# Finbolt (remote · api.getfinbolt.com)

SEC-filed company financials with filing citations, plus market data, for AI agents

- Trust score: 77/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.getfinbolt.com`: 77/100 (this document), [markdown](https://verifymcp.io/servers/com-getfinbolt-finbolt/api.md), [page](https://verifymcp.io/servers/com-getfinbolt-finbolt/api)

## Channel facts

- Endpoint: `https://api.getfinbolt.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 60/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 31 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 73/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 6274 tokens (~202/item across 31 items; 31 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 87/100
  - Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (42% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 31 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 32 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Finbolt MCP server?

Finbolt is a hosted endpoint at https://api.getfinbolt.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-getfinbolt-finbolt 'https://api.getfinbolt.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-getfinbolt-finbolt": {
      "url": "https://api.getfinbolt.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-getfinbolt-finbolt": {
      "type": "http",
      "url": "https://api.getfinbolt.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-getfinbolt-finbolt]
url = "https://api.getfinbolt.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-getfinbolt-finbolt": {
      "type": "remote",
      "url": "https://api.getfinbolt.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-getfinbolt-finbolt --url 'https://api.getfinbolt.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-getfinbolt-finbolt:
    url: "https://api.getfinbolt.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-getfinbolt-finbolt": {
      "Transport": "http",
      "Url": "https://api.getfinbolt.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-getfinbolt-finbolt -t streamable-http -u 'https://api.getfinbolt.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-getfinbolt-finbolt": {
      "type": "http",
      "url": "https://api.getfinbolt.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-11 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-09 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-07 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-06 (score 70, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (31)

### `fetch_time_series_daily` (~149 tokens)

[Personal research only] Fetch daily stock data with OHLCV (Open, High, Low, Close, Volume) information for each trading day.

Input parameters:

- `datatype` (string): Response data type.
- `end_date` (string): Optional end date filter in YYYY-MM-DD format (inclusive).
- `max_data_points` (integer): Maximum number of time series data points to return.
- `outputsize` (string): Data output size.
- `start_date` (string): Optional start date filter in YYYY-MM-DD format (inclusive).
- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'TSLA') for which to retrieve daily data

### `fetch_time_series_weekly` (~137 tokens)

[Personal research only] Fetch weekly stock data with OHLCV (Open, High, Low, Close, Volume) aggregated by week.

Input parameters:

- `datatype` (string): Response data type.
- `end_date` (string): Optional end date filter in YYYY-MM-DD format (inclusive).
- `max_data_points` (integer): Maximum number of time series data points to return.
- `start_date` (string): Optional start date filter in YYYY-MM-DD format (inclusive).
- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'TSLA') for which to retrieve weekly data

### `fetch_time_series_monthly` (~137 tokens)

[Personal research only] Fetch monthly stock data with OHLCV (Open, High, Low, Close, Volume) aggregated by month.

Input parameters:

- `datatype` (string): Response data type.
- `end_date` (string): Optional end date filter in YYYY-MM-DD format (inclusive).
- `max_data_points` (integer): Maximum number of time series data points to return.
- `start_date` (string): Optional start date filter in YYYY-MM-DD format (inclusive).
- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'TSLA') for which to retrieve monthly data

### `search_endpoint` (~64 tokens)

[Personal research only] Searches for stock symbols and company names based on keywords (e.g., 'Tesla', 'Microsoft Corp').

Input parameters:

- `keywords` (string, required): Keywords to search for company names or stock symbols (e.g., 'Tesla', 'Microsoft Corp', 'AAPL')

### `fetch_quote` (~62 tokens)

[Personal research only] Fetches the latest price and trading information for a stock ticker symbol.

Input parameters:

- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'TSLA') for which to fetch the latest price and trading…

### `fetch_news_sentiment` (~164 tokens)

[Personal research only] Fetch news sentiment analysis data with sentiment scores, relevance scores, and article metadata.

