_ registry / mcp streamable-http · checked 6h ago

edgar-insider-signals

https://mcp.tradestarinsider.com

Registry code: f753d6047e0bfc3e

api record

Read-only SEC EDGAR insider-buy signals. Every record is Rule-2-gated: each figure traces to a parsed Form-4 field and carries its source filing_url. Use these tools to surface open-market insider purchases (SEC code P), cluster buys, and per-filing detail. No figure is estimated.

endpoint
https://mcp.tradestarinsider.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing
karma
0 · newcomer
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
208ms

last good check

priced tools
0

of 12 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ used through this hub 30 days

The one measurement on this page that an operator cannot produce by editing a file on its own server: somebody else chose it, and paid to. Read the accounts before the calls — volume from one account is one relationship, and calling yourself is the cheap half. Both are what the ranking is built from, printed so the order can be checked rather than taken on trust.

accounts
0

distinct, expensive to fake

calls served
0

successful, last 30 days

_ what it can do 12 tools
12 never probed 0 of 12 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • insider_filing_lookup unknown never probed

    The single Rule-2 record for one SEC filing accession, with its filing_url. Returns an error if no gated filing matches the accession.

    mcp-tool

    {
  "type": "object",
  "required": [
    "accession"
  ],
  "properties": {
    "accession": {
      "type": "string",
      "description": "SEC filing accession, e.g. 0001493152-26-040454"
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • insider_signals_today unknown never probed

    Rule-2 insider-buy signals filed today (SEC code P open-market purchases). Returns the newest 25 by default (set `limit`; page with `offset`); the response's `total_matched` reports the full count. Optional `days`/`ticker` filters. Each record carries its source filing_url.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "days": {
      "type": "integer",
      "description": "Only rows filed within the last N days (relative to today)."
    },
    "limit": {
      "type": "integer",
      "description": "Max rows to return (default 25, newest first). Page with offset; the response's total_matched shows the full count. limit<=0 = no cap."
    },
    "offset": {
      "type": "integer",
      "description": "Rows to skip before this page (pagination). Default 0."
    },
    "ticker": {
      "type": "string",
      "description": "Case-insensitive exact ticker filter, e.g. DKS."
    }
  },
  "additionalProperties": false
}
    arguments 23 lines
  • insider_signals_by_ticker unknown never probed

    All Rule-2 insider-buy signals for one ticker (case-insensitive). Returns the newest 25 by default (set `limit`; page with `offset`; optional `days`); `total_matched` reports the full count. Each record carries its source filing_url.

    mcp-tool

    {
  "type": "object",
  "required": [
    "ticker"
  ],
  "properties": {
    "days": {
      "type": "integer",
      "description": "Only rows filed within the last N days (relative to today)."
    },
    "limit": {
      "type": "integer",
      "description": "Max rows to return (default 25, newest first). Page with offset; the response's total_matched shows the full count. limit<=0 = no cap."
    },
    "offset": {
      "type": "integer",
      "description": "Rows to skip before this page (pagination). Default 0."
    },
    "ticker": {
      "type": "string",
      "description": "Ticker symbol (case-insensitive), e.g. DKS"
    }
  },
  "additionalProperties": false
}
    arguments 25 lines
  • insider_signals_by_date_range unknown never probed

    Rule-2 insider-buy signals filed within an inclusive ISO date range. Returns the newest 25 by default (set `limit`; page with `offset`; optional `days`/`ticker`); `total_matched` reports the full count. Each record carries its source filing_url.

    mcp-tool

    {
  "type": "object",
  "required": [
    "start",
    "end"
  ],
  "properties": {
    "end": {
      "type": "string",
      "format": "date",
      "description": "Inclusive end date, ISO YYYY-MM-DD"
    },
    "days": {
      "type": "integer",
      "description": "Only rows filed within the last N days (relative to today)."
    },
    "limit": {
      "type": "integer",
      "description": "Max rows to return (default 25, newest first). Page with offset; the response's total_matched shows the full count. limit<=0 = no cap."
    },
    "start": {
      "type": "string",
      "format": "date",
      "description": "Inclusive start date, ISO YYYY-MM-DD"
    },
    "offset": {
      "type": "integer",
      "description": "Rows to skip before this page (pagination). Default 0."
    },
    "ticker": {
      "type": "string",
      "description": "Case-insensitive exact ticker filter, e.g. DKS."
    }
  },
  "additionalProperties": false
}
    arguments 36 lines
  • insider_cluster_buys unknown never probed

