# CapitalSnitch (remote · capitalsnitch.com)

SEC insider trades, Congress trades, 13F funds, earnings and 8-K filings for AI, with SEC links.

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

## Components

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

## Channel facts

- Endpoint: `https://capitalsnitch.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.20261025.0`

## 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**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 41/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 6000 tokens (~206/item across 29 items; 27 tools + 2 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**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 97% of tool parameters carry a description.
  - Structured output schemas are declared (100% 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 27 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 29 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

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

CapitalSnitch is a hosted endpoint at https://capitalsnitch.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-capitalsnitch-insider-trading 'https://capitalsnitch.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-capitalsnitch-insider-trading": {
      "url": "https://capitalsnitch.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-capitalsnitch-insider-trading": {
      "type": "http",
      "url": "https://capitalsnitch.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-capitalsnitch-insider-trading]
url = "https://capitalsnitch.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-capitalsnitch-insider-trading": {
      "type": "remote",
      "url": "https://capitalsnitch.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-capitalsnitch-insider-trading --url 'https://capitalsnitch.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-capitalsnitch-insider-trading:
    url: "https://capitalsnitch.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-capitalsnitch-insider-trading": {
      "Transport": "http",
      "Url": "https://capitalsnitch.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-capitalsnitch-insider-trading -t streamable-http -u 'https://capitalsnitch.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-capitalsnitch-insider-trading": {
      "type": "http",
      "url": "https://capitalsnitch.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.

### 2026-11-16 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-10 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 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 (27)

### `get_insider_activity` (~161 tokens)

Insider activity for a company

List and summarize insider trades (SEC Form 4) for one company: who bought or sold, when, how much,
their role (CEO, CFO, Director, 10% owner…), and a link to each filing. Use for questions like
'are insiders buying or selling NVDA?' or 'show Tesla insider trades this year'.

Input parameters:

- `days` (integer): Look-back window in days (1–3650).
- `limit` (integer): Max trades to return (1–100).
- `open_market_only` (boolean): True = only open-market buys/sells (the meaningful signal). False = include awards, option exercises, gifts, tax withholding.
- `ticker` (string, required): Stock ticker, e.g. 'AAPL'.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `find_insider_buying` (~175 tokens)

Market-wide insider buying scan

Scan ALL U.S. companies for insider open-market PURCHASES — the strongest insider signal. Ranks companies by
total value bought, number of distinct insiders buying ('cluster buying'), or recency. Use for 'which insiders
are buying right now?', 'CEO purchases this month', 'companies where 3+ insiders bought'.

Input parameters:

- `days` (integer): Look-back window in days (1–365).
- `limit` (integer): Max companies (1–50).
- `min_insiders` (integer): Minimum number of distinct insiders buying (cluster buying).
- `min_total_value_usd` (number): Minimum total purchase value per company.
- `roles`: Only count buyers with these roles, e.g. ['CEO','CFO']. Omit for all.
- `sort_by` (string): Ranking.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_insider_signal` (~124 tokens)

Explained insider signal for a company

Score current insider behavior for one company (0–100, 50 = neutral) and EXPLAIN it: open-market buying vs
selling, how unusual it is versus the company's own 5-year history, cluster buying, and C-suite participation,
with the evidence trades and SEC links. Use for 'is insider activity at X bullish or bearish?' or 'anything
unusual about insiders at X?'.

Input parameters:

- `days` (integer): Window to evaluate (30–365 days).
- `ticker` (string, required): Stock ticker, e.g. 'PLTR'.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_insider_person` (~113 tokens)

Trades by a specific insider

Find an insider (executive, director, or large holder) by name and list their open-market trades across all
companies, with totals. Use for 'what has Warren Buffett bought recently?' or 'Jensen Huang stock sales'.

Input parameters:

- `days` (integer): Look-back window in days (1–7300).
- `limit` (integer): Max trades (1–100).
- `name` (string, required): Insider name or part of it, e.g. 'Buffett' or 'Huang Jen'.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `search_companies` (~80 tokens)

Find a company / ticker

Look up tickers and official company names (with SEC CIK) from recent insider filings. Use when the user
names a company but not its ticker, or a ticker returns no results.

Input parameters:

- `limit` (integer)
- `query` (string, required): Company name or ticker fragment, e.g. 'palantir' or 'BRK'.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_data_status` (~54 tokens)

Data coverage and freshness

Report what data CapitalSnitch covers, how fresh it is, update schedule, sources, and known limitations.
Use when asked 'how current is this?', 'what data do you have?', or before making time-sensitive claims.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_market_context` (~130 tokens)

Market backdrop: regime, rates, Fed meeting odds

Current U.S. market backdrop in one call: market regime (calm uptrend / uptrend under stress / downtrend / panic /
recovery, from the S&P 500 trend and VIX), VIX level and percentile, Fed funds rate, 2y and 10y Treasury yields,
yield-curve shape, and the next Fed (FOMC) meetings with days until each and the market-implied odds of a cut,
hold or hike. Use for 'what's the market backdrop?', 'when is the next Fed meeting?', 'odds of a rate cut?'.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_company_context` (~251 tokens)

Full company picture: insiders + earnings + volatility + analysts

Everything that matters about one company in one call: the explained insider signal (score, cluster and
C-suite buying, unusual vs history) PLUS the next earnings date and countdown (and last earnings), the stock's
volatility regime (calm / normal / elevated / extreme vs its own past year), trend vs 50/200-day averages,
drawdown from the 52-week high, recent returns, Wall Street analyst consensus and its 3-month trend, and the
market backdrop (regime + next Fed meeting odds). Ends with 'what stands out' facts. Use for 'analyze X',
'should I look closer at X?', 'anything notable about X before earnings?'. Also includes the company's
financials (valuation, growth, profit) and dilution summary. Includes 'analysis': a written
CapitalSnitch Take (headline, story, bull case, bear case, what to watch) grounded in the data — present it to the
user, and say it is automated context, not investment advice.

Input parameters:

- `insider_days` (integer): Insider look-back window (30–365 days).
- `ticker` (string, required): Stock ticker, e.g. 'NVDA'.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_financials` (~165 tokens)

Financials: valuation, growth, profit, quarterly revenue trend

A company's fundamentals from its SEC filings (10-Q/10-K): market cap, P/E, price/sales, dividend yield,
12-month revenue and net income with year-over-year growth (growing / flat / declining, accelerating or slowing),
margins, free cash flow, cash, debt, cash runway, stock-based pay, and a quarter-by-quarter table of revenue,
net income and EPS with YoY change for each quarter. Use for 'is revenue growing?', 'what's the P/E?',
'does it pay a dividend?', 'is it profitable?', 'show the last 8 quarters'.

Input parameters:

- `quarters` (integer): Quarters of history (4–12).
- `ticker` (string, required): Stock ticker, e.g. 'SOFI'.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_dilution_history` (~216 tokens)

Dilution tracker: offerings, share count, price impact

Every stock offering, at-the-market (ATM) program, convertible note (including private Rule 144A deals announced
only in an 8-K), notes exchanged for shares, unregistered share sale and shelf registration the company filed with
the SEC, plus the company's 8-K filings of the last 30 days in plain English, with size, price per share, and how the stock reacted (day 1, day 2,
1 week, 1 month vs the prior close); the share-count trend (1-year change, 3-year yearly rate); and a 0–100
dilution-risk score with reasons (recent offerings, active shelf, cash burn, heavy stock pay). Use for 'has SOFI
diluted shareholders?', 'what happened to the price after the last offering?', 'is a share sale likely?'.

Input parameters:

- `ticker` (string, required): Stock ticker, e.g. 'SOFI'.
- `years` (integer): Years of offering history (1–5).

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `find_insider_clusters` (~261 tokens)

Smart cluster buying: batch detection + conviction score

Find every company where several different insiders made OPEN-MARKET purchases (option exercises, awards and
sales excluded), list each buyer's name, title and amount, and FLAG BATCHES: many buyers filing on the same day
with similar, modest amounts usually means one company program (employee purchase plan, IPO or private-placement
allocation), not independent conviction. Each company gets a 0–100 conviction score (independent buyers, C-suite
participation, size per buyer, how much they grew their stake, purchases spread over several days, minus batch
penalty) with reasons. Use for 'find companies where 3+ insiders bought in the last 60 days', 'cluster buying
that is real, not a comp plan', 'rank insider clusters by conviction'.