Input parameters:

- `datatype` (string): Response data type.
- `limit` (integer): Maximum number of news articles to return (1-200).
- `sort` (string): Sort order for results.
- `tickers` (string, required): Comma-separated list of ticker symbols to filter news articles.
- `time_from` (string): Start time for news articles in YYYYMMDDTHHMM format (e.g., '20240101T0000')
- `time_to` (string): End time for news articles in YYYYMMDDTHHMM format (e.g., '20240131T2359')
- `topics` (string): Optional news topics filter.

### `fetch_company_overview` (~70 tokens)

[Personal research only] Fetch comprehensive company overview including business description, financial ratios, market capitalization, dividend information, and key financial metrics.

Input parameters:

- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'TSLA') for which to retrieve comprehensive company over…

### `fetch_income_statement` (~73 tokens)

[Personal research only] Fetch annual and quarterly income statement data including revenue, expenses, net income, EPS, and other profit & loss metrics.

Input parameters:

- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'GOOGL') for which to retrieve annual and quarterly inco…

### `fetch_balance_sheet` (~71 tokens)

[Personal research only] Fetch annual and quarterly balance sheet data including assets, liabilities, shareholders' equity, and other financial position metrics.

Input parameters:

- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'GOOGL') for which to retrieve annual and quarterly bala…

### `fetch_cash_flow` (~67 tokens)

[Personal research only] Fetch annual and quarterly cash flow statement data including operating, investing, and financing cash flows.

Input parameters:

- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'GOOGL') for which to retrieve annual and quarterly cash…

### `fetch_earnings` (~77 tokens)

[Personal research only] Fetch annual and quarterly earnings data including EPS (earnings per share) estimates vs actual results, surprise percentages, and earnings growth trends.

Input parameters:

- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'GOOGL') for which to retrieve annual and quarterly earn…

### `fetch_exchange_rate` (~86 tokens)

[Personal research only] Fetch real-time currency exchange rates between two currencies with bid/ask prices and conversion rates.

Input parameters:

- `from_currency` (string, required): Source currency code (e.g., 'USD', 'EUR', 'GBP') to convert from
- `to_currency` (string, required): Target currency code (e.g., 'USD', 'EUR', 'JPY') to convert to

### `fetch_sma` (~203 tokens)

[Personal research only] Fetch Simple Moving Average (SMA) technical indicator time series with customizable time periods.

Input parameters:

- `datatype` (string): Response data type.
- `end_date` (string): Optional end date filter in YYYY-MM-DD format (e.g., '2024-12-31').
- `interval` (string, required): Time interval for data points.
- `max_data_points` (integer): Maximum number of time series data points to return.
- `series_type` (string): Price data to use for calculation.
- `start_date` (string): Optional start date filter in YYYY-MM-DD format (e.g., '2024-01-01').
- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'TSLA') for which to calculate Simple Moving Average
- `time_period` (integer, required): Number of data points to use for moving average calculation (e.g., 20 for 20-day SMA)

### `fetch_ema` (~206 tokens)

[Personal research only] Fetch Exponential Moving Average (EMA) technical indicator time series with greater weight on recent prices.

Input parameters:

- `datatype` (string): Response data type.
- `end_date` (string): Optional end date filter in YYYY-MM-DD format (e.g., '2024-12-31').
- `interval` (string, required): Time interval for data points.
- `max_data_points` (integer): Maximum number of time series data points to return.
- `series_type` (string): Price data to use for calculation.
- `start_date` (string): Optional start date filter in YYYY-MM-DD format (e.g., '2024-01-01').
- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'TSLA') for which to calculate Exponential Moving Average
- `time_period` (integer, required): Number of data points to use for moving average calculation (e.g., 12 for 12-period EMA)

### `fetch_macd` (~238 tokens)

[Personal research only] Fetch MACD (Moving Average Convergence Divergence) technical indicator time series with signal line and histogram.

Input parameters:

- `datatype` (string): Response data type.
- `end_date` (string): Optional end date filter in YYYY-MM-DD format (e.g., '2024-12-31').
- `fastperiod` (integer): Fast EMA period for MACD calculation (default: 12)
- `interval` (string, required): Time interval for data points.
- `max_data_points` (integer): Maximum number of time series data points to return.
- `series_type` (string): Price data to use for calculation.
- `signalperiod` (integer): Signal line EMA period for MACD calculation (default: 9)
- `slowperiod` (integer): Slow EMA period for MACD calculation (default: 26)
- `start_date` (string): Optional start date filter in YYYY-MM-DD format (e.g., '2024-01-01').
- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'TSLA') for which to calculate MACD

### `fetch_rsi` (~192 tokens)

[Personal research only] Fetch RSI (Relative Strength Index) momentum oscillator time series ranging from 0 to 100.

Input parameters:

- `datatype` (string): Response data type.
- `end_date` (string): Optional end date filter in YYYY-MM-DD format (e.g., '2024-12-31').
- `interval` (string, required): Time interval for data points.
- `max_data_points` (integer): Maximum number of time series data points to return.
- `series_type` (string): Price data to use for calculation.
- `start_date` (string): Optional start date filter in YYYY-MM-DD format (e.g., '2024-01-01').
- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'TSLA') for which to calculate RSI
- `time_period` (integer): Number of periods for RSI calculation (typically 14)

### `fetch_bbands` (~238 tokens)

[Personal research only] Fetch Bollinger Bands technical indicator time series with upper band, lower band, and middle line (SMA).

Input parameters:

- `datatype` (string): Response data type.
- `end_date` (string): Optional end date filter in YYYY-MM-DD format (e.g., '2024-12-31').
- `interval` (string, required): Time interval for data points.
- `max_data_points` (integer): Maximum number of time series data points to return.
- `nbdevdn` (integer): Number of standard deviations for lower band (typically 2)
- `nbdevup` (integer): Number of standard deviations for upper band (typically 2)
- `series_type` (string): Price data to use for calculation.
- `start_date` (string): Optional start date filter in YYYY-MM-DD format (e.g., '2024-01-01').
- `symbol` (string, required): Stock ticker symbol (e.g., 'AAPL', 'MSFT', 'TSLA') for which to calculate Bollinger Bands
- `time_period` (integer): Number of periods for moving average calculation (typically 20)

### `analyze_stock` (~387 tokens)

[Personal research only] One-call stock brief. `filed` holds fundamentals from SEC filings (TTM revenue and growth, gross and
operating margin, net income, free cash flow, net debt; for banks net revenue, net interest income,
efficiency ratio, PPNR, provisions, loans, deposits, ROE, ROTCE and tangible book; for broker-dealers
efficiency ratio, pretax margin, compensation ratio and ROE; for insurers total revenues, premiums earned,
net investment income, benefits and losses, a simple combined ratio for P&C insurers, ROE, and book value
per share with and without AOCI), each filing cited by accession in
sources.edgar (https://www.sec.gov/Archives/edgar/data/{cik}/{accession without dashes}/). A balance
input the newest filing omits comes from the latest filing within 15 months, dated in inputs_as_of.
\`market` holds delayed price, 52-week range, 50/200-day averages and RSI(14); `derived` holds market
cap, P/E (on filed diluted EPS LTM), P/B and P/TBV (insurers: P/B and P/B ex-AOCI), each with its inputs. A figure that couldn't be
computed is in gaps with its reason; lines that don't apply to the company's layout are left out (layout_note). Up to 4 descriptive
observations, including any quarter whose tax rate or non-operating income moves net income. News
sentiment on Pro. Start here for "tell me about X".

Personal research only: on every plan, this tool's output is for your own personal, non-commercial research. Do not use it in a commercial product, client deliverable or service.

Input parameters:

- `symbol` (string, required): Stock ticker, e.g. 'AAPL'

### `compare_stocks` (~276 tokens)

[Personal research only] Side-by-side comparison of 2-6 stocks as one table: TTM revenue and growth, pretax margin, net income
growth and diluted EPS growth from SEC filings (each row's window ends on its ttm_to), net debt for
standard layouts, delayed price, day change, distance from the 52-week high and trend, market cap, and
P/E on filed diluted EPS LTM (FY + YTD - prior YTD). `order` lists each filed figure highest first, P/E
lowest first. `comparability` says what revenue means per layout; cell_notes say what moves a figure.
Filings are cited by accession in sources.edgar: open
https://www.sec.gov/Archives/edgar/data/{cik}/{accession without dashes}/. Costs 5 credits for each ticker
that returns an analysis: 10 for 2 tickers, 30 for 6. A ticker that is not covered or fails is free.

