What is gryps-agent-mcp CLAUDE.md?

Repository instructions for gryps-agent-mcp, a read-only local server that gives agents live market and venue data from Gryps v2. They define the server’s layout, safety boundaries, and checks.

Use them when changing the server, its symbol lookup, package contents, tests, diagnostics, or verification process.

They preserve rules that prevent accidental trading features, credential handling, package leaks, broken message output, and unsafe symbol guessing.

How gryps-finance/gryps-agent-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to gryps-finance/gryps-agent-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/gryps-finance/gryps-agent-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/gryps-finance/gryps-agent-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gryps-finance/gryps-agent-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/gryps-finance/gryps-agent-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/gryps-finance/gryps-agent-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gryps-finance/gryps-agent-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gryps-finance/gryps-agent-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gryps-finance/gryps-agent-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 399 This file is loaded in full into every session.

When invoked 399 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.

Model	Per session	Once invoked
Fable 5.1	$0.00399	$0.00399
Opus 5	$0.00199	$0.00199
Sonnet 5	$0.00080	$0.00080
Haiku 4.5	$0.00040	$0.00040

Measured 11d ago against content hash c33b41c5d8df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

gryps-agent-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 11d 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 · 33 lines

What it actually says

gryps-agent-mcp — agent notes

Public read-only MCP server (stdio) for live Gryps v2 market/venue data, plus a private single-account observer profile that never ships in the npm tarball.

Hard invariants — do not "improve" these away

PUBLIC_TOOL_NAMES is a frozen four-tool allowlist with boundary tests.
The public package must never gain execution, signing, credentials, env-var configuration, or a network listener. Execution belongs in a separate package (see ROADMAP.md §5).
internal-src/, internal-test/, internal-dist/ must stay out of the npm tarball (npm run verify:package proves it).
stdout belongs to the stdio MCP transport. Diagnostics go to stderr only.
Symbol resolution is exact-match only, after an exact-keyed rewrite through the curated alias table in src/symbols.ts. An alias is a rename, not a guess: it rewrites the query and never asserts a market exists. Substring guessing stays refused. Edit-distance results are suggestions only — they surface in gryps_list_markets and in not_found messages, labelled as guesses, and never resolve a symbol.

Layout

src/ public server: config → client (HTTP+cache+retry) → service (envelopes) → server (MCP tools).
internal-src/ observer: same shape, one wallet address fixed at process start.
scripts/ release verification (npm run verify:release chains all of it).

Verification

npm run verify:release must pass before any commit lands on main. npm run smoke:live needs network access; it is not part of CI PR gates. Style: no semicolons, single quotes, explicit .js on relative imports.

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.

11d ago First seen · 33 lines · 399 tokens per session scan A c33b41c5d8df

Subscribe to this mod's changes

gryps-agent-mcp CLAUDE.md is an instructions file published in the GitHub repository gryps-finance/gryps-agent-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 399 tokens to every session, about $0.0020 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.

Finance and fintech

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 · 7,126 tokens

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

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

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

gryps-agent-mcp: Instructions file for Claude Code