Input parameters:

- `days` (integer): Look-back window in days (7–365).
- `exclude_batches` (boolean): True = hide companies whose buying looks like one company program (same day, similar small amounts).
- `limit` (integer): Max companies (1–40).
- `min_insiders` (integer): Minimum different insiders buying.
- `min_total_value_usd` (number): Minimum total bought per company.
- `sort_by` (string): Ranking.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `find_emerging_insider_buying` (~168 tokens)

Emerging vs crowded insider buying

Spot insider buying EARLY: companies where fewer than 5 different insiders bought in the window but the pace is
rising (more buyers or more dollars recently than earlier), versus 'crowded' companies where 5+ insiders already
bought. Explains exactly how 'rising' is measured. Use for 'which stocks have early, increasing insider buying
that is not crowded yet?', 'emerging insider signals'.

Input parameters:

- `days` (integer): Whole window in days (45–365).
- `limit` (integer): Max companies per list (1–30).
- `min_value_usd` (number): Minimum total bought in the window per company.
- `recent_days` (integer): 'Recent' part of the window, compared with the earlier part.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_institutional_ownership` (~167 tokens)

Institutional ownership (13F): who owns the stock and what changed

Who owns a stock, from SEC Form 13F filings by investment managers (hedge funds, mutual funds, banks, pensions
with $100M+): number of institutional holders, share of the company they hold, top holders with their stake and
quarter-over-quarter change, and how many funds opened, added, cut or sold out. Analyst and Edge also get the
lists of new funds, sold-out funds, biggest adds and biggest cuts. Use for 'who owns PLTR?', 'are funds buying or
selling NVDA?', 'top institutional holders', 'did hedge funds add last quarter?'.

Input parameters:

- `ticker` (string, required): Stock ticker, e.g. 'PLTR'.
- `top` (integer): How many top holders (5–25).

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_fund_holdings` (~131 tokens)

What a fund owns (13F) and what it changed

A fund's latest SEC Form 13F portfolio: total value, number of positions, top holdings with % of portfolio,
and what changed vs the quarter before: new positions, positions sold out, biggest adds and biggest cuts. Use for
'what did Berkshire buy last quarter?', 'top holdings of Bridgewater', 'did Ark sell Tesla?'.

Input parameters:

- `manager` (string, required): Fund / manager name or part of it, e.g. 'Berkshire', 'Bridgewater', 'Renaissance', 'ARK'.
- `top` (integer): How many top holdings (5–40).

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_congress_trades` (~271 tokens)

Congress members' stock trades (free)

Stock trades reported by members of the U.S. House and Senate (STOCK Act Periodic Transaction Reports): member,
party, state, chamber, stock, purchase or sale, amount range, trade date, filing date, how many days late it was
reported, owner (self/spouse/joint/child) and a link to the official filing. With no filters: the week's summary,
most-traded stocks and late filers. FREE public information on every plan and never counted toward the daily limit.
Reports arrive up to 45 days after the trade (median about a month), so this is a historical record, not a live feed.
Use for 'which members of Congress traded NVDA?', 'what has Pelosi bought?', 'congressional trades this week'.
Must not be used for credit decisions, fundraising or solicitation.

Input parameters:

- `chamber` (string): Filter by chamber.
- `days` (integer): Look-back window by filing date (7–1100 days).
- `limit` (integer): Max trades (1–100).
- `member`: Member of Congress name or part of it, e.g. 'Pelosi'.
- `ticker`: Stock ticker, e.g. 'NVDA'. Omit for all.
- `trade_type` (string): Filter by type.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_earnings_calendar` (~191 tokens)

Upcoming earnings, with insider buying

Companies reporting earnings soon, with the date, time (before open / after close) and countdown, joined with
recent insider activity. With only_with_insider_buying=true it answers 'which companies reporting soon have
insiders been buying?' — insiders buying ahead of a report is a rare and closely watched signal. Also use for
'when does X report?' (pass tickers=['X'], only_with_insider_buying=false).

Input parameters:

- `days_ahead` (integer): Companies reporting within this many days (1–60).
- `insider_lookback_days` (integer): Insider look-back window (7–365 days).
- `limit` (integer)
- `only_with_insider_buying` (boolean): True = only companies where insiders made open-market purchases in the look-back window (the 'edge' list).
- `tickers`: Optional: only these tickers.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_daily_brief` (~74 tokens)

Today's insider + market briefing

Ready-made daily briefing: market backdrop and next Fed meeting odds, insiders who bought ahead of upcoming
earnings, the biggest insider purchases this week, CEO/CFO purchases, and cluster buying. Use for 'give me
today's briefing', 'what's interesting today?', or as the start of a morning routine.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `manage_watchlist` (~158 tokens)

Manage my watchlist (alerts)

The user's CapitalSnitch watchlist (Edge plan, up to 25 tickers). Watchlist companies get INSTANT EMAIL ALERTS
(insider buys, big insider sales, new stock offerings; ~30 minutes after the SEC filing) and lead the daily email
briefing. Use for 'alert me when insiders buy NVDA', 'add PLTR and SOFI to my watchlist', 'what am I watching?',
'stop alerting me about TSLA'. Never counts toward the daily limit.

Input parameters:

- `action` (string): list = show it; add/remove tickers; replace = set the whole list.
- `tickers`: Tickers for add/remove/replace, e.g. ['NVDA','PLTR'].

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `set_alert_preferences` (~162 tokens)

Alert settings (instant alerts, big insider moves, daily email)

Turn the user's CapitalSnitch email alerts on or off (Edge plan): instant watchlist alerts, market-wide 'big
insider moves' alerts, and the daily briefing email. Omit a setting to leave it unchanged; call with no settings to
see the current ones. Use for 'alert me about any big insider buys', 'stop the daily email', 'turn my alerts on'.
Never counts toward the daily limit.

Input parameters:

- `big_moves_alerts`: Email alerts for major insider moves across the WHOLE market: CEO/CFO purchases of $1M+ and high-conviction cluster buying, even outside the watchlist.
- `daily_email`: The weekday morning briefing email.
- `instant_alerts`: Email alerts for watchlist companies.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_my_alerts` (~73 tokens)

My recent alert emails

The alert and daily-briefing emails CapitalSnitch sent the user recently, newest first (Edge plan). Use for
'what alerts did I get today?', 'did anything trigger on my watchlist?'. Never counts toward the daily limit.

Input parameters:

- `limit` (integer): How many (1–50).

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `about_capitalsnitch` (~130 tokens)

About CapitalSnitch: plans, prices, sign-up, support

Facts about CapitalSnitch itself: what it is (a live commercial service, not a demo), every plan with price,
daily limit and features, which data each plan includes, payment methods, how to sign up (right here in the chat
or on the website), which AI apps can connect and how, and the support email. Use for 'what is CapitalSnitch?',
'how much does it cost?', 'what plans are there?', 'how do I contact them?', 'can ChatGPT/Grok connect?'.
Free, needs no account and never counts toward the daily limit.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_my_account` (~139 tokens)

My CapitalSnitch account and subscription

The user's own CapitalSnitch account: plan (Free / Scout / Analyst / Edge), whether it is active, renewing,
cancelled or expired, the date it renews or ends and days left, payment method type, questions used today vs
the daily limit, which features are included and which need an upgrade. Free to call (does not count toward the
daily limit). Use when the user asks 'what plan am I on?', 'when does my subscription renew?', 'is my plan
active?', 'how many questions do I have left?'. The user is recognized by their personal connection address —
no email or password is needed.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `get_account_link` (~143 tokens)

One-click link to upgrade, renew or manage the account

Create a private, single-use link that signs the user straight into the right CapitalSnitch page — checkout
(card or crypto) to upgrade or renew, or their account page to cancel, change email settings or make a new
connection address. Valid 15 minutes, works once. Give it to the user to click; no password or email code
needed. Free to call.

Input parameters:

- `action` (string): upgrade/renew = checkout page; manage = account page (cancel, watchlist, email settings); new_connection_address = account page to replace a leaked address; briefing = today's briefing page.
- `plan`: Plan to pre-select for upgrade/renew.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `start_signup` (~365 tokens)

Sign up or sign in from the chat (step 1: email code)

Create a CapitalSnitch account — or sign back in and get a new connection address — entirely from the chat,
no website needed. Step 1 of 2: emails the user a 6-digit code. Then ask the user for the code and call
confirm_signup(email, code). Before calling, ask the user which plan they want (Free, Scout $29, Analyst $39,
Edge $49 per month; yearly = 2 months free, one-time, never auto-renews) and, for a paid plan, card or crypto.
The user must agree to the key terms first: call once without user_accepted_terms to get them, show them, and
only after an explicit 'yes' set user_accepted_terms=true. Free to call.

