCP server - tools, resources, startup
│   ├── indexer.ts       # Document indexing and search logic
│   └── docs-fetcher.ts  # Downloads and caches docs from docs.dfns.co + GitHub
├── package.json
├── README.md
└── LICENSE

Note: The dfns-api-docs/ and dfns-sdk-ts/ directories are NOT part of the repo. They are automatically downloaded to ~/.cache/dfns-mcp/ on first run.

Running the Server

# Start the server
bun run start

# Development with watch mode
bun run dev

# Inspect with MCP Inspector
bun run inspect

Publishing

# Publish to npm
npm publish

# Users install with:
bunx dfns-mcp@latest

Architecture Overview

Documentation Fetching

The server automatically downloads DFNS docs on first startup from two sources:

  1. Cache Location: ~/.cache/dfns-mcp/
  2. Sources Fetched:
    • API Docs: https://docs.dfns.co/llms-full.txt (split into individual markdown files)
    • SDK Types: dfns/dfns-sdk-ts GitHub tarball (branch: m)
  3. Update Strategy: Auto-checks every 24 hours, or manual via update_docs tool
  4. Mechanism: Docs fetched as single file and split; SDK downloaded as GitHub tarball
  5. Graceful Degradation: If a fetch fails but cached data exists, server continues with stale data

Indexing

  • In-memory index: Documents and types indexed at startup
  • Document scoring: Title (100pts), phrase (30pts), keyword (5pts)
  • Type indexer: Parses TypeScript for type, interface, class definitions
  • Categories: Auto-detected from file paths

MCP Tools Provided

Documentation Tools

Tool Description
init Initialize DFNS MCP context and establish documentation requirements
search_docs Full-text search across all documentation
get_doc Retrieve specific document by path
list_docs List documents, optionally by category
get_code_examples Extract code blocks from documentation
browse_api_structure Hierarchical view of API endpoints
get_blockchain_info Get SDK info for a specific blockchain
list_blockchains List all supported blockchains
get_api_endpoint Get documentation for specific API endpoint

Read the full file on GitHub · 123 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. 7d ago First seen · 123 lines · 934 tokens per session scan A 37caa8d63c70

Subscribe to this mod's changes

dfns-mcp CLAUDE.md is an instructions file published in the GitHub repository jhubbardsf/dfns-mcp (0 stars, last pushed 7mo ago), licensed MIT. It adds 934 tokens to every session, about $0.0047 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens