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.
npx agentmods add instructions/blake365/macrostrat-mcp/claude-mdgit clone --depth 1 https://github.com/blake365/macrostrat-mcpWrote 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.
[](https://agentmods.dev/instructions/blake365/macrostrat-mcp/claude-md)<a href="https://agentmods.dev/instructions/blake365/macrostrat-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/blake365/macrostrat-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00905 | $0.00905 |
| Opus 5 | $0.00452 | $0.00452 |
| Sonnet 5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
macrostrat-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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is a Model Context Protocol (MCP) server that provides access to the Macrostrat geological API. It enables AI assistants to query comprehensive geological data including geologic units, columns, minerals, and timescales.
Architecture
Core Components:
src/server.ts: Server factory (createServer) with all tools, prompts, resource schemas, and API integrations. Side-effect free — it only builds and returns anMcpServer. This is the package's library export.src/index.ts: STDIO entry point, and themacrostrat-mcpbin. ImportscreateServerand connects aStdioServerTransport.
Keeping them separate means src/server.ts can be imported and attached to a
different transport without starting stdio as a side effect.
Distribution: published to npm as macrostrat-mcp; the intended install path is
npx -y macrostrat-mcp. build/ is generated and gitignored — npm ships it via the
files field, so do not commit it.
Key Features:
- 8 tools for querying Macrostrat API endpoints
- 3 built-in prompts for common geological queries
- Resource schemas for API response validation
- Coordinate validation for geographic queries
- All tools are annotated
readOnlyHint: true; everything exceptlat-lng-to-tileis alsoopenWorldHint: true
Conventions:
- Use the shared
fetchJson()helper for Macrostrat JSON endpoints. It applies the 30s timeout and converts non-2xx responses and network failures into tool errors (isError: true) rather than throwing. - Native
fetchis used — do not reintroducenode-fetch.
Development Commands
# Install dependencies
npm install
# Compile TypeScript to build/ and set executable permissions
npm run build
# Run from source over STDIO, no build step
npm run dev
# Type-check without emitting
npm run typecheck
# No tests configured (test command will fail)
npm test # Returns error
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.
- 5d ago First seen · 110 lines · 905 tokens per session scan A 9e51b314a330
macrostrat-mcp CLAUDE.md is an instructions file published in the GitHub repository blake365/macrostrat-mcp (8 stars, last pushed 26d ago), licensed MIT. It adds 905 tokens to every session, about $0.0045 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.
Other instructions, from other repositories
ida-pro-mcp CLAUDE.md
Instructions for mrexodia/ida-pro-mcp, covering claude.md, what this project is, core implementation rules, ida thread safety and api conventions.
octocode AGENTS.md
AGENTS.md instructions for bgauryy/octocode, covering agents.md — octocode monorepo, dogfood, architecture, packages and tools.
obot CLAUDE.md
Claude Code instructions for obot-platform/obot, covering claude.md, project overview, tech stack, common commands and development.
tableau-mcp CLAUDE.md
Claude Code instructions for tableau/tableau-mcp, covering claude.md, build & development commands, building, running the server and testing.
MCP-Nest CLAUDE.md
Claude Code instructions for rekog-labs/MCP-Nest, covering claude.md, what this repo is, packages, layout and commands.
octocode CLAUDE.md
Claude Code instructions for bgauryy/octocode: Read AGENTS.md. Discover repository skills under .agents/skills and activate only those matching the task.