Coldpine: Congressional Stock Disclosures
REMOTE · COLDPINE.IO
Read-only U.S. congressional stock trade disclosures (STOCK Act filings), parsed and source-linked.
Available components
Last scanned (1 hour ago)
Scores higher than 93% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Finance and Payments
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. How we score → Why this is hard to score →
Endpoint Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability67
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 3015 tokens (~274/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Oct 26 0
- Stability: 0.97 → pass security
- 19 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Oct 26 +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.
- 13 Oct 26 +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.
- 12 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 67 to 73. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Oct 26 +2
No change was recorded against any check on this day. Stability & Change Management went from 47 to 63. That category is still filling its 30-day observation window: 14 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.
- 4 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://coldpine.io/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=coldpine.io | CN=YR2,O=Let's Encrypt,C=US | 17 Sept 2026 | 16 Dec 2026 | RSA 2048 | SHA256-RSA | 67370ab974f89d6428a15bcc1e14b6009dc |
| SANs: coldpine.io | ||||||
| CN=YR2,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | 4ebd24947e24d394802d84a52fd5b319 |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of coldpine.io. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| io. | present | 38690 | 8 | Verified |
| coldpine.io. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://coldpine.io/api/mcp | Verified | 200 | |
| http (plaintext) | http://coldpine.io/api/mcp | HTTPS enforced | 308 | https://coldpine.io/api/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
cluster_trades Cluster buys and sells ~354
Stocks that several members of Congress traded in the same direction inside a rolling window (Coldpine's cluster detection, same definition as the bot). Returns ticker, direction, distinct member count, trade count, date span, summed disclosed amount range and the member names. Same data as coldpine.io/research/biggest-cluster-buys-in-congress. Use it for 'what are several members buying (or selling) at once'; for everyone who ever traded one given stock use get_stock instead. The window counts back from the most recent trade date on record, not from a date you choose, and clusters come back largest first by distinct members. A person is counted once per cluster however many trades they made. Overlap in timing is a description of the filings, not evidence of coordination. Access: needs the agent token from a free Coldpine account, sent as 'Authorization: Bearer <token>'; without it the call returns setup steps instead of data. Read-only, cached for up to an hour.
| Name | Type | Req | Description |
|---|---|---|---|
| direction | string | – | Which side to cluster: 'purchase' for stocks several members bought, 'sale' for stocks several sold. Default 'purchase'. One direction per call. |
| limit | integer | – | Maximum clusters to return, 1 to 50. Default 10. |
| min_members | integer | – | Smallest number of distinct members that makes a cluster, 2 to 20. Default 3. Raise it to keep only the broadest overlaps. |
| window_days | integer | – | Length of the look-back window in days, 1 to 365, ending at the latest trade date on record. Default 90. A longer window finds more and larger clusters. |
No output schema declared.
No examples provided.
congress_leaderboard Most active traders in Congress ~325
Members of Congress ranked by disclosed trading activity: trade count, disclosed dollar volume (sum of amount-range midpoints), average trade size, or disclosure speed. Optional chamber and party filters. Same data as coldpine.io/leaderboard. Use it for 'who trades the most in Congress' style questions. Each row has the member, chamber, party, state, trade count, disclosed volume, average trade size, average days from trade to disclosure and the member's coldpine.io page; total_members is the count after filters. This ranks activity only. For returns against the S&P 500 use members_vs_market, and for late filing use stock_act_compliance. Access: needs the agent token from a free Coldpine account, sent as 'Authorization: Bearer <token>'; without it the call returns setup steps instead of data. Read-only, cached for up to an hour.
| Name | Type | Req | Description |
|---|---|---|---|
| chamber | string | – | Restrict to one chamber. Omit for both. |
| limit | integer | – | Members to return, 1 to 100. Default 25. |
| party | string | – | Restrict to one party: 'D', 'R' or 'I' (the words Democrat, Republican, Independent are accepted too). Omit for all. |
| sort | string | – | Ranking: 'trades' = most disclosed trades, 'volume' = largest disclosed dollar volume (amount-range midpoints), 'avg_size' = largest average trade, 'speed' = shortest average gap between trade and di… |
No output schema declared.
No examples provided.
get_filing One Periodic Transaction Report, parsed ~204
A single STOCK Act Periodic Transaction Report: who filed it and when, the roll-up (trade count, buy/sell split, tickers, amount range, longest disclosure lag, trades past the 45-day window, trades by spouse or dependent child), every trade it disclosed, a link to the original government document, and the one sample scored trade the public page shows. Use it after whats_new, list_recent_filings or get_member has given you a filing id and the question is about what that one report contained. Returns a not-found error for an unknown id. Access: needs the agent token from a free Coldpine account, sent as 'Authorization: Bearer <token>'; without it the call returns setup steps instead of data. Read-only, cached for up to an hour.
| Name | Type | Req | Description |
|---|---|---|---|
| filing_id | integer | yes | Coldpine filing id (the trailing number in any coldpine.io/filings URL, or from list_recent_filings / get_member). |
No output schema declared.
No examples provided.
get_member Member profile and recent disclosed trades ~191
One member of Congress: profile, aggregate trading stats (counts, volume range, average disclosure lag, most-traded tickers), the 20 most recent disclosed trades with links to the original government filing, the member's 5 most recent Periodic Transaction Reports, and the one sample scored trade the public page shows. Use it for 'what has this member been trading'. Get the member_id from search_members first. For more than 20 trades, page list_transactions with the same member_id. Returns a not-found error for an unknown id. Access: needs the agent token from a free Coldpine account, sent as 'Authorization: Bearer <token>'; without it the call returns setup steps instead of data. Read-only, cached for up to an hour.
| Name | Type | Req | Description |
|---|---|---|---|
| member_id | integer | yes | Coldpine member id (from search_members or any coldpine.io/politicians URL, the trailing number). |
No output schema declared.
No examples provided.
get_stock Congressional trading in one stock ~166
Every member of Congress who disclosed trading a ticker: totals, buy/sell split, disclosed volume range, first and last trade dates, the members who traded it most, the 20 most recent disclosed trades with source-filing links, and the one sample scored trade the public page shows. Use it for 'who in Congress trades this stock'. For the full trade history of a ticker, page list_transactions with the same ticker; for stocks several members bought or sold together, use cluster_trades. Returns a not-found error when no member has disclosed a trade in the symbol. Access: no key or account needed. Read-only, cached for up to an hour.
| Name | Type | Req | Description |
|---|---|---|---|
| ticker | string | yes | Stock symbol, case-insensitive, e.g. NVDA. One symbol per call. |
No output schema declared.
No examples provided.
list_recent_filings Recent Periodic Transaction Reports ~233
The newest Periodic Transaction Reports (STOCK Act filings) with parsed trades, newest filed date first, 25 per page: member, chamber, filed date, trade count, buy/sell split, tickers, and how many trades were reported more than 45 days after the trade (late_45). Mirrors coldpine.io/filings. Use it to browse the archive of reports page by page; `coverage` in the response gives the total number of reports, members and the date span, so you know how many pages exist. For just the latest reports or polling by date, whats_new is lighter and needs no token; for the trades inside one report, pass its id to get_filing. Access: needs the agent token from a free Coldpine account, sent as 'Authorization: Bearer <token>'; without it the call returns setup steps instead of data. Read-only, cached for up to an hour.
| Name | Type | Req | Description |
|---|---|---|---|
| page | integer | – | Page number, 25 reports per page, 1 is the newest. Default 1. A page past the end returns an empty list. |
No output schema declared.
No examples provided.
list_transactions Disclosed trades, newest first ~323
Individual disclosed congressional stock trades, newest disclosure first. The paging tool: use it when get_member or get_stock's 20 most recent trades are not enough, or to walk the whole record. Filter by ticker, by member_id, by both (one member's trades in one stock), or by neither (every trade). Each row has the ticker and asset name, purchase/sale/exchange, trade date, disclosure date, days between them, whether that passed the 45-day STOCK Act window, the reported amount range, the owner (self, spouse, dependent child), the member, and a link to the original House Clerk PDF or Senate eFD filing. `total` is the full match count, so keep raising `offset` by `limit` until you reach it. Access: needs the agent token from a free Coldpine account, sent as 'Authorization: Bearer <token>'; without it the call returns setup steps instead of data. Read-only, cached for up to an hour.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Rows per page, 1 to 50. Default 25. |
| member_id | integer | – | Only trades by this member (id from search_members). Combine with ticker to narrow further. Omit for all members. |
| offset | integer | – | Rows to skip, for paging: 0 for the first page, then add `limit` each time. Default 0. |
| ticker | string | – | Only trades in this stock symbol, e.g. NVDA. Case-insensitive. Omit for all tickers. |
No output schema declared.
No examples provided.
members_vs_market Members' disclosed purchases vs the S&P 500 ~332
Per-member 90-day return on disclosed stock purchases versus the S&P 500 over the same windows (alpha), with the 30-day alpha and hit rate. Only members with at least min_trades priced purchases that have a full 90-day window. Most members do not beat the market; this is the measured record. Same data as coldpine.io/research/members-who-beat-the-market. Use it when the question is about performance; congress_leaderboard ranks activity and carries no returns. Rows come back highest 90-day alpha first, each with the number of purchases measured, the average 90-day return, the S&P 500 average over the same windows, the 90-day and 30-day alpha, the share of purchases that beat the index, and the member's page. The response states the method. These are measured past outcomes on disclosed purchases only (sales and trades younger than 90 days are excluded), not a forecast and not a reason to trade. Access: needs the agent token from a free Coldpine account, sent as 'Authorization: Bearer <token>'; without it the call returns setup steps instead of data. Read-only, cached for up to an hour.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Members to return, 1 to 300, highest 90-day alpha first. Default 50. |
| min_trades | integer | – | Smallest number of priced purchases a member needs to be included, 1 to 100. Default 5. Low values let one or two lucky trades top the list; raise it for a steadier record. |
No output schema declared.
No examples provided.
search_members Search members of Congress ~199
Find members of the U.S. House or Senate who have disclosed stock trades, by full or partial name. Start here whenever a question names a person: it returns the member_id that get_member and list_transactions take. Each match carries name, chamber, party, state, trade and filing counts, buy/sell split, the disclosed dollar volume range and the member's coldpine.io page. total_matches tells you when the list was cut by `limit`. To rank all members rather than look one up, use congress_leaderboard. Access: no key or account needed. Read-only, cached for up to an hour.
| Name | Type | Req | Description |
|---|---|---|---|
| chamber | string | – | Restrict matches to one chamber. Omit to search both. |
| limit | integer | – | Maximum matches to return, 1 to 25. Default 10. |
| query | string | yes | Part of the member's name, e.g. 'Pelosi' or 'Tuberville'. |
No output schema declared.
No examples provided.
stock_act_compliance STOCK Act disclosure lag and late filers ~363
How quickly Congress reports its trades against the STOCK Act's 45-day window: the site-wide summary (median lag, share late, House vs Senate) and the per-member board (trades dated, average and median lag, trades past 45 and 90 days, share late). Where a member has at least 5 priced purchases, the average pre-disclosure move of those purchases is given WITH the S&P 500 move over the same windows (avg_lag_excess); never quote one without the other. Same data as coldpine.io/research/congress-stock-act-late-filers. Use it for 'who files late' and 'how late is Congress overall'; the site-wide `summary` comes back on every call whatever the sort. For one member's lag on individual trades, read disclosure_lag_days in get_member or list_transactions. A late report is a fact about the filing date; it is not a finding of wrongdoing. Access: needs the agent token from a free Coldpine account, sent as 'Authorization: Bearer <token>'; without it the call returns setup steps instead of data. Read-only, cached for up to an hour.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Members to return, 1 to 250. Default 25. |
| sort | string | – | Ranking, always highest first: 'pct_late' = share of trades reported past 45 days, 'late_45' = count past 45 days, 'egregious_90' = count past 90 days, 'avg_lag' / 'median_lag' / 'max_lag' = days fro… |
No output schema declared.
No examples provided.
whats_new Latest congressional disclosures ~220
The newest STOCK Act Periodic Transaction Reports filed by members of Congress, newest first. Use this to answer 'what did Congress just disclose' or to poll for new filings: pass `since` (YYYY-MM-DD) to get only reports filed after that date. Returns one row per report: filing_id, filed_date, member name/id, chamber, party, state, trade count, buys, sells, distinct tickers, whether any trade was reported past the 45-day window, the top tickers, and the coldpine.io URL of the report and the member. Looks at the 100 most recent reports; for older ones page through list_recent_filings, and for the trades inside one report call get_filing. Access: no key or account needed. Read-only, cached for up to an hour.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many reports to return, 1 to 50. Default 25. |
| since | string | – | Only filings filed AFTER this date (YYYY-MM-DD). Omit for the latest 25. |
No output schema declared.
No examples provided.
How do I install the Coldpine: Congressional Stock Disclosures MCP server?
Coldpine: Congressional Stock Disclosures is a hosted endpoint at https://coldpine.io/api/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.
remote · coldpine.io
claude mcp add --transport http io-coldpine-congress-disclosures 'https://coldpine.io/api/mcp'
What is the Coldpine: Congressional Stock Disclosures MCP server?
Coldpine: Congressional Stock Disclosures is an MCP server listed in the public MCP registry as io.coldpine/congress-disclosures. Read-only U.S. congressional stock trade disclosures (STOCK Act filings), parsed and source-linked. This page covers its hosted endpoint (https://coldpine.io/api/mcp).
Is the Coldpine: Congressional Stock Disclosures MCP server safe to use?
Coldpine: Congressional Stock Disclosures scores 86 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 Coldpine: Congressional Stock Disclosures MCP server expose?
Coldpine: Congressional Stock Disclosures exposes 11 tools: whats_new, search_members, get_member, get_stock, list_transactions, and 6 more. Their descriptions and schemas cost roughly 2,910 tokens of context every time the server is loaded.
Does the Coldpine: Congressional Stock Disclosures MCP server require authentication?
No. We connected to Coldpine: Congressional Stock Disclosures without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Coldpine: Congressional Stock Disclosures MCP server still maintained?
Coldpine: Congressional Stock Disclosures is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.