Input parameters:

- `billing` (string): Paid plans: monthly, or annual (2 months free).
- `crypto_asset`: Crypto only, e.g. 'USDC-base' (recommended), 'USDT-solana', 'BTC-bitcoin', 'ETH-base', 'SOL-solana'.
- `email` (string, required): The user's email address. A 6-digit code is sent there.
- `payment_method`: Paid plans: 'card' (credit/debit via Square; monthly renews automatically), 'wallet' (Apple Pay / Google Pay / Cash App Pay, one-time, no auto-renew) or 'crypto' (USDC/USDT/BTC/ETH/SOL, one-time, no…
- `plan` (string): Plan the user wants. Ask them; describe the options if unsure.
- `user_accepted_terms` (boolean): True ONLY after you showed the user the key terms (returned when this is false) and the user explicitly said they agree.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `confirm_signup` (~100 tokens)

Sign up or sign in from the chat (step 2: confirm code)

Step 2 of 2: checks the emailed code, creates the account (or signs in), and returns the user's personal
connection address plus — for a paid plan — the payment step (a secure card link, or exact crypto payment
details). The plan activates automatically when the payment lands. Free to call.

Input parameters:

- `code` (string, required): The 6-digit code from the email.
- `email` (string, required): Same email used in start_signup.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `buy_plan` (~200 tokens)

Buy or change a plan from the chat

Upgrade, renew or switch the signed-in user's plan without the website. Card: returns a secure Square
payment link (or, for an active card subscriber, switches the plan right away). Crypto: returns the exact amount,
coin, network and address to send. The plan activates automatically when paid. Free to call. Requires the user's
personal connection address; on the public preview use start_signup instead.

Input parameters:

- `billing` (string): monthly, or annual (2 months free).
- `crypto_asset`: Crypto only, e.g. 'USDC-base' (recommended).
- `payment_method` (string): 'card' (monthly renews automatically), 'wallet' (Apple Pay / Google Pay / Cash App, one-time) or 'crypto' (one-time).
- `plan` (string, required): Plan to buy.
- `user_accepted_terms` (boolean): True ONLY after showing the user the key terms and getting an explicit yes for this purchase.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

### `check_payment` (~74 tokens)

Check a payment

Has the payment arrived and is the plan active? For crypto, pass order_id: shows waiting / seen on the network
/ confirmed. For card, omit it: shows the account's current plan. Free to call.

Input parameters:

- `order_id`: Crypto order_id from buy_plan/confirm_signup. Omit for card payments.

Output parameters:

- `data_as_of`: Latest SEC filing date included in the data (YYYY-MM-DD).
- `disclaimer` (string)
- `notes` (array): Caveats, data-quality notes, next steps.
- `results`: Structured results (rows or an object).
- `sources` (array): Links to official SEC filings / pages backing the answer.
- `summary` (string): Plain-language answer. Quote this, then cite sources.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-capitalsnitch-insider-trading/capitalsnitch#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: 74
- 2026-11-14: 74
- 2026-11-13: 73
- 2026-11-12: 73
- 2026-11-11: 72
- 2026-11-10: 72
- 2026-11-09: 71
- 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: 67
- 2026-10-30: 67
- 2026-10-29: 66
- 2026-10-28: 66
- 2026-10-27: 65
- 2026-10-26: 65

## Common questions

### What is the CapitalSnitch MCP server?

CapitalSnitch is an MCP server listed in the public MCP registry as com.capitalsnitch/insider-trading. SEC insider trades, Congress trades, 13F funds, earnings and 8-K filings for AI, with SEC links. This page covers its hosted endpoint (https://capitalsnitch.com/mcp).

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

CapitalSnitch 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 CapitalSnitch MCP server expose?

CapitalSnitch exposes 27 tools: get_insider_activity, find_insider_buying, get_insider_signal, get_insider_person, search_companies, and 22 more. Their descriptions and schemas cost roughly 4,276 tokens of context every time the server is loaded.

### Does the CapitalSnitch MCP server require authentication?

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

### Is the CapitalSnitch MCP server still maintained?

CapitalSnitch 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 CapitalSnitch MCP server?

VerifyMCP ran 13 checks on CapitalSnitch, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. 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://capitalsnitch.com/mcp
- Website: https://capitalsnitch.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-capitalsnitch-insider-trading/capitalsnitch.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-capitalsnitch-insider-trading/capitalsnitch/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-capitalsnitch-insider-trading/capitalsnitch.json
- HTML version of this page: https://verifymcp.io/servers/com-capitalsnitch-insider-trading/capitalsnitch
