agentmods.dev

web3-research-mcp: Instructions file for Claude Code

CLAUDE.md

web3-research-mcp CLAUDE.md is an instructions file for Claude Code from aaronjmars/web3-research-mcp. It costs 1,413 tokens per session, scanned A, original, MIT.

A guide for coding agents working on web3-research-mcp, a local server that lets AI clients search the web and query CoinGecko and DeFiLlama for cryptocurrency research.

In plain words
What is it for?
Use it when developing or running this TypeScript Model Context Protocol server, including its search, crypto-data, and reference-storage features.
Why use it?
It explains how the server is structured and how to build and run it without setting up a database or separate network service.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is aaronjmars/web3-research-mcp's own configuration. It tells Claude Code how to work on web3-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 web3-research-mcp configures →

not rated 161repo 5d ago A scan 1,413 tokens original MIT
View source ↗ aaronjmars/web3-research-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to aaronjmars/web3-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/aaronjmars/web3-research-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/aaronjmars/web3-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 web3-research-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aaronjmars/web3-research-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/aaronjmars/web3-research-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/aaronjmars/web3-research-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aaronjmars/web3-research-mcp/claude-md/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 web3-research-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/aaronjmars/web3-research-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aaronjmars/web3-research-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,413 This file is loaded in full into every session.
When invoked 1,413 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 $0.01413 $0.01413
Opus 5 $0.00707 $0.00707
Sonnet 5 $0.00283 $0.00283
Haiku 4.5 $0.00141 $0.00141

Measured 9d ago against content hash 99f56c975e23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

web3-research-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 9d 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 · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for AI agents (Claude Code and others) working in this repository.

What this is

web3-research-mcp is a Model Context Protocol server that gives an AI client (Claude Desktop, Cursor, etc.) a toolset for deep, free, and fully local crypto research — web search plus direct CoinGecko and DeFiLlama API access, with results stored as referenceable MCP resources.

It runs over stdio as a single Node process. There is no database and no network service to stand up: the client launches it via npx web3-research-mcp and talks to it on stdin/stdout.

Stack

  • TypeScript (ESM, "type": "module"), compiled with tsc to dist/.
  • @modelcontextprotocol/sdk — McpServer + StdioServerTransport.
  • zod — tool/prompt input schemas.
  • duck-duck-scrape — web/news/image/video search (no API key).
  • cheerio — parse fetched HTML. Network I/O uses the global fetch.
  • Node >= 18 (CI builds on 20.x and 22.x).

Build & run

npm ci            # install (use this in CI / clean checkouts)
npm run build     # tsc -> dist/
npm start         # node dist/server.js   (talks MCP over stdio)
npm run dev       # build + start

There is no test suite and no linter configured. CI (.github/workflows/ci.yml) is the source of truth for "does it pass": it runs npm ci → npm run build → asserts dist/server.js exists → node --check bin/cli.js → node bin/cli.js --help. Before opening a PR, run npm run build locally and make sure it's clean — tsc runs with strict: true, so type errors fail the build.

Layout

bin/cli.js                  npx entrypoint — spawns dist/server.js over stdio
src/server.ts               wires up McpServer: resources, the token-research prompt,
                            then calls registerAllTools()
src/tools/index.ts          registerAllTools() -> research + coingecko + defillama
src/tools/researchTools.ts  search, fetch-content, research-with-keywords,
                            create-research-plan, update-status, list-resources, ...
src/tools/coinGeckoTool.ts  coingecko-data / coingecko-search / coingecko-tickers
src/tools/defiLlamaTool.ts  defillama-data / defillama-search
src/utils/searchUtils.ts    performSearch / fetchContent / searchSource (DDG + fetch)
src/utils/format.ts         fmtUsd — shared number formatting
src/storage/researchStorage.ts  in-memory + on-disk research state and resources,
                            and the ResearchData / ResearchResource types

Read the full file on GitHub · 112 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. 9d ago First seen · 112 lines · 1,413 tokens per session scan A 99f56c975e23

Subscribe to this mod's changes

web3-research-mcp CLAUDE.md is an instructions file published in the GitHub repository aaronjmars/web3-research-mcp (161 stars, last pushed 5d ago), licensed MIT. It adds 1,413 tokens to every session, about $0.0071 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.

ResearchWeb3 and blockchainmcpmcp-cryptomcp-server
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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens