What can you do with this server?

The Toolstem MCP Server provides curated, agent-ready financial data tools that combine multiple data sources, pre-compute derived signals, and return flat JSON — enabling AI agents to perform equity research in a single call. * get_stock_snapshot: Comprehensive stock overview including real-time price, 52-week range distances, valuation (P/E, DCF value/upside, dcf_signal: UNDERVALUED/FAIRLY VALUED/OVERVALUED), analyst ratings/recommendations, and company fundamentals. * get_company_metrics: Deep fundamental analysis covering: * Profitability: revenue, margins, ROE, ROA, ROIC, YoY growth → derived margin_trend (EXPANDING/STABLE/CONTRACTING) * Financial health: debt, cash, D/E, current ratio, interest coverage → derived health_signal (STRONG/ADEQUATE/WEAK) * Cash flow: operating CF, FCF, FCF margin/yield, capex, buybacks * 3-year CAGRs (revenue, net income, FCF) → derived growth_signal (ACCELERATING/STEADY/DECELERATING) * Per-share metrics: EPS, book value, FCF/share, dividends, payout ratio * compare_companies: Side-by-side comparison of 2–5 stocks across valuation, profitability, financial health, growth, dividends, and analyst ratings — with auto-computed rankings: lowest_pe, highest_margin, strongest_balance_sheet, best_growth, most_undervalued, highest_rated. All tools pre-compute financial math and derive signals, eliminating complex parsing. Available via hosted pay-per-call endpoint (USDC on Base via x402, no API key needed) or self-hosted with a Financial Modeling Prep (FMP) API key.

Which integrations are available for this server?

Supports deployment as a self-hosted MCP server on Cloudflare Workers runtime, enabling financial data tools to run on edge infrastructure.

de en es ja ko ru zh

Toolstem MCP Server

by toolstem

Overview Schema Related Servers Score Discussions

TypeScript

Remote

📊 Toolstem — Financial Data MCP for AI Agents | Stock Analysis & DCF

npm version npm downloads MCP Registry License: MIT

Curated financial data MCP for AI agents — equity research in one call.

Toolstem is the financial data MCP built for AI stock analysis, equity research, and agent-driven investment workflows. Real-time stock data, company fundamentals, DCF valuations, financial metrics, and the ability to compare companies side-by-side — all returned as flat, agent-friendly JSON with derived signals already computed.

Works natively with Claude, OpenAI Agents SDK, and LangChain. Pay-per-call pricing, no subscription. More finance MCP servers (SEC filings, insider transactions, institutional holdings) are on the way.

Unlike passthrough wrappers that just expose a vendor's REST API, every Toolstem tool combines multiple data sources, derives signals, and pre-computes the math an agent would otherwise have to do itself.

One call. One agent-friendly JSON response. No nested arrays to parse, no cross-endpoint stitching, no null-checking boilerplate.

Quickstart — hosted endpoint (recommended)

Point your MCP client or agent at the hosted endpoint. No API key, no infra, no setup. Billing is per-call via x402 — the agent's wallet pays directly in USDC on Base mainnet.

https://mcp.toolstem.com/mcp/finance

No FMP API key required — you do not bring or manage any upstream data key.
No infrastructure — nothing to install, host, or keep running.
No setup — connect an MCP client and call a tool.
initialize and tools/list are free (discovery and schema introspection).
Each tools/call costs $0.01 USDC on Base mainnet, settled via x402.

Claude Desktop

Drop this into your claude_desktop_config.json:

{
  "mcpServers": {
    "toolstem-finance": {
      "url": "https://mcp.toolstem.com/mcp/finance"
    }
  }
}

Restart Claude Desktop, then ask: "Use Toolstem to get a snapshot of NVDA."

Any MCP client (LangChain.js)

The official @langchain/mcp-adapters library connects directly to the hosted URL:

import { MultiServerMCPClient } from "@langchain/mcp-adapters";
import { ChatOpenAI } from "@langchain/openai";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const client = new MultiServerMCPClient({
  toolstem_finance: {
    transport: "http",
    url: "https://mcp.toolstem.com/mcp/finance",
    // Add your x402-signing middleware via headers, OR run an x402
    // proxy locally and point url at it. See https://www.x402.org/clients.
  },
});

const tools = await client.getTools();
const agent = createReactAgent({ llm: new ChatOpenAI({ model: "gpt-4o-mini" }), tools });
await agent.invoke({ messages: "Compare AAPL, MSFT, and GOOGL on valuation and growth." });

LangChain quick-start (`langchain-toolstem`)

The langchain-toolstem wrapper handles x402 payment for you — pass a funded wallet key and the tools auto-pay per call:

import { createToolstemTools } from 'langchain-toolstem';
const tools = await createToolstemTools({ walletPrivateKey: process.env.WALLET_KEY });
// Tools auto-pay $0.01 USDC per call via x402

Prefer to run the server yourself with your own FMP key? See Advanced: self-host at the bottom.

Try the tools live in the Toolstem playground.

Product page: https://toolstem.com/finance/.

Related MCP server: TickerAPI

Pricing

MCP initialize and tools/list are free — discovery, schema introspection, and health checks never cost anything.
tools/call costs $0.01 USDC on Base mainnet per invocation, paid via x402. No API key, no signup, no marketplace account required — the agent's wallet pays directly.

Tool	Per call
`get_stock_snapshot`	$0.01 USDC
`get_company_metrics`	$0.01 USDC
`compare_companies`	$0.01 USDC

How billing works

Toolstem uses the x402 payment protocol. Agents pay per call in USDC on Base — no API keys, no subscriptions, no invoices. The agent's wallet settles each call automatically via EIP-3009.

How it works

Toolstem ships as a Node MCP server (this repo) and as a hosted, x402-gated proxy.

Agent ──MCP──▶ Cloudflare Worker (x402 paywall) ──MCP──▶ Toolstem MCP server ──REST──▶ Financial Modeling Prep
                  │                                          │
                  └─ free: initialize, tools/list            └─ composite tool: fans out to 3–5 FMP endpoints
                  └─ paid: tools/call → 0.01 USDC on Base       in parallel, derives signals, returns flat JSON

Cloudflare Worker terminates the public MCP connection at mcp.toolstem.com and enforces the x402 payment for tools/call.
MCP server (this package) implements the 3 composite tools and talks to Financial Modeling Prep.
x402 on Base mainnet handles the micropayment — settlement is sub-second, no off-chain accounts.

Tools

Three composite tools, each one synthesizing multiple FMP endpoints with derived signals and pre-computed math.

Tool	Title	Required input	Optional input
`get_stock_snapshot`	Stock Snapshot	`symbol` (string)	—
`get_company_metrics`	Company Metrics	`symbol` (string)	`period` (`annual` \| `quarter`, default `annual`)
`compare_companies`	Company Comparison	`symbols` (string[2..5])	—

All three are read-only, idempotent, and safe for agent retry.

`get_stock_snapshot`

Comprehensive stock overview combining quote, profile, DCF valuation, and rating into a single response.

Input:

{
  "symbol": "AAPL"
}

Example output (truncated):

{
  "symbol": "AAPL",
  "company_name": "Apple Inc.",
  "sector": "Technology",
  "industry": "Consumer Electronics",
  "exchange": "NASDAQ",
  "price": {
    "current": 178.52,
    "change": 2.34,
    "change_percent": 1.33,
    "day_high": 179.80,
    "day_low": 175.10,
    "year_high": 199.62,
    "year_low": 130.20,
    "distance_from_52w_high_percent": -10.57,
    "distance_from_52w_low_percent": 37.11
  },
  "valuation": {
    "market_cap": 2780000000000,
    "market_cap_readable": "$2.78T",
    "pe_ratio": 29.5,
    "dcf_value": 195.20,
    "dcf_upside_percent": 9.35,
    "dcf_signal": "FAIRLY VALUED"
  },
  "rating": {
    "score": 4,
    "recommendation": "Buy",
    "dcf_score": 5,
    "roe_score": 4,
    "roa_score": 4,
    "de_score": 5,
    "pe_score": 3
  },
  "fundamentals_summary": {
    "beta": 1.28,
    "avg_volume": 55000000,
    "employees": 164000,
    "ipo_date": "1980-12-12",
    "description": "Apple Inc. designs, manufactures..."
  },
  "meta": {
    "source": "Toolstem via Financial Modeling Prep",
    "timestamp": "2026-04-17T18:30:00Z",
    "data_delay": "End of day"
  }
}

Derived fields (not in raw APIs):

dcf_signal — UNDERVALUED if DCF upside > 10%, OVERVALUED if < -10%, else FAIRLY VALUED.
market_cap_readable — human-friendly $2.78T, $450.2B, $12.5M format.
distance_from_52w_high_percent / distance_from_52w_low_percent — pre-computed range position.

`get_company_metrics`

Deep fundamentals analysis — profitability, financial health, cash flow, growth, and per-share metrics — synthesized from 5 financial statements endpoints.

Input:

{
  "symbol": "AAPL",
  "period": "annual"
}

period accepts annual (default) or quarter.

Example output (truncated):

{
  "symbol": "AAPL",
  "period": "annual",
  "latest_period_date": "2025-09-30",
  "profitability": {
    "revenue": 394328000000,
    "revenue_readable": "$394.3B",
    "revenue_growth_yoy": 7.8,
    "net_income": 96995000000,
    "net_income_readable": "$97.0B",
    "gross_margin": 46.2,
    "operating_margin": 31.5,
    "net_margin": 24.6,
    "roe": 160.5,
    "roa": 28.3,
    "roic": 56.2,
    "margin_trend": "EXPANDING"
  },
  "financial_health": {
    "total_debt": 111000000000,
    "total_cash": 65000000000,
    "net_debt": 46000000000,
    "debt_to_equity": 1.87,
    "current_ratio": 1.07,
    "interest_coverage": 41.2,
    "health_signal": "STRONG"
  },
  "cash_flow": {
    "operating_cash_flow": 118000000000,
    "free_cash_flow": 104000000000,
    "free_cash_flow_readable": "$104.0B",
    "fcf_margin": 26.4,
    "capex": 14000000000,
    "dividends_paid": 15000000000,
    "buybacks": 89000000000,
    "fcf_yield": 3.7
  },
  "growth_3yr": {
    "revenue_cagr": 8.2,
    "net_income_cagr": 10.1,
    "fcf_cagr": 9.5,
    "growth_signal": "ACCELERATING"
  },
  "per_share": {
    "eps": 6.42,
    "book_value_per_share": 3.99,
    "fcf_per_share": 6.89,
    "dividend_per_share": 0.96,
    "payout_ratio": 14.9
  },
  "meta": {
    "source": "Toolstem via Financial Modeling Prep",
    "timestamp": "2026-04-17T18:30:00Z",
    "periods_analyzed": 3,
    "data_delay": "End of day"
  }
}

Derived fields:

margin_trend — EXPANDING, STABLE, or CONTRACTING based on net margin series direction.
health_signal — STRONG, ADEQUATE, or WEAK from debt-to-equity, current ratio, and interest coverage.
growth_signal — ACCELERATING, STEADY, or DECELERATING based on YoY growth trajectory.
revenue_cagr, net_income_cagr, fcf_cagr — compound annual growth rates over the analyzed window.
fcf_margin, fcf_yield — pre-computed from cash flow + revenue + market cap.

`compare_companies`

Side-by-side comparison of 2–5 companies across price, valuation, profitability, financial health, growth, dividends, and analyst ratings.

Input:

{
  "symbols": ["AAPL", "MSFT", "GOOGL"]
}

symbols must be an array of 2 to 5 ticker strings.

Example output (truncated):

{
  "symbols_compared": ["AAPL", "MSFT", "GOOGL"],
  "comparison_date": "2026-04-20T18:30:00Z",
  "companies": [
    {
      "symbol": "AAPL",
      "company_name": "Apple Inc.",
      "sector": "Technology",
      "price": { "current": 178.52, "change_percent": 1.33 },
      "valuation": { "pe_ratio": 29.5, "dcf_upside_percent": 9.35 },
      "profitability": { "net_margin": 24.6, "roe": 160.5, "roic": 56.2 },
      "financial_health": { "debt_to_equity": 1.87, "current_ratio": 1.07 },
      "growth": { "revenue_growth_yoy": 7.8, "earnings_growth_yoy": 10.1 },
      "dividend": { "dividend_yield": 0.5, "payout_ratio": 14.9 },
      "rating": { "score": 4, "recommendation": "Buy" }
    }
  ],
  "rankings": {
    "lowest_pe": "GOOGL",
    "highest_margin": "AAPL",
    "strongest_balance_sheet": "GOOGL",
    "best_growth": "MSFT",
    "most_undervalued": "GOOGL",
    "highest_rated": "MSFT"
  },
  "meta": {
    "source": "Toolstem via Financial Modeling Prep",
    "timestamp": "2026-04-20T18:30:00Z",
    "data_delay": "Real-time during market hours",
    "api_calls_made": 19
  }
}

Derived fields:

rankings — automatically computed: lowest_pe, highest_margin, strongest_balance_sheet, best_growth, most_undervalued, highest_rated.
All valuation, profitability, health, and growth metrics pre-computed per company.
Uses batch quote for efficient multi-symbol price retrieval.

Why Toolstem?

Most financial MCP servers expose one tool per API endpoint — forcing your agent to make 4–5 sequential calls, write glue code, and reason about raw data shapes. Toolstem is built differently:

Parallel data fetching — every tool fans out to multiple sources concurrently.
Derived signals — human-readable recommendations like UNDERVALUED, STRONG, ACCELERATING computed from raw numbers.
Pre-computed math — CAGRs, YoY growth, margin trends, distance from 52-week high/low, FCF yield, and more are already in the response.
Flat, predictable schema — no deeply nested vendor quirks leaking into agent prompts.
Graceful degradation — if one upstream endpoint fails, the rest of the response still comes through with nulls in place.

Advanced: self-host

Most users should use the hosted endpoint above — it needs no API key, no infrastructure, and no setup. This section is for users who specifically want to run the server themselves.

Run the Node MCP server locally with your own FMP key — no x402, no per-call charge beyond your FMP quota. You are responsible for obtaining and managing your own FMP_API_KEY and for any infrastructure you run.

npm

npm install -g toolstem-mcp-server

stdio (default — for Claude Desktop, Cursor, etc.):

FMP_API_KEY=your_key_here toolstem-mcp-server

HTTP — local only (default, binds 127.0.0.1):

FMP_API_KEY=your_key_here toolstem-mcp-server --http

HTTP — remote + auth (binds 0.0.0.0, requires bearer token):

FMP_API_KEY=your_key ALLOW_REMOTE=1 MCP_AUTH_TOKEN=my-secret toolstem-mcp-server --http

Clients must send Authorization: Bearer my-secret on every /mcp request.

HTTP — auth disabled (local only):

FMP_API_KEY=your_key MCP_AUTH_DISABLED=1 toolstem-mcp-server --http

MCP_AUTH_DISABLED=1 forces the server to bind 127.0.0.1 regardless of ALLOW_REMOTE. This is a safe "skip auth, local only" mode for development.

HTTP — remote without auth (dangerous):

FMP_API_KEY=your_key ALLOW_REMOTE=1 MCP_AUTH_DISABLED=1 I_KNOW_THIS_IS_DANGEROUS=1 toolstem-mcp-server --http

Warning: This exposes your FMP API key to anyone who can reach the port. Requires all three env vars. A [SECURITY WARNING] banner prints at startup and repeats every 60 seconds. Only use for trusted networks or development.