    Rule-2 cluster buys only (>=2 insiders buying the same issuer in-window) — the highest-signal subset. Each row carries `uniform_price_cluster`: true when >=3 distinct insiders bought at the IDENTICAL price on the same filed_date for the same issuer — the fingerprint of an offering/conversion (one administered price), NOT independent open-market conviction. Note Form-4 code P covers open-market purchases AND some offering/conversion purchases filed under P; this flag marks the latter. Genuine clusters rank ABOVE uniform-price ones. Returns the newest 25 by default (set `limit`; page with `offset`; optional `days`/`ticker`); `total_matched` reports the full count. Each record carries its source filing_url.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "days": {
      "type": "integer",
      "description": "Only rows filed within the last N days (relative to today)."
    },
    "limit": {
      "type": "integer",
      "description": "Max rows to return (default 25, newest first). Page with offset; the response's total_matched shows the full count. limit<=0 = no cap."
    },
    "offset": {
      "type": "integer",
      "description": "Rows to skip before this page (pagination). Default 0."
    },
    "ticker": {
      "type": "string",
      "description": "Case-insensitive exact ticker filter, e.g. DKS."
    }
  },
  "additionalProperties": false
}
    arguments 23 lines
  • federal_awards_recent unknown never probed

    Recently signed U.S. federal new awards from USAspending.gov, newest first. Returns the newest 25 by default (set `limit`; page with `offset`); `total_matched` reports the full count. Optional min_amount (USD floor) and `days` (last-N-days window). Every award carries its source award_url; awards without a source link are dropped and never returned.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "days": {
      "type": "integer",
      "description": "Only awards signed within the last N days."
    },
    "limit": {
      "type": "integer",
      "description": "Max rows to return (default 25, newest first). Page with offset; the response's total_matched shows the full count. limit<=0 = no cap."
    },
    "offset": {
      "type": "integer",
      "description": "Rows to skip before this page (pagination). Default 0."
    },
    "min_amount": {
      "type": "number",
      "description": "Only awards at or above this USD amount"
    }
  },
  "additionalProperties": false
}
    arguments 23 lines
  • activist_stakes_recent unknown never probed

    Recent activist Schedule 13D / 13D-A filings on US-listed companies, newest first then by stated-intent strength (control/take-private > board/proxy > strategic/value, or none stated). Returns the newest 25 by default (set `limit`; page with `offset`); `total_matched` reports the full count. Optional min_percent (percent-of-class floor), ticker, and `days` (last-N-days window). Every stake carries its source filing_url; filings without a source link are dropped.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "days": {
      "type": "integer",
      "description": "Only stakes filed within the last N days."
    },
    "limit": {
      "type": "integer",
      "description": "Max rows to return (default 25, newest first). Page with offset; the response's total_matched shows the full count. limit<=0 = no cap."
    },
    "offset": {
      "type": "integer",
      "description": "Rows to skip before this page (pagination). Default 0."
    },
    "ticker": {
      "type": "string",
      "description": "Filter to one subject ticker (case-insensitive), e.g. DH"
    },
    "min_percent": {
      "type": "number",
      "description": "Only stakes at or above this percent-of-class"
    }
  },
  "additionalProperties": false
}
    arguments 27 lines
  • fund_position_changes unknown never probed

    What large institutional filers CHANGED quarter-over-quarter in their SEC 13F-HR holdings (opened / added / trimmed / exited a position) — the delta is the product; the raw snapshot is only the input. Every row carries as_of_quarter_end, filed_date and lag_days (values are up to ~45 days stale), value_usd in whole dollars, cusip + issuer_name, and its source filing_url. ticker is null (no authoritative free CUSIP->ticker source; never guessed). A missing prior quarter is the explicit state 'first_filing_on_record', not 'everything new'. Covers LONG US 13(f)-listed positions only — no shorts, non-US, or options. UNIVERSE: the fifty largest 13F filers by reported value as of the latest quarter, re-ranked quarterly. Because it is ranked BY REPORTED VALUE, the head is the biggest asset managers (BlackRock, Vanguard, State Street, Fidelity, ...) whose quarter-over-quarter changes largely reflect index rebalancing, not conviction; the feed reports WHAT WAS FILED, not what it means, and does not tag any manager active or passive (that would be inference). Coverage is PER SEC CIK, not per brand: a firm filing under several CIKs appears as several entries, and when a filer's 13F moves to a new CIK, historical coverage stays attached to the CIK that filed it. This is a convenience/completeness view of public data, NOT a trading edge. Returns the newest 25 by default (set `limit`; page with `offset`); `total_matched` reports the full count. Optional filer, change_type, min_value_usd, and `days` (last-N-days window).