Personal research only: on every plan, this tool's output is for your own personal, non-commercial research. Do not use it in a commercial product, client deliverable or service.

Input parameters:

- `symbols` (array, required): 2 to 6 tickers, e.g. ['NVDA', 'AMD']

### `get_fact` (~288 tokens)

One reported figure from SEC filings, with its citation: filing accession number, form, filing
date, XBRL tag, period and a link to the filing. Restated values are listed. A figure the company
never reported comes back as missing, never estimated. Values are in units as filed (USD, shares,
USD/shares). A value and its as_originally_reported version come only from financial statements
(10-K, 10-Q, their amendments and transition reports, 20-F, 40-F), never a proxy or an 8-K.

Input parameters:

- `as_of`: Optional date: return the figure as it was on file then (before any later restatement)
- `company` (string, required): Ticker (e.g. 'AAPL') or SEC CIK
- `concept` (string, required): Line item such as 'revenue', 'net_income', 'eps_diluted', 'total_assets', 'operating_cash_flow', 'shares_outstanding', 'book_value_per_share', 'net_debt', 'dividend_payout_ratio', 'net_revenues', or…
- `period` (string): 'latest', a fiscal year 'FY2025', a fiscal quarter 'FY2025 Q2', or a period end date '2025-06-28'

### `financials` (~422 tokens)

A financial statement from SEC filings, newest period first, every value traceable to its filing.
Quarterly figures the company reported only year-to-date are derived (e.g. Q4 = FY - 9M) and marked;
per-share values and share counts can't be derived that way and are null with reason not_derivable.
A line the company tagged with its own element is null with reason custom_element. Common equity and the
book values from it are null with reason pending when a preferred issue or redemption follows the last
tagged liquidation preference.
Every null carries a reason, in cell_notes or (when all of a row's nulls share it) on the row. Banks,
insurers and broker-dealers get not_applicable, with a reason, for lines they don't present (capex,
current assets, total debt for banks and brokers); banks get loans, allowance and deposits. Broker-dealers
and asset managers get the bank layout under net_revenues, with compensation and the compensation ratio.
Balance sheets include common equity, book value per share and net debt. A balance the period's own
filing didn't present is null, with any later comparative value in a note. A derived or fallback line equal to
another row in every column (total equity with no NCI) is named in same_as instead of shown, and a derived Q4
with the opposite sign to Q1-Q3 says so. Values are in units as filed. Values and earlier
versions come only from financial statements (10-K, 10-Q, their amendments and transition reports,
20-F, 40-F).

Input parameters:

- `as_of`: Optional date: the statement as it was on file then
- `company` (string, required): Ticker (e.g. 'AAPL') or SEC CIK
- `limit` (integer): Number of periods, 1 to 8
- `period_type` (string): 'annual' or 'quarterly'
- `statement` (string): 'income', 'balance' or 'cashflow'

### `earnings_release` (~247 tokens)

The quarterly earnings release from the company's 8-K, as the company printed it: headline figures (GAAP,
non-GAAP and operating measures) with period and scale, the company's guidance word for word, and beside each
figure the SEC-tagged figure for the same quarter and for the quarter before. matches_tagged says whether the
printed and tagged figures agree. Differences are shown, never reconciled, and nothing is merged into get_fact. A
quarter just released has no tagged figure until its 10-Q or 10-K is filed. Set all_cells to true to get every
figure in the release that matches one of our line items. 1 credit.