Claude Desktop (self-hosted)

{
  "mcpServers": {
    "toolstem": {
      "command": "npx",
      "args": ["-y", "toolstem-mcp-server"],
      "env": {
        "FMP_API_KEY": "your_fmp_api_key"
      }
    }
  }
}

From source

npm install
npm run build
FMP_API_KEY=your_key npm run start:http

Environment Variables

Variable	Required	Description
`FMP_API_KEY`	Yes (self-hosted)	Financial Modeling Prep API key. Get one at financialmodelingprep.com. Not needed when calling the hosted endpoint.
`PORT`	No	Port for HTTP transport. Defaults to `3000`.
`ALLOW_REMOTE`	No	Set to `1` to bind HTTP on `0.0.0.0` instead of `127.0.0.1`.
`MCP_AUTH_TOKEN`	When `ALLOW_REMOTE=1`	Bearer token for authenticating `/mcp` requests.
`MCP_AUTH_DISABLED`	No	Set to `1` to skip auth. Forces `127.0.0.1` bind unless `I_KNOW_THIS_IS_DANGEROUS=1` is also set.
`I_KNOW_THIS_IS_DANGEROUS`	No	Set to `1` alongside `ALLOW_REMOTE=1` and `MCP_AUTH_DISABLED=1` to allow remote access without auth. Triggers a periodic warning banner.

Development

npm install
npm run dev           # stdio, hot reload via tsx
npm run build         # TypeScript -> dist/
npm start             # run built stdio server
npm run start:http    # run built HTTP server

Architecture

src/
├── index.ts          # MCP server entry (stdio + Streamable HTTP)
├── actor.ts          # Apify Actor entry (legacy)
├── services/
│   └── fmp.ts        # Financial Modeling Prep API client
├── tools/
│   ├── get-stock-snapshot.ts
│   ├── get-company-metrics.ts
│   └── compare-companies.ts
└── utils/
    └── formatting.ts # Market cap formatting, CAGR, trend signals

All FMP endpoints are wrapped in a single FmpClient class. Tool implementations fan out to multiple client methods in parallel via Promise.all, then synthesize the merged result.

License

MIT — see LICENSE.

Toolstem — curated financial intelligence for the agent-native economy. https://toolstem.com/finance/

Available Tools

3 tools

compare_companiesCompany ComparisonA

Read-onlyIdempotent

Side-by-side comparison of 2-5 companies across price, valuation (P/E, P/B, P/S, EV/EBITDA, DCF), profitability (margins, ROE, ROA, ROIC), financial health (D/E, current ratio, interest coverage), growth (revenue and earnings YoY), dividends, and analyst ratings. Returns derived rankings showing which company leads each dimension — lowest_pe, highest_margin, strongest_balance_sheet, best_growth, most_undervalued, highest_rated. Use this for investment comparisons, competitive analysis, or evaluating alternatives in the same sector.

ParametersJSON Schema

Name	Required	Description	Default
`symbols`	Yes	2-5 stock ticker symbols to compare (e.g., ["AAPL", "MSFT", "GOOGL"])

Output Schema

ParametersJSON Schema

Name	Required	Description
`symbols_compared`	Yes
`comparison_date`	Yes
`companies`	Yes
`rankings`	Yes
`meta`	Yes

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. The description aligns fully, detailing the read-only operation and output format (derived rankings). No contradictions, and the description adds significant behavioral context (categories of metrics, derived rankings) beyond annotations.

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?

Three sentences: first states core purpose, second lists all metric categories, third gives use cases. Front-loaded, no filler, every sentence adds value.

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 tool's complexity (many metrics and derived rankings) and the presence of an output schema, the description is complete. It covers input constraints (2-5 symbols), output nature (derived rankings), and typical use cases. No gaps for an agent to misuse.

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

Parameters3/5

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

Schema description coverage is 100% (the symbols parameter has a detailed description including example). The tool description restates '2-5 companies' but adds no new semantics beyond the schema. Baseline 3 applies.

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?

The description explicitly states the tool performs side-by-side comparison of 2-5 companies across price, valuation, profitability, financial health, growth, dividends, and analyst ratings. It also lists derived rankings (lowest_pe, etc.). This clearly distinguishes from siblings get_company_metrics (likely single company) and get_stock_snapshot (likely a quick overview).

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 explicit use cases: 'Use this for investment comparisons, competitive analysis, or evaluating alternatives in the same sector.' It does not explicitly state when not to use or name alternatives, but the context is clear and actionable.

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

get_company_metricsCompany MetricsA

Read-onlyIdempotent

Deep financial analysis including profitability, financial health, cash flow, growth (3-year CAGR), and per-share metrics. Synthesizes key metrics, financial ratios, income statement, balance sheet, and cash flow statement into one agent-ready response with derived signals: margin_trend (EXPANDING/STABLE/CONTRACTING), health_signal (STRONG/ADEQUATE/WEAK), and growth_signal (ACCELERATING/STEADY/DECELERATING). Use this for fundamental analysis, financial health checks, or when you need to understand a company's trajectory.

ParametersJSON Schema

Name	Required	Description	Default
`symbol`	Yes	Stock ticker symbol (e.g., AAPL, MSFT, TSLA)
`period`	No	Reporting period. Defaults to annual.	annual

Output Schema

ParametersJSON Schema

Name	Required	Description
`symbol`	Yes
`period`	Yes
`latest_period_date`	Yes
`profitability`	Yes
`financial_health`	Yes
`cash_flow`	Yes
`growth_3yr`	Yes
`per_share`	Yes
`meta`	Yes

TDQS

A4.1/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, covering safety. The description adds value by explaining derived signals and output structure, but doesn't disclose additional behavioral traits beyond what annotations provide.

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?

Two sentences, front-loaded with key content. Each sentence contributes: first lists included metrics, second explains output and use cases. No unnecessary words.

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 (handling return values), complete schema coverage, and annotations covering safety, the description provides sufficient context about purpose, usage, and derived signals. It is thorough for a tool of this complexity.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents both parameters adequately. The description does not add extra parameter detail beyond what is in the schema, aligning with the baseline of 3.

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?

The description clearly states it provides deep financial analysis and synthesizes key metrics, ratios, and statements into an agent-ready response. It distinguishes from siblings (compare_companies and get_stock_snapshot) by emphasizing depth and derived signals.

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?

Explicitly recommends use for fundamental analysis, financial health checks, or understanding a company's trajectory. While it doesn't directly mention alternatives, sibling tool names and the focus on depth imply when not to use.

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

get_stock_snapshotStock SnapshotA

Read-onlyIdempotent

Get a comprehensive stock snapshot including real-time price, valuation metrics, DCF analysis, and analyst ratings for any publicly traded company. Returns curated, agent-ready data synthesized from multiple sources in a single call — includes derived signals like dcf_signal (UNDERVALUED/FAIRLY VALUED/OVERVALUED), human-readable market cap, and 52-week range distance. Use this when you need a quick overview of a stock before digging into financials.

ParametersJSON Schema

Name	Required	Description	Default
`symbol`	Yes	Stock ticker symbol (e.g., AAPL, MSFT, TSLA)

Output Schema

ParametersJSON Schema

Name	Required	Description
`symbol`	Yes
`company_name`	Yes
`sector`	Yes
`industry`	Yes
`exchange`	Yes
`price`	Yes
`valuation`	Yes
`rating`	Yes
`fundamentals_summary`	Yes
`meta`	Yes

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already indicate readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds behavioral context by explaining the tool synthesizes data from multiple sources, returns derived signals (dcf_signal), and provides curated agent-ready data. This adds value beyond the annotations.

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 concise, consisting of three focused sentences. The first sentence states the main purpose, the second lists key output components, and the third provides usage guidance. No redundant or irrelevant information.

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 tool's simplicity (one parameter), presence of output schema, and rich annotations, the description sufficiently covers the tool's functionality, output highlights, and usage context. It explains derived signals and the nature of the data, making it complete for an agent to understand and invoke correctly.

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

Parameters3/5

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

The input schema has 100% description coverage for the single required parameter 'symbol' (ticker). The description does not add additional semantic information about the parameter beyond what the schema already provides. With full schema coverage, a baseline score of 3 is appropriate.

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?

The description clearly states the tool provides a comprehensive stock snapshot including real-time price, valuation metrics, DCF analysis, and analyst ratings. It distinguishes from siblings by noting it is a quick overview before diving into financials, differentiating from get_company_metrics and compare_companies.

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 explicitly says 'Use this when you need a quick overview of a stock before digging into financials,' providing clear context for when to use the tool. It implies but does not explicitly state when not to use it or mention alternatives beyond the sibling context.