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "days": {
      "type": "integer",
      "description": "Only changes filed within the last N days."
    },
    "filer": {
      "type": "string",
      "description": "Filter to one fund by name substring (case-insensitive, e.g. 'Berkshire') or exact filer CIK"
    },
    "limit": {
      "type": "integer",
      "description": "Max rows to return (default 25, newest first). Page with offset; the response's total_matched shows the full count. limit<=0 = no cap."
    },
    "offset": {
      "type": "integer",
      "description": "Rows to skip before this page (pagination). Default 0."
    },
    "change_type": {
      "enum": [
        "new_position",
        "added",
        "trimmed",
        "exited",
        "no_prior_quarter"
      ],
      "type": "string",
      "description": "Only this kind of quarter-over-quarter change"
    },
    "min_value_usd": {
      "type": "number",
      "description": "Only positions at or above this current value in WHOLE US dollars"
    }
  },
  "additionalProperties": false
}
    arguments 38 lines
  • verify_insider_purchase unknown never probed

    Check a claim about an insider open-market buy (ticker/issuer, person, amount, timeframe) against the filed record. Returns status=confirmed with the source filing(s) + link; not_found; partial (same insider/company but value/date differs, itemised claimed-vs-filed); out_of_scope (sales/options/grants aren't covered); or out_of_coverage (outside the collected window). Every response states the coverage window checked. Rule-2: no estimates, no unlabelled partial matches — absence is reported as absence, never guessed.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "end": {
      "type": "string",
      "format": "date",
      "description": "Window end (ISO) if the claim is a range"
    },
    "date": {
      "type": "string",
      "format": "date",
      "description": "Claimed date, ISO YYYY-MM-DD (matched ±3 filing days)"
    },
    "start": {
      "type": "string",
      "format": "date",
      "description": "Window start (ISO) if the claim is a range"
    },
    "person": {
      "type": "string",
      "description": "Insider name in any order, e.g. 'Alfonso de Angoitia'"
    },
    "shares": {
      "type": "number",
      "description": "Claimed share count"
    },
    "ticker": {
      "type": "string",
      "description": "Issuer ticker (case-insensitive), e.g. CAVA"
    },
    "txn_type": {
      "type": "string",
      "description": "Optional; only open-market buys are covered — sale/option/grant returns out_of_scope"
    },
    "amount_usd": {
      "type": "number",
      "description": "Claimed purchase value in USD (matched ±5% or ±$1)"
    },
    "issuer_name": {
      "type": "string",
      "description": "Issuer/company name (use if you don't have the ticker)"
    }
  },
  "additionalProperties": false
}
    arguments 46 lines
  • verify_activist_13d unknown never probed

    Check a claim about an activist stake (ticker/subject, filer, percent-of-class, stated intent, timeframe) against the filed Schedule 13D/13D-A record. Returns status=confirmed with the source filing(s) + link; not_found; partial (same filer/subject but percent/intent/date differs, itemised claimed-vs-filed); out_of_scope (passive 13G isn't covered); or out_of_coverage (outside the collected window). Every response states the coverage window checked. Rule-2: no estimates — absence is reported as absence, never guessed.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "end": {
      "type": "string",
      "format": "date",
      "description": "Window end (ISO) if the claim is a range"
    },
    "date": {
      "type": "string",
      "format": "date",
      "description": "Claimed filed date, ISO YYYY-MM-DD (matched ±3 filing days)"
    },
    "start": {
      "type": "string",
      "format": "date",
      "description": "Window start (ISO) if the claim is a range"
    },
    "intent": {
      "enum": [
        "I1",
        "I2",
        "I3"
      ],
      "type": "string",
      "description": "Optional pre-registered intent: I1 control/take-private, I2 board/proxy, I3 strategic/value"
    },
    "ticker": {
      "type": "string",
      "description": "Subject-company ticker (case-insensitive), e.g. DH"
    },
    "form_type": {
      "type": "string",
      "description": "Optional; only activist 13D/13D-A is covered — a passive 13G returns out_of_scope"
    },
    "filer_name": {
      "type": "string",
      "description": "Activist filer name in any order, e.g. 'Elliott Management'"
    },
    "subject_name": {
      "type": "string",
      "description": "Subject/target company name (use if you don't have the ticker)"
    },
    "percent_of_class": {
      "type": "number",
      "description": "Claimed percent-of-class owned (matched ±0.5 percentage points)"
    }
  },
  "additionalProperties": false
}
    arguments 51 lines
  • verify_8k_event unknown never probed

