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/cohend/fin-data-mcp/claude-mdgit clone --depth 1 https://github.com/CohenD/fin-data-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/cohend/fin-data-mcp/claude-md)<a href="https://agentmods.dev/instructions/cohend/fin-data-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cohend/fin-data-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 | $0.01618 | $0.01618 |
| Opus 5 | $0.00809 | $0.00809 |
| Sonnet 5 | $0.00324 | $0.00324 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
fin-data-mcp CLAUDE.md scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. Add the key to `config.ts` + `.env.example`. Run build + a curl check. 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.
fin-data-mcp-server — agent guide
A standalone Model Context Protocol server exposing free financial market data
across 13 categories. Lives inside the cc-stack workspace but is its own Node
package with its own deps. 83 no-key tools (15 providers) always on; optional
free keys unlock 7 more providers (up to 110 tools / 22 providers).
Stack / runtime
- TypeScript + ESM (
"type": "module",module: NodeNext). Relative imports MUST use the.jsextension (e.g.import { httpGet } from "../lib/http.js"). @modelcontextprotocol/sdkover stdio (StdioServerTransport).- Zod v3 (
^3.25) — pinned for MCP SDKinputSchema(ZodRawShape) compat. This deliberately diverges from the parent repo's Zod 4 convention; do not "upgrade" it without checking the SDK still accepts the raw-shape schemas. - No
axios/extra HTTP libs — uses nativefetchviasrc/lib/http.ts.
Commands
npm run build # tsc → dist/ (run before considering work done)
npm run dev # tsx watch src/index.ts
npm start # node dist/index.js (stdio)
npx tsc --noEmit # typecheck (strict + noUncheckedIndexedAccess)
npx tsx scripts/smoke.ts # core no-key endpoints
npx tsx scripts/smoke-full.ts # broad sample incl. expanded + chained discovery
npx tsx scripts/mcp-test.ts # MCP handshake: tools/list, resource, a tool call
Architecture
src/
index.ts # stdio entry (never write to stdout — logs go to stderr)
server.ts # createServer(): instructions, registers tools w/ annotations,
# structuredContent + CHARACTER_LIMIT truncation, error mapping,
# the fin-data://catalog resource
config.ts # all env config (all optional)
constants.ts # CHARACTER_LIMIT (~25k), DEFAULT_PAGE_SIZE
lib/
http.ts # httpGet(url, {params,headers,accept,retries,timeoutMs}); HttpError;
# formatHttpError() → actionable messages; sends Accept-Language: en
cache.ts # cached(key, fn, ttlMs) in-memory TTL
tool.ts # ToolDef + tool() helper (applies read-only annotations centrally)
providers/
index.ts # PROVIDERS registry → allTools (enabled only) + catalog
<provider>.ts # one file per source; exports `<name>Tools: ToolDef[]`
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.
- 4d ago First seen · 112 lines · 1,618 tokens per session scan A 65dfed1a3182
fin-data-mcp CLAUDE.md is an instructions file published in the GitHub repository CohenD/fin-data-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,618 tokens to every session, about $0.0081 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
LLM-TradeBot copilot-instructions.md
Copilot instructions for EthanAlgoX/LLM-TradeBot, covering repository instructions, core rules, validation and ai asset governance.
Convertible-Bond-Pricing-Research CLAUDE.md
Instructions for ericxuzhesheng/Convertible-Bond-Pricing-Research, covering claude.md — convertible bond pricing research, current published state and routine commands.
bukio-cli AGENTS.md
AGENTS.md instructions for erikvankempen/bukio-cli, covering agents.md — bukio-cli agent manual, 1. house rules (non-negotiable), 2. environment, 3. command quick reference and 3.1 jurisdiction profiles (16 markets).
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.