MCP server "agentii" as configured in agentii-ai/agentii-investment-intelligence. Runs locally from the @agentii/investment-intelligence npm package. Needs 1 environment variable to run.
★not rated 207▲
+1 17d agoA
tokens not measured
originalApache-2.0
Orchestrating equity-research agent that bundles all 24 skills from the 4 vertical plugins (equity-research-core, business-intelligence, industry-analysis, models-and-pitches) with a long-range analytical system prompt ported from references/prompts/systemv27.py. Invokes the agentii.ai data plane for SEC filings, XBR.
Institutional-grade equity research skills for AI agents. 80 skills across 14 verticals, exposed under a single /agentii:skill-name namespace and powered by agentii.ai's agent-use-ready SEC filing data plane.
5 business-intelligence skills for deep analysis of revenue models, unit economics, and operational KPIs: business-model analysis, revenue decomposition, unit economics, what-if scenarios, and operational KPI tracking. Backed by agentii.ai's data API.
7 financial-modeling and presentation skills: DCF, comps analysis, 3-statement model, LBO, audit-xls, xlsx-author, and pitch-deck. 6 skills ported from anthropics/financial-services (Apache 2.0) with data-source blocks rewritten to agentii.ai's data API; pitch-deck is net-new composite authoring. All Excel-producing…
Options and derivatives skills: foundations, income strategies, volatility trading, technical execution. Powered by spec 037 knowledge base (L3, L4, K7).
★not rated 207▲
+1 17d agoA
tokens not measured
originalApache-2.0
Quantitative financial analysis skills — ratio analysis, PEG valuation, reverse DCF, DDM, residual income. Uses XBRL financial data and real-time price data for US equity analysis.
The Auto 档 scenario — a soft-plan orchestrator for a complete fundamental equity research thesis: understand → financials → valuation → synthesize. The body is a soft plan (stages), not a rigid DAG; correctness is enforced by each referenced skill's own requires: preconditions, never by this plan's rigidity (Q2).
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
Create or update the feature specification from a natural language feature description.
★not rated 102 1mo agoA13 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: