Compound Interesting — market intelligence
REMOTE · API.COMPOUNDINTEREST.ING · SCANNED SEP 26
Source-backed US market signals: insider filings, Congress trades, institutions, consensus.
Available components
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 Security46
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 16 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- 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 Usability77
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1496 tokens (~93/item across 16 items; 16 tools + 0 resources), lean.Pass
- 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 Coverage99
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 97% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 17 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
How do I install the Compound Interesting — market intelligence MCP server?
Compound Interesting — market intelligence is a hosted endpoint at https://api.compoundinterest.ing/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 · api.compoundinterest.ing
claude mcp add --transport http ing-compoundinterest-market-intelligence 'https://api.compoundinterest.ing/mcp'
{
"mcpServers": {
"ing-compoundinterest-market-intelligence": {
"url": "https://api.compoundinterest.ing/mcp"
}
}
} {
"servers": {
"ing-compoundinterest-market-intelligence": {
"type": "http",
"url": "https://api.compoundinterest.ing/mcp"
}
}
} [mcp_servers.ing-compoundinterest-market-intelligence] url = "https://api.compoundinterest.ing/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"ing-compoundinterest-market-intelligence": {
"type": "remote",
"url": "https://api.compoundinterest.ing/mcp",
"enabled": true
}
}
} openclaw mcp add ing-compoundinterest-market-intelligence --url 'https://api.compoundinterest.ing/mcp' --transport streamable-http
mcp_servers:
ing-compoundinterest-market-intelligence:
url: "https://api.compoundinterest.ing/mcp" {
"McpServers": {
"ing-compoundinterest-market-intelligence": {
"Transport": "http",
"Url": "https://api.compoundinterest.ing/mcp"
}
}
} assistant mcp add ing-compoundinterest-market-intelligence -t streamable-http -u 'https://api.compoundinterest.ing/mcp'
{
"mcpServers": {
"ing-compoundinterest-market-intelligence": {
"type": "http",
"url": "https://api.compoundinterest.ing/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
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.
- 26 Sept 26 0
- Tool “get_evidence” rewrote its description, which is the text the model reads security
- Tool “get_monthly_activity” rewrote its description, which is the text the model reads security
- Tool “get_signal” rewrote its description, which is the text the model reads security
- Tool “list_congress_trades” rewrote its description, which is the text the model reads security
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 20 Sept 26 0
- New tool “get_monthly_activity” functional
- “screen” reworded the description of “rating” cosmetic
- “screen” reworded the description of “sort” cosmetic
- 4 Sept 26 0
- Stability: 0.97 → pass security
- 3 Sept 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.
- 1 Sept 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.
- 30 Aug 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.
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
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 26 Sept 2026 · Probed https://api.compoundinterest.ing/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=compoundinterest.ing | CN=WE1,O=Google Trust Services,C=US | 5 Aug 2026 | 3 Nov 2026 | ECDSA 256 | ECDSA-SHA256 | 8c3298edd2f1e8af1365bf95571eaa79 |
| SANs: compoundinterest.ing, api.compoundinterest.ing, *.api.compoundinterest.ing | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.compoundinterest.ing. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ing. | present | 27256 | 8 | Verified |
| compoundinterest.ing. | 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 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.compoundinterest.ing/mcp | Verified | 200 | |
| http (plaintext) | http://api.compoundinterest.ing/mcp | Inconclusive | 405 |
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 →
get_composite Composite signal for a ticker ~66
Everything the platform knows about one ticker in a single record: the cross-signal consensus, each contributing dimension with its direction and provenance, and risk flags. Start here for any question about a specific company.
| Name | Type | Req | Description |
|---|---|---|---|
| ticker | string | yes | Ticker symbol, e.g. AAPL. |
No output schema declared.
No examples provided.
get_consensus Cross-signal consensus for one ticker ~58
Whether the independent actors this platform tracks — insiders, Congress, institutions, the model — agree on one ticker, with the per-dimension breakdown that produced the verdict.
| Name | Type | Req | Description |
|---|---|---|---|
| ticker | string | yes | Ticker symbol, e.g. AAPL. |
No output schema declared.
No examples provided.
get_demo_composite Composite signal for a demo ticker (no key required) ~57
A single fixed demo ticker, callable without an API key, so the data shape can be inspected before signing up. Returns only the demo ticker regardless of input. For real tickers use get_composite, which requires a free key.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_equity_perp Overnight positioning for one ticker ~82
Funding and open interest for a single name on the 24/7 perpetual venue. Most tickers are NOT listed there — only about 51 of ~5,400 — and a 'not listed' answer means no venue coverage, never that positioning is flat or zero.
| Name | Type | Req | Description |
|---|---|---|---|
| ticker | string | yes | Ticker symbol, e.g. AAPL. |
No output schema declared.
No examples provided.
get_evidence Source documents behind a ticker's signals ~103
The primary documents a ticker's signals were derived from — insider Form 4s, institutional holdings and macro series, each with the filing it came from. Use this to cite a claim rather than assert it. Paid keys only, and slower than the other tools because it is computed on demand. Congressional trades are not included: use list_congress_trades, which works on every key.
| Name | Type | Req | Description |
|---|---|---|---|
| ticker | string | yes | Ticker symbol, e.g. AAPL. |
No output schema declared.
No examples provided.
get_historic_moves How big a move is normal for this ticker ~106
The historical distribution of 5-day and 1-month returns for a ticker, sampled over the last 5 years: mean, standard deviation, percentiles, a histogram, and the worst drawdowns with their dates. Use it to say whether a move is unusual FOR THIS NAME rather than in the abstract. Every number is a fraction: 0.0821 means 8.21%.
| Name | Type | Req | Description |
|---|---|---|---|
| ticker | string | yes | Ticker symbol, e.g. AAPL. |
No output schema declared.
No examples provided.
get_house_rating House rating for a ticker ~58
The platform's own buy/hold/sell rating for a ticker, with the reasoning behind it. A judgement about the stock, not a recommendation to any reader.
| Name | Type | Req | Description |
|---|---|---|---|
| ticker | string | yes | Ticker symbol, e.g. AAPL. |
No output schema declared.
No examples provided.
get_monthly_activity Current-month insider or Congressional activity ~111
Rank ticker activity aggregated from available published filings by transaction date for the current UTC month through today. Includes coverage metadata and unknown-value counts; this is not total market activity. Congress: 10 names on every customer key. Insiders: free keys receive up to 10 names, paid keys up to 20.
| Name | Type | Req | Description |
|---|---|---|---|
| kind | string | yes | Which published filing activity to aggregate. |
| month | string | – | Optional YYYY-MM; only the current UTC month is supported. Defaults to the current UTC month. |
No output schema declared.
No examples provided.
get_signal Market-level signal ~78
A whole-market gauge rather than a per-company one. 'macro' is the market-regime read, 'energy' the macro energy balance, 'crypto' crypto positioning and funding, 'rate_expectations' the market-implied path for policy rates. Use these for the backdrop a single name is trading against.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | – |
No output schema declared.
No examples provided.
list_congress_trades Recent Congressional trades ~115
Disclosed House and Senate trades, newest first, each linked to its disclosure. Committee overlap is reported as oversight, never as an accusation. Up to 20 rows per call on every customer key; page with next_cursor.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from a previous call. |
| limit | integer | – | How many trades to return. |
| since | string | – | ISO date; only records on or after it. |
| ticker | string | – | Restrict to one ticker, e.g. TSLA. |
No output schema declared.
No examples provided.
list_equity_perp Overnight positioning on US names (24/7 perps) ~105
Funding rate and open interest for the ~51 US single names listed on a 24/7 perpetual futures venue, ranked by notional. This is the ONLY source here that moves outside US market hours, so it is what to check overnight and at weekends. High positive funding means longs are paying to hold — crowded