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/quantgist-technologies/quantgist_mcp/claude-mdgit clone --depth 1 https://github.com/QuantGist-Technologies/QuantGist_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/quantgist-technologies/quantgist_mcp/claude-md)<a href="https://agentmods.dev/instructions/quantgist-technologies/quantgist_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/quantgist-technologies/quantgist_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 | $0.02611 | $0.02611 |
| Opus 5 | $0.01306 | $0.01306 |
| Sonnet 5 | $0.00522 | $0.00522 |
| Haiku 4.5 | $0.00261 | $0.00261 |
Grade A, and why
QuantGist_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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — QuantGist MCP Server
Layer: L2 · Tentpole: T2 (AI/developer adoption)
Stack: Python 3.10+ using the official mcp SDK (low-level Server API, stdio transport)
Protocol: Model Context Protocol (MCP)
Distribution: PyPI package quantgist-mcp (entry point quantgist-mcp), runnable via pip/uv/uvx.
Purpose
Exposes QuantGist data as MCP tools so Claude and other AI agents can query macro events, earnings, and market snapshots — all within an AI conversation.
Use cases:
- Claude Code agents checking event risk before generating trading code
- Claude.ai / Claude Desktop users asking "what macro events affect EURUSD this week?"
- AI trading assistants checking "is it safe to trade gold right now?"
The server is a thin client over the public QuantGist REST API
(https://api.quantgist.com/v1). It holds no data of its own — every tool maps to
one or two REST calls. The earnings and markets tools require the corresponding
backend feature flags (EARNINGS_API_ENABLED, MARKETS_API_ENABLED) to be on in
production; both are enabled today.
MCP tools (22)
Macro events:
| Tool | Maps to |
|---|---|
get_upcoming_events |
GET /events (now → now+N hours) |
get_events_range |
GET /events (explicit range + country/impact/symbol filters) |
get_economic_calendar |
GET /calendar (single UTC day, macro calendar envelope with coverage/warnings) |
get_event_detail |
GET /events/{id} |
Earnings:
| Tool | Maps to |
|---|---|
get_earnings_upcoming |
GET /earnings/upcoming |
get_earnings_for_ticker |
GET /earnings/{ticker} |
get_earnings_summary |
GET /earnings/{ticker}/summary |
get_earnings_surprises |
GET /earnings/surprises |
get_earnings_season_summary |
GET /earnings/season/summary |
Markets:
| Tool | Maps to |
|---|---|
get_markets_overview |
GET /markets/overview |
Discovery / help (read-only, no API key — static/computed data in discovery.py):
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 · 214 lines · 2,611 tokens per session scan A 1e275e127d2b
QuantGist_MCP CLAUDE.md is an instructions file published in the GitHub repository QuantGist-Technologies/QuantGist_MCP (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,611 tokens to every session, about $0.0131 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
robinhood-mcp AGENTS.md
Instructions for verygoodplugins/robinhood-mcp, covering agents.md, project overview, read-only is a hard invariant, build & development and install with dev dependencies (editable).
longbridge-mcp CLAUDE.md
Claude Code instructions for longbridge/longbridge-mcp, covering code formatting, code style, generic bounds, imports and comments.
freetaxusa-mcp CLAUDE.md
Claude Code instructions for schwarztim/freetaxusa-mcp, covering freetaxusa mcp server, architecture, commands, tool categories and phase 1 (implemented).
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.
lobbywatch-mcp CLAUDE.md
Claude Code instructions for malkreide/lobbywatch-mcp, covering claude.md, teil 1 — portfolio-konventionen, vor der arbeit, tests and wenn etwas rot ist.
apra-mcp CLAUDE.md
Claude Code instructions for Bigred97/apra-mcp, covering apra-mcp, source, curated datasets (13), repo-specific module set and repo-specific gotchas.