Aigroup Fmp Mcp

Use `aigroup-fmp-mcp` for listed-equity data from Financial Modeling Prep, including quotes, company profiles, statements, ratios, sector context, and calend...

Security Scan

The skill's declared purpose (Financial Modeling Prep market data via an MCP tool) matches its instructions and manifest; it is an instruction-only skill with no surprising env vars, installs, or file reads.

Purpose & Capability

Name/description map to the listed tool calls (quotes, profiles, statements, ratios, market snapshots). The agent dependency (mcp value: "aigroup-fmp-mcp") is consistent with a proxied Financial Modeling Prep integration.

Instruction Scope

SKILL.md only instructs the agent to confirm tickers and call specific FMP-related tool operations (get_quote, get_company_profile, etc.). It does not ask the agent to read local files, environment variables, or transmit unrelated data.

Install Mechanism

No install spec and no included code files — this is instruction-only, so nothing is written to disk or downloaded during install.

Credentials

No environment variables or credentials are requested, which is coherent if the MCP server handles FMP API credentials. As a result, you should confirm you trust the MCP server (aigroup-fmp-mcp) since credentials and network calls may be managed there rather than in the skill.

Persistence & Privilege

always is false and the skill does not request elevated or persistent privileges. The agents/openai.yaml sets allow_implicit_invocation: false, which limits implicit autonomous invocation for this interface.

Assessment

This skill appears to be a thin instruction wrapper for an MCP-backed Financial Modeling Prep integration and is internally consistent. Before installing, verify you trust the MCP server named "aigroup-fmp-mcp" (check the GitHub homepage and the server implementation) because API keys and network requests may be handled by that server rather than the skill. Also confirm your platform enforces the declared allow_implicit_invocation: false and that no secret (FMP API key) needs to be provided to the agent in your environment. If you cannot audit the MCP service, treat it like an external data provider and limit its access to only non-sensitive queries.

FMP MCP

Use aigroup-fmp-mcp for listed-equity quote, company profile, statement, ratio, and market snapshot requests.

Route

1. Confirm the company or ticker first. If the ticker is unknown or ambiguous, resolve it with search_symbol.
2. Pull only the fields needed for the request:
   • get_quote for price context
   • get_company_profile for issuer overview
   • get_income_statement, get_balance_sheet, get_cash_flow for financials
   • get_key_metrics and get_financial_ratios for benchmarking
3. Add market context only when it improves the answer:
   • get_market_gainers, get_market_losers, get_most_active
   • get_sector_performance
   • get_sp500_constituents
4. Add estimate or technical context only when asked:
   • get_analyst_estimates, get_price_target, get_analyst_ratings
   • get_technical_indicator_rsi, get_technical_indicator_sma, get_technical_indicator_ema
5. State dates clearly for quotes, charts, and calendars.

Requests

• Research a public company with current quote, profile, and recent financial statements.
• Compare a small peer set on margins, valuation, or balance-sheet strength.
• Summarize market breadth using gainers, losers, most active names, or sector performance.
• Pull earnings or economic calendar context for a near-term event.
• Add a quick technical read to a fundamentals-led answer.

References

• Read capabilities.md for the exposed tool groups and recommended task mapping.