    Check a claim that a registrant (cik/company/accession) filed an 8-K carrying specific SEC item code(s) in a timeframe, against the filed record. Returns status=confirmed with the source filing(s) + link; not_found; partial (same registrant/filing but the claimed item(s) aren't carried, or the date differs — itemised claimed-vs-filed); out_of_scope (claims about the body's meaning/materiality aren't covered — the filing is never paraphrased); or out_of_coverage. Every response states the coverage window checked. Rule-2: item codes are the SEC controlled vocabulary parsed from the filing — never inferred from prose.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "cik": {
      "type": "string",
      "description": "Registrant CIK (leading zeros ignored), e.g. 320193"
    },
    "end": {
      "type": "string",
      "format": "date",
      "description": "Window end (ISO) if the claim is a range"
    },
    "date": {
      "type": "string",
      "format": "date",
      "description": "Claimed filing date, ISO YYYY-MM-DD (matched ±3 filing days)"
    },
    "items": {
      "type": "string",
      "description": "Claimed SEC 8-K item code(s), comma-separated (e.g. '5.02' or '1.01,9.01') — checked against the filing"
    },
    "start": {
      "type": "string",
      "format": "date",
      "description": "Window start (ISO) if the claim is a range"
    },
    "accession": {
      "type": "string",
      "description": "SEC filing accession, e.g. 0001193125-26-389400"
    },
    "company_name": {
      "type": "string",
      "description": "Registrant name substring (case-insensitive), e.g. 'Apple'"
    }
  },
  "additionalProperties": false
}
    arguments 38 lines
  • verify_13f_holding unknown never probed

    Check whether a fund (filer name/CIK) HELD an issuer (issuer_name or cusip) as of a quarter, against the filed 13F-HR record. Returns status=held with the source filing(s) + link; not_held (the fund reported the position EXITED that quarter — a filed 'no', distinct from not_found); not_found (no such row in the covered window); or out_of_coverage (the claimed quarter is outside the collected as-of window). Every response states the coverage window checked. Rule-2: LONG US 13(f) positions only, values are as-of quarter-end and up to ~45 days stale, and ticker is never guessed — match on issuer_name or cusip.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "end": {
      "type": "string",
      "format": "date",
      "description": "Quarter-window end (ISO) if the claim spans quarters"
    },
    "cusip": {
      "type": "string",
      "description": "9-char CUSIP of the held security — give this or issuer_name. (ticker is never accepted: 13F carries no authoritative ticker)"
    },
    "filer": {
      "type": "string",
      "description": "Fund/institution name substring (case-insensitive, e.g. 'Berkshire') or exact filer CIK — REQUIRED"
    },
    "start": {
      "type": "string",
      "format": "date",
      "description": "Quarter-window start (ISO) if the claim spans quarters"
    },
    "quarter": {
      "type": "string",
      "format": "date",
      "description": "As-of quarter-end the claim is about, ISO YYYY-MM-DD (e.g. '2026-06-30')"
    },
    "issuer_name": {
      "type": "string",
      "description": "Held company/issuer name (e.g. 'Apple') — give this or cusip"
    }
  },
  "additionalProperties": false
}
    arguments 34 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/f753d6047e0bfc3e/badge.svg)](https://brick.blue/agent/f753d6047e0bfc3e)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Own the domain? Prove it and the listing carries a verified badge here too: passport.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.