Input parameters:

- `all_cells` (boolean): Leave false to get the headline figures and the guidance. Set true to get every figure in the release that matches one of our line items, which can be long.
- `company` (string, required): Ticker (e.g. 'AAPL') or SEC CIK
- `period` (string): 'latest', a fiscal quarter 'FY2026 Q3', the quarter's end date '2026-09-30', or the 8-K's accession number

### `restatement_history` (~395 tokens)

Figures that a later SEC filing changed: the value as first filed, the latest value, the change in percent, and
which one get_fact gives you. Most changes are recasts (a new accounting rule, a reclassification or a
discontinued business shown again on the new basis), not corrections of errors. amended: true marks a change
from an amended filing. Covers the main lines of the income statement, balance sheet and cash flow statement for
up to 8 years, or any line you name. Not listed: rounding, stock-split rebasing, a sign flipped by tagging, a
1,000-times scale fix, and a full-year figure tagged with a quarter's value. 1 credit. The main lines checked
are: revenue, total_revenues, total_net_revenue, cost_of_revenue, gross_profit, selling_general_admin,
research_and_development, operating_income, interest_expense, net_interest_income, noninterest_income,
noninterest_expense, provision_for_credit_losses, premiums_earned, benefits_and_losses, net_investment_income,
pretax_income, income_tax, net_income, eps_basic, eps_diluted, diluted_shares_weighted, total_assets,
total_liabilities, stockholders_equity, cash, long_term_debt, loans_net, deposits, operating_cash_flow,
investing_cash_flow, financing_cash_flow, capital_expenditure, depreciation_amortization, dividends_paid,
share_repurchases.

Input parameters:

- `as_of`: Optional date: the history as it was on file then
- `company` (string, required): Ticker (e.g. 'AAPL') or SEC CIK
- `concept`: Optional line item such as 'revenue' or 'net_income'; left out, the main lines listed below are checked
- `years` (integer): Fiscal years back from the latest on file, 1 to 8

### `changes_since` (~185 tokens)

For up to 40 companies, what each one filed with the SEC since a date in the last 400 days: annual and quarterly
reports, amendments, earnings-release 8-Ks, non-reliance 8-Ks (the company says earlier statements should no
longer be relied on), the new periods get_fact can now answer, and figures a filing in that window changed. 1
credit per company with a new filing in the period; a call where nothing changed is free.

Input parameters:

- `as_of`: Optional date: what was on file then
- `companies` (array, required): Tickers (e.g. 'AAPL') or SEC CIKs, at most 40
- `since` (string, required): Date, inclusive, compared with the filing date, within the last 400 days, e.g. '2026-10-01'

### `peer_table` (~159 tokens)

2 to 10 companies side by side from their SEC filings: revenue and its growth over the last four quarters, pretax
margin, net income growth, diluted EPS growth and net debt (negative means net cash), with each column ranked.
Pass a price and its date for any company to get its market cap and P/E. 1 credit per company with filed
figures.

Input parameters:

- `prices`: Optional prices you supply, keyed by ticker, each {'price': 182.5, 'date': '2026-10-24'}. A ticker without a dated price gets null valuation columns.
- `tickers` (array, required): 2 to 10 tickers, like ['JPM', 'BAC', 'WFC']

### `snapshot` (~146 tokens)

A first look at one company from its SEC filings alone: revenue, margins, growth, EPS, cash flow and net debt
(negative means net cash) over the last four quarters, with short observations built only from those figures,
and the filings cited. Finbolt uses no market price: pass price and price_date to get market cap, P/E and price
to book. 1 credit.

Input parameters:

- `company` (string, required): Ticker (e.g. 'AAPL') or SEC CIK
- `price`: Optional price per share you supply; needs price_date
- `price_date`: The date of your price, e.g. '2026-10-24'

### `resolve` (~191 tokens)

Before you ask for a figure: which company a ticker or SEC CIK is and whether Finbolt covers it, what a period
phrase such as "Q3 2025" or "the June 2025 quarter" means for that company's fiscal year (both readings when
fiscal and calendar differ), and which line item a name such as "capex" maps to. Returns no figures. Free.

Input parameters:

- `as_of`: Optional date phrases without a year are read against
- `company` (string, required): Ticker (e.g. 'BRK.B') or SEC CIK
- `concept`: Optional line item name or alias, e.g. 'EBIT', 'capex'
- `period`: Optional period phrase, e.g. 'Q3 2025', 'FY2024', 'the June 2025 quarter', 'twelve months to March 2025'

### `verify` (~389 tokens)

Check the figures in a memo against SEC filings. Each claim gets one verdict: supported,
supported_rounded, period_mismatch, contradicted, ambiguous, not_in_primary_sources or skipped. Returns
record_id, counts by verdict, each contradicted claim (memo value vs filed value, period, accession, and the
error when it is a unit or sign error) and how_to_read. Every call is written to your account's append-only
Record; call verify_evidence with the record_id for each claim's full evidence.

