Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@fmp-mcp-research Build earnings evidence pack for AAPL"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Read-only MCP server for FMP and SEC research context. The server behaves as an information and suggestion layer: it returns source context, selected periods, tables, filings where requested, and recommended_next_actions without enforcing gates, restrictions, or blocking logic.
Tool | Purpose |
| Return company profile and metadata. |
| Discover available earnings-call periods and suggested transcript fetch actions. |
| Return prepared remarks / call-start text for a selected period. |
| Return Q&A text for a selected period. |
| Return income statement, balance sheet, cash flow, metrics, ratios and growth tables. |
| Return SEC filing candidates from FMP. |
| Fetch an earnings release from public PR sources via FMP and convert it to LLM-friendly Markdown. |
| Build selected periods, evidence manifest, context notes and recommended next actions. |
| Compatibility alias for the evidence-pack tool. |
| Return informational notes and recommended next actions from a payload. |
| Return suggested report structure and sector lenses. |
Related MCP server: Financial Modeling Prep (FMP) MCP Server
get_earnings_release inputsThe FMP earnings release tool intentionally exposes only three model-facing parameters:
{
"symbol": "SPT",
"fiscalYear": 2026,
"fiscalQuarter": 1
}The tool infers the SEC filing internally by ranking public SEC filings and candidate exhibits using filing metadata, exhibit metadata, earnings-release language, requested fiscal period signals, and table density. Do not pass filingDate in recommended_next_actions.
fmp_build_research_evidence_pack returns:
evidence_pack_version
symbol
selected_periods
latest_completed_fiscal_year
evidence_manifest
context_notes
recommended_next_actions
The evidence-pack output omits strict templates, policies, source flags, gates and embedded SEC filing prioritization. Use fmp_search_sec_filings separately when filing discovery is needed.
The MCP provides information and suggestions only. It does not tell the LLM what it is allowed to conclude, does not block downstream work, and does not enforce downstream decision rules.
This server cannot be deployed
MCP server giving AI agents one-connection access to China A-share market intelligence: financials,
Your agent needs company financials it can compute on — statements, ratios, earnings, estimates, filings and insider activity as structured data, not a PDF. **What you can ask for** • "Give me 8 quarters of income statement, balance sheet and cash flow for this ticker." • "What do analysts estimate for next quarter, and how did the last four surprise?" • "Find this exact line item across every filing." • "Who bought or sold as an insider in the last 90 days?" • "Screen for profitable companies under this valuation with growing revenue." **How to use it** Point any MCP client at https://mcp.aisa.one/marketpulse/mcp and sign in with OAuth — there is no key to create or paste. 21 tools: prices and snapshots, income statements, balance sheets, cash-flow statements, financial metrics and snapshots, earnings, analyst estimates, company facts, filings and filing items, line-item search, a screener, insider trades, macro interest rates, news, plus EDINET documents and filing digests for Japanese issuers. **Why this rather than the source** Statements as fields you can compute on, and a screener in the same place. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Read the fundamentals here, then ask the same agent what social is saying about the ticker — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/finance/mcp for equities, crypto and prediction markets in one place.
MCP server exposing the Backtest360 engine API as tools for AI agents.
Research-only MCP server: your AI as a quant research desk. 90 tools, no trades, no brokers.