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

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0

Disambiguation5/5

The two tools have clearly distinct purposes: get_company_metrics focuses on deep financial analysis and fundamental metrics, while get_stock_snapshot provides a comprehensive stock overview including real-time price and valuation. There is no overlap in functionality, making it easy for an agent to choose the right tool based on the task.

Naming Consistency5/5

Both tools follow a consistent verb_noun naming pattern (get_company_metrics and get_stock_snapshot), using the same verb 'get' and descriptive nouns. This uniformity makes the tool set predictable and easy to understand.

Tool Count2/5

With only two tools, the server feels under-scoped for financial analysis, as it lacks essential operations like searching for companies, comparing metrics, or updating data. While the tools are well-defined, the count is too low to cover a comprehensive financial domain effectively.

Completeness2/5

The tool set is severely incomplete for financial analysis, missing critical operations such as listing companies, retrieving historical data, or performing comparisons. Agents will face dead ends when trying to conduct thorough analysis beyond the two provided snapshots.

Maintenance

ActivityStale

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Drillr — The financial MCP for AI agents A
ai.drillr
The financial MCP for AI agents - 90+ financial tables, SEC filings, signals, alt-data.
Finance Research & Data Data Platforms
1036
ko-mcp A
io.github.SharpLu
Real SEC, 13F, insider, congress & macro data your AI agent can cite. Hosted MCP, 24 tools.
Finance Government Data
242
circlfi-mcp
io.github.negm17111995
13-model stock valuation engine for AI agents - fair values for 5,900+ US stocks, updated daily.
Finance AI & Machine Learning
2
Stockfacts
io.github.AAAZZZR
US stock market data for AI agents: SEC filings, financials, insider trades, 13F, options, macro.
Finance Research & Data
2

Related MCP Servers

fathom-fyi
Finance Blockchain AI & Machine Learning
0xHashy
A
license
A
quality
D
maintenance
Financial intelligence for AI agents. 31 tools across 8 data sources — regime, derivatives, stablecoin flows, momentum, volatility, macro, DeFi, weather patterns, political cycles, seasonality. The context layer between your agent and a bad trade.
Updated 4 months ago (2026-05-04 06:39 UTC)
31
19
9
MIT
TickerAPIofficial
Finance Search AI & Machine Learning
tickerdb
A
license
A
quality
A
maintenance
Pre-computed financial market intelligence for AI agents. Stocks, crypto, and ETFs.
Updated a month ago (2026-08-10 01:27 UTC)
9
167
5
MIT
MCP Financial Tools
Finance Research & Data
huntbuilds
A
license
A
quality
D
maintenance
Provides actionable financial intelligence tools for AI agents including insider buying signals, earnings IV plays, market pulse, stock analysis, and options strategies via free public data sources.
Updated 6 months ago (2026-03-15 12:54 UTC)
6
MIT
MCP-Server-Financial-Analyzer
Finance Research & Data
HonglingLei
F
license
A
quality
D
maintenance
Provides AI assistants with real-time stock prices, financial statements, SEC filings, and analytical tools like DCF valuation and ratio analysis.
Updated 5 months ago (2026-04-07 03:39 UTC)
14

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/toolstem/toolstem-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

📊 Toolstem — Financial Data MCP for AI Agents | Stock Analysis & DCF

Quickstart — hosted endpoint (recommended)

Claude Desktop

Any MCP client (LangChain.js)

LangChain quick-start (langchain-toolstem)

Pricing

How billing works

How it works

Tools

get_stock_snapshot

get_company_metrics

compare_companies

Why Toolstem?

Advanced: self-host

npm

Claude Desktop (self-hosted)

From source

Environment Variables

Development

Architecture

License

Available Tools

Output Schema

TDQS

Output Schema

TDQS

Output Schema

TDQS

TDQS

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

fathom-fyi

TickerAPIofficial

MCP Financial Tools

MCP-Server-Financial-Analyzer

Latest Blog Posts

MCP directory API

LangChain quick-start (`langchain-toolstem`)

`get_stock_snapshot`

`get_company_metrics`

`compare_companies`