MCP servers › com.capitalsnitch › insider-trading
MCP server · registry snapshot 2026-10-26 · last tested 2026-10-26
com.capitalsnitch/insider-trading
CapitalSnitch — the publisher's title
by capitalsnitch.com · domain (the registry's namespace rule)Website ↗
SEC insider trades, Congress trades, 13F funds, earnings and 8-K filings for AI, with SEC links. — the publisher's description
Summary
com.capitalsnitch/insider-trading is a remote MCP server listed in the official MCP registry at version 1.20261025.0, under the namespace of the domain capitalsnitch.com. On 2026-10-26 ProtocolProbe connected to it in read-only mode and read its inventory: 27 tools, 2 resources and 3 prompts.
Record checks
1 of 2 record checks met · 7 do not apply
- met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
From public records, not a safety rating. Each check with its reason
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Tools
- 27
- Last tested
- 2026-10-26
Tool list size
11,046 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (27 tools). Counted with Anthropic's token counter on 2026-10-26, from the tool list we read on 2026-10-26. Median across 23,424 counted servers: 2,725 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-10-26 (capitalsnitch.com), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (1.20261025.0).
Observed fact
This server accepted a session without any credential and lists 1 tool whose name or declaration suggests it changes data (set_alert_preferences). That is our reading of the names; we did not call it. Source: our connection, 2026-10-26.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-26
- Mode
- read-only (no tool calls)
- Latest version
- 1.20261025.0, published 2026-10-26 (registry, as of the 2026-10-26 snapshot)
- First listed version
- 2026-10-26 (earliest version still in the registry; older removed versions would be earlier)
- Registry data
- snapshot 2026-10-26
- Package and repository
- checked 2026-10-26
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
New in the registry: not in the list of 2026-10-24, listed on 2026-10-26 with version 1.20261025.0 (published 2026-10-26).
Source: the official MCP Registry list on 2026-10-24 and on 2026-10-26.
What it is
What does this server offer?
Observed inventoryNone of its 27 tools are described as changing anything. For 27 the reading was uncertain, so no mark is shown.
- get_insider_activityon 6 other servers
“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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
tickerstringrequired“Stock ticker, e.g.”daysinteger“Look-back window in days (1–3650).”open_market_onlyboolean“True = only open-market buys/sells (the meaningful signal).”limitinteger“Max trades to return (1–100).”
- find_insider_buying
“Scan ALL U.S.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
daysinteger“Look-back window in days (1–365).”min_total_value_usdnumber“Minimum total purchase value per company.”rolesarray or null“Only count buyers with these roles, e.g.”min_insidersinteger“Minimum number of distinct insiders buying (cluster buying).”sort_bystring“Ranking.”limitinteger“Max companies (1–50).”
- get_insider_signal
“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-su…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
tickerstringrequired“Stock ticker, e.g.”daysinteger“Window to evaluate (30–365 days).”
- get_insider_person
“Find an insider (executive, director, or large holder) by name and list their open-market trades across all companies, with totals.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
namestringrequired“Insider name or part of it, e.g.”daysinteger“Look-back window in days (1–7300).”limitinteger“Max trades (1–100).”
- search_companieson 99 other servers
“Look up tickers and official company names (with SEC CIK) from recent insider filings.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
querystringrequired“Company name or ticker fragment, e.g.”limitinteger
- get_data_statuson 10 other servers
“Report what data CapitalSnitch covers, how fresh it is, update schedule, sources, and known limitations.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- get_market_contexton 7 other servers
“Current U.S.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- get_company_contexton 2 other servers
“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 earning…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
tickerstringrequired“Stock ticker, e.g.”insider_daysinteger“Insider look-back window (30–365 days).”
- get_financialson 24 other servers
“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, accele…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
tickerstringrequired“Stock ticker, e.g.”quartersinteger“Quarters of history (4–12).”
- get_dilution_historyon 1 other server
“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 registr…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
tickerstringrequired“Stock ticker, e.g.”yearsinteger“Years of offering history (1–5).”
- find_insider_clusters
“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 f…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
daysinteger“Look-back window in days (7–365).”min_insidersinteger“Minimum different insiders buying.”min_total_value_usdnumber“Minimum total bought per company.”exclude_batchesboolean“True = hide companies whose buying looks like one company program (same day, similar small amounts).”sort_bystring“Ranking.”limitinteger“Max companies (1–40).”
- find_emerging_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 …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
daysinteger“Whole window in days (45–365).”recent_daysinteger“'Recent' part of the window, compared with the earlier part.”min_value_usdnumber“Minimum total bought in the window per company.”limitinteger“Max companies per list (1–30).”
Show 15 more tools
- get_institutional_ownership
“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 holde…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
tickerstringrequired“Stock ticker, e.g.”topinteger“How many top holders (5–25).”
- get_fund_holdingson 4 other servers
“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…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
managerstringrequired“Fund / manager name or part of it, e.g.”topinteger“How many top holdings (5–40).”
- get_congress_tradeson 6 other servers
“Stock trades reported by members of the U.S.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
tickerstring or null“Stock ticker, e.g.”memberstring or null“Member of Congress name or part of it, e.g.”daysinteger“Look-back window by filing date (7–1100 days).”trade_typestring“Filter by type.”chamberstring“Filter by chamber.”limitinteger“Max trades (1–100).”
- get_earnings_calendaron 11 other servers
“Companies reporting earnings soon, with the date, time (before open / after close) and countdown, joined with recent insider activity.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
days_aheadinteger“Companies reporting within this many days (1–60).”only_with_insider_buyingboolean“True = only companies where insiders made open-market purchases in the look-back window (the 'edge' list).”insider_lookback_daysinteger“Insider look-back window (7–365 days).”tickersarray or null“Optional: only these tickers.”limitinteger
- get_daily_briefon 6 other servers
“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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- manage_watchliston 2 other servers
“The user's CapitalSnitch watchlist (Edge plan, up to 25 tickers).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs
actionstring“list = show it; add/remove tickers; replace = set the whole list.”tickersarray or null“Tickers for add/remove/replace, e.g.”
- set_alert_preferenceson 1 other server
“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.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs
instant_alertsboolean or null“Email alerts for watchlist companies.”big_moves_alertsboolean or null“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_emailboolean or null“The weekday morning briefing email.”
- get_my_alertson 1 other server
“The alert and daily-briefing emails CapitalSnitch sent the user recently, newest first (Edge plan).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
limitinteger“How many (1–50).”
- about_capitalsnitch
“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 (…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- get_my_accounton 10 other servers
“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, questi…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- get_account_linkon 1 other server
“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 setting…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs
actionstring“upgrade/renew = checkout page; manage = account page (cancel, watchlist, email settings); new_connection_address = account page to replace a leaked address; br…”planstring or null“Plan to pre-select for upgrade/renew.”
- start_signupon 9 other servers
“Create a CapitalSnitch account — or sign back in and get a new connection address — entirely from the chat, no website needed.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
6 inputs, 1 required
emailstringrequired“The user's email address.”planstring“Plan the user wants.”billingstring“Paid plans: monthly, or annual (2 months free).”payment_methodstring or null“Paid plans: 'card' (credit/debit via Square; monthly renews automatically), 'wallet' (Apple Pay / Google Pay / Cash App Pay, one-time, no auto-renew) or 'crypt…”crypto_assetstring or null“Crypto only, e.g.”user_accepted_termsboolean“True ONLY after you showed the user the key terms (returned when this is false) and the user explicitly said they agree.”
- confirm_signupon 1 other server
“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 cry…”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 2 required
emailstringrequired“Same email used in start_signup.”codestringrequired“The 6-digit code from the email.”
- buy_planon 2 other servers
“Upgrade, renew or switch the signed-in user's plan without the website.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs, 1 required
planstringrequired“Plan to buy.”billingstring“monthly, or annual (2 months free).”payment_methodstring“'card' (monthly renews automatically), 'wallet' (Apple Pay / Google Pay / Cash App, one-time) or 'crypto' (one-time).”crypto_assetstring or null“Crypto only, e.g.”user_accepted_termsboolean“True ONLY after showing the user the key terms and getting an explicit yes for this purchase.”
- check_paymenton 12 other servers
“Has the payment arrived and is the plan active?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
order_idstring or null“Crypto order_id from buy_plan/confirm_signup.”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-26.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 97% of 70
- Tools with a description
- 100% of 27
- Typical description length
- 424 characters
The tool set
Counted from the listing
- Tools
- 27
- Size of the list
- about 14,296 tokens for an agent to load (characters ÷ 4)
- Naming
- 27 of 27 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 27 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-10-26 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://capitalsnitch.com/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"insider-trading": {
"url": "https://capitalsnitch.com/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"insider-trading": {
"type": "http",
"url": "https://capitalsnitch.com/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"insider-trading","type":"http","url":"https://capitalsnitch.com/mcp"}'Claude Code
claude mcp add --transport http insider-trading https://capitalsnitch.com/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"insider-trading": {
"type": "streamableHttp",
"url": "https://capitalsnitch.com/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"insider-trading": {
"httpUrl": "https://capitalsnitch.com/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.insider-trading] url = "https://capitalsnitch.com/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"insider-trading": {
"url": "https://capitalsnitch.com/mcp"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://capitalsnitch.com/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
Does the registry listing match what we found?
Feature #6The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint capitalsnitch.com/mcp | Session opened | matches | our test · 2026-10-26 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-10-26 |
Choosing
Record checks
Public records · not a safety rating1 of 2 record checks met · 7 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- Not metSource repository link opensThe registry entry gives no repository link.
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-26. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards
Common questions about com.capitalsnitch/insider-trading
Answered from the data aboveWho publishes com.capitalsnitch/insider-trading?
The registry ties the namespace com.capitalsnitch to the domain capitalsnitch.com; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.
Does com.capitalsnitch/insider-trading need an API key or sign-in?
It opened a session without any credential on 2026-10-26. The registry entry declares no required credential; no declaration is not a guarantee.
Has com.capitalsnitch/insider-trading been security tested?
Partly. 4 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: exercised
- Fake assistant turns: exercised
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: not applicable
4 exercised11 not run (reason given)3 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 12Hidden content
audience-hidingChecks resources that hide content from the user.exercised - 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable
Source: our own test, 2026-10-26, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 1,441 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 27 tools, 2 resources, 3 prompts.
- 6,959 msFinished: 4 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “com.capitalsnitch/insider-trading: MCP server record.” Data checked 2026-10-26. https://protocolprobe.com/mcp/servers/com.capitalsnitch/insider-trading
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/com.capitalsnitch/insider-trading)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.
Write to hello@protocolprobe.com · corrections log · methodology