Input parameters:

- `agent` (string): The model and version that wrote the memo
- `claims`: Up to 50 claims you parsed, each {claim_id, span (the verbatim clause), type 1-6 (1 reported, 2 derived, 3 company_disclosed, 4 market, 5 estimate, 6 forward_looking), concept, value or stated (e.g.…
- `company` (string, required): Ticker (e.g. 'AAPL') or SEC CIK of the company the memo is about
- `input_text`: Optional: the prompt. On the Fund plan it is kept encrypted in your Record; on other plans it is not kept.
- `memo_date`: The memo's date, e.g. '2026-06-30': figures are read as they were on file that day
- `output_text`: Optional: the memo. On the Fund plan it is kept encrypted in your Record; on other plans it is not kept.
- `sentences`: Instead of claims: up to 50 memo sentences, parsed for you, with ids C1..Cn

### `verify_evidence` (~83 tokens)

Full evidence for the claims of one verify call on your account: each claim's span, parsed figure,
verdict, reason, tolerance and the filings read, with tag, accession, link, period and source credit.

Input parameters:

- `claim_ids`: Optional: only these claims (default: all)
- `record_id` (string, required): The record_id a verify call returned

### `find_tool` (~36 tokens)

Search all 113 data tools, including ones not in the default list.

Input parameters:

- `query` (string, required): What you need, e.g.

### `run_tool` (~52 tokens)

Run any Finbolt data tool by name, including ones not in the default list.

Input parameters:

- `arguments` (object): Arguments for that tool
- `name` (string, required): Exact tool name from find_tool, e.g.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-getfinbolt-finbolt/api#diagnostics

## Score history

- 2026-11-21: 77
- 2026-11-20: 77
- 2026-11-19: 76
- 2026-11-18: 76
- 2026-11-17: 75
- 2026-11-16: 75
- 2026-11-15: 75
- 2026-11-14: 74
- 2026-11-13: 74
- 2026-11-12: 73
- 2026-11-11: 73
- 2026-11-10: 72
- 2026-11-09: 72
- 2026-11-08: 71
- 2026-11-07: 71
- 2026-11-06: 70
- 2026-11-05: 70
- 2026-11-04: 69
- 2026-11-03: 69
- 2026-11-02: 68
- 2026-11-01: 68
- 2026-10-31: 68
- 2026-10-30: 67
- 2026-10-29: 67
- 2026-10-28: 66
- 2026-10-27: 66
- 2026-10-26: 65

## Common questions

### What is the Finbolt MCP server?

Finbolt is an MCP server listed in the public MCP registry as com.getfinbolt/finbolt. SEC-filed company financials with filing citations, plus market data, for AI agents. This page covers its hosted endpoint (https://api.getfinbolt.com/mcp).

### Is the Finbolt MCP server safe to use?

Finbolt scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Finbolt MCP server expose?

Finbolt exposes 31 tools: fetch_time_series_daily, fetch_time_series_weekly, fetch_time_series_monthly, search_endpoint, fetch_quote, and 26 more. Their descriptions and schemas cost roughly 5,490 tokens of context every time the server is loaded.

### Does the Finbolt MCP server require authentication?

No. We connected to Finbolt without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Finbolt MCP server still maintained?

Finbolt is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Finbolt MCP server?

VerifyMCP ran 12 checks on Finbolt, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Finbolt: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.getfinbolt.com/mcp
- Authorisation metadata: https://api.getfinbolt.com/.well-known/oauth-protected-resource/mcp
- Website: https://getfinbolt.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-getfinbolt-finbolt/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-getfinbolt-finbolt/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-getfinbolt-finbolt/api.json
- HTML version of this page: https://verifymcp.io/servers/com-getfinbolt-finbolt/api
