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 skills add cyanheads/finnhub-mcp-server --skill finnhub-guidegit clone --depth 1 https://github.com/cyanheads/finnhub-mcp-serverWrote 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/skills/cyanheads/finnhub-mcp-server/finnhub-guide)<a href="https://agentmods.dev/skills/cyanheads/finnhub-mcp-server/finnhub-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/finnhub-mcp-server/finnhub-guide/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.
<a href="https://agentmods.dev/skills/cyanheads/finnhub-mcp-server/finnhub-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/finnhub-mcp-server/finnhub-guide.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.00634 |
| Opus 5.5 | $0.00021 | $0.00254 |
| Sonnet 5.5 | $0.00010 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
finnhub-guide 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 8d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
Use Finnhub for current equity context and financial news. This surface does not provide historical price candles or FX rates; forex and crypto news categories do not imply pricing tools.
Identifiers
For an unfamiliar company or ambiguous ticker, select the intended security from finnhub_search_symbols using its name and security type, then carry the returned symbol through the briefing. Do not substitute its display label or rewrite class-share punctuation. isLikelyUS is a symbol-format heuristic; a successful search does not establish access to every endpoint.
Gates
- Before concluding that data is absent, establish the intended security and name the endpoint and window checked. An empty company-news window, empty earnings calendar, and missing analyst recommendations do not establish that the security is invalid or that no information exists elsewhere.
- Before interpreting missing fundamentals or peers, inspect
partial. A failed component is unavailable; a null metric is not zero. A quote succeeding does not establish company-profile or analyst coverage for that security, including a fund or trust. - Before describing a price as current, retain its quote timestamp and market-status context. A false
priceIsLivealone does not establish a prior-close timestamp; unavailable market status means freshness is unknown. Preserve returned session and holiday information. - Before claiming a list is complete, inspect truncation and totals. Increasing a limit can expose more of the fetched response, not establish exhaustive historical coverage. Do not promise a fixed depth of analyst history.
Workflows
Company or earnings briefing. Resolve the security, then use finnhub_get_quote and finnhub_get_company for price and business context. For a company's next release, use its symbol with finnhub_get_earnings calendar mode; use history separately for reported EPS and surprises. Add finnhub_get_news company news for the relevant event window and finnhub_get_recommendations when analyst context is needed. Keep quote timestamps, fiscal periods, expected release dates, article publication times, and recommendation periods attached to their respective claims.
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.
- 8d ago First seen · 32 lines · 52 tokens per session scan A 9937f26f15b7
finnhub-guide is a skill published in the GitHub repository cyanheads/finnhub-mcp-server (1 stars, last pushed 9d ago), licensed Apache-2.0. It adds 52 tokens to every session and 634 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-31.
finnhub-guide compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| finnhub-guidecyanheads/finnhub-mcp-server | Skill | 1 | 9d ago | Apache-2.0 | A | 52 | Claude Code |
| polymarketNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 18 | Claude Code, Codex |
| fred-economic-datasynthetic-sciences/openscience | Skill | 4.4k | yesterday | Apache-2.0 | A | 75 | Claude Code, Codex |
| tinker-training-costsynthetic-sciences/openscience | Skill | 4.4k | yesterday | Apache-2.0 | A | 55 | Claude Code, Codex |
| tickdb-market-dataTickDB/tickdb-unified-realtime-marketdata-api | Skill | 917 | 2d ago | MIT | A | 165 | Claude Code, Codex |
| defeatbeta-earnings-analysisdefeat-beta/defeatbeta-api | Skill | 795 | 9d ago | Apache-2.0 | A | 112 | Claude Code |
| defeatbeta-earnings-previewdefeat-beta/defeatbeta-api | Skill | 795 | 9d ago | Apache-2.0 | A | 60 | Claude Code, Codex |