Skip to main content
Glama
gmoneyn

FinAgent

by gmoneyn
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

FinAgent

Free financial analysis MCP server for any MCP-compatible AI app (Claude, ChatGPT, Cursor, Copilot, and more).

Get live stock data and market news — all from your AI assistant.

Tools

Tool

Description

financial_data

Stock quotes, income statements, balance sheets, cash flow, analyst estimates, insider trades, key ratios

market_news

Financial news, analyst reactions, market sentiment

Related MCP server: Modal MCP Stock Analysis Server

Quick Start

Install

pip install finagent-mcp

Add to your MCP config

{
  "mcpServers": {
    "finagent": {
      "command": "finagent"
    }
  }
}

Run as HTTP server

finagent --http --port 8080

Examples

Ask your AI assistant:

  • "What's NVIDIA's current stock price and P/E ratio?"

  • "Show me Apple's last 4 quarters of revenue"

  • "Who's been buying or selling TSLA stock lately?"

  • "What are analysts saying about AMZN?"

Want More?

FinAgent Pro adds SEC filing analysis and stock screening. Get it at mcp-marketplace.io/server/finagent-pro.

Data Sources

  • Market data: Yahoo Finance (free, real-time)

  • News: Yahoo Finance news feed (free)

Available Tools

2 tools
financial_dataA

Retrieve financial data for a stock ticker.

Args: ticker: Stock ticker symbol (e.g. "AAPL", "MSFT"). data_type: One of: quote, income_statement, balance_sheet, cash_flow, analyst_estimates, insider_trades, key_ratios. period: Reporting period — "annual" or "quarterly" (default "annual"). limit: Maximum number of periods to return (default 4).

Returns: JSON string with the requested data or an error object.

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNo
periodNoannual
tickerYes
data_typeYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden. It provides defaults, valid data_type values, and the return format (JSON string or error), but does not disclose side effects, authentication requirements, or error conditions beyond returning an error object.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a compact, well-organized docstring with a clear title, Args, and Returns sections. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The combination of parameter documentation, return type, and defaults fully describes the tool for an agent. The output schema handles detailed return structure, and the description covers the rest.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage, the description fully explains each parameter: ticker with examples, data_type with allowed values, period with options, and limit with default. This adds substantial meaning beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description explicitly states 'Retrieve financial data for a stock ticker' with a specific verb and resource, and the data_type options further clarify scope. This distinguishes it from the sibling market_news tool, which is for news.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly indicates this tool is for financial data retrieval, which differentiates it from market_news. However, it does not explicitly state when to use it versus alternatives or provide exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

market_newsA

Fetch recent market news articles filtered by keyword.

Args: query: Keyword to search for in article titles (e.g. "earnings", "Federal Reserve", "AI"). ticker: Optional stock ticker to narrow results to a specific company (e.g. "AAPL", "TSLA"). When omitted the search scans broad-market index ETFs (SPY, QQQ, DIA). days_back: Number of days of history to consider (default 7).

Returns: JSON string containing a list of article objects with keys: title, source, link, published, type, related_tickers.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes
tickerNo
days_backNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states the return format as a JSON string with specific keys, and explains the default behavior for ticker. It does not mention any side effects or rate limits, but for a read-only news fetch, this is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear 'Args' and 'Returns' sections, and is concise without redundant information. Every sentence adds value, and the main purpose is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema and three params, the description is complete: it explains all parameters, return format, and default behaviors. It provides enough context for an agent to correctly invoke the tool without needing additional information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds significant meaning beyond the schema: it specifies that 'query' searches article titles, explains the optional 'ticker' behavior and its effect on index ETFs, and clarifies the default for 'days_back'. This greatly enhances understanding beyond the raw schema properties.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with 'Fetch recent market news articles filtered by keyword,' which clearly states the tool's verb (fetch), resource (market news articles), and primary behavior (filtering by keyword). However, it does not explicitly distinguish itself from the sibling tool 'financial_data' beyond the obvious domain difference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on how to use the tool, including parameter explanations and the default behavior of 'ticker' when omitted ('scans broad-market index ETFs'). It does not mention alternative tools or when not to use this tool, but the usage context is sufficiently clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv0.1.0
    • First observedfinancial_data
    • First observedmarket_news
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.3/5.0

Scored across 2 tools

Disambiguation5/5

market_news and financial_data have clearly distinct purposes: one retrieves news articles, the other retrieves structured financial data. There is no ambiguity about which tool to use for a given request.

Naming Consistency5/5

Both tool names follow the same pattern of two lowercase words joined by an underscore, describing a noun (market_news, financial_data). The naming convention is fully consistent.

Tool Count3/5

With only 2 tools, the server feels minimal for a financial domain. While the two tools cover distinct functions, the count is on the thin side and may not justify a dedicated server without additional capabilities.

Completeness3/5

The tools cover market news and several types of financial data (quotes, statements, estimates), but lack obvious features like historical price data, ticker search or screening, and portfolio tracking. Core reading operations are present, but the surface is not fully complete for broader financial workflows.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Financial Datasets MCP Server by financial-datasets

    Financial Datasets MCP Serverofficial

    financial-datasets
    A
    license
    B
    quality
    C
    maintenance
    MCP server that provides AI assistants access to stock market data including financial statements, stock prices, and market news through a Model Context Protocol interface.
    11
    2,290
    MIT

  • Modal MCP Stock Analysis

    koyeliaghosh
    F
    license
    Not graded
    quality
    D
    maintenance
    Provides real-time stock analysis tools including price lookup, comprehensive investment scoring, and company-to-ticker conversion through a MCP interface.
    1
    -

  • FinImpulse MCP Server

    finimpulse
    A
    license
    A
    quality
    C
    maintenance
    Provides structured financial market data (stocks, ETFs, mutual funds, fundamentals, market indicators) to AI systems via MCP, enabling natural language access to financial datasets with both hosted and local deployment options.
    31
    19 npm
    ISC

  • Yahoo Finance MCP Server

    danishashko
    A
    license
    Not graded
    quality
    A
    maintenance
    Provides real-time stock market data for Claude Desktop and MCP-compatible clients, enabling natural language queries for quotes, historical prices, company profiles, financial statements, analyst ratings, comparisons, news, options, holdings, dividends, estimates, symbol search, and market status.
    447 npm
    19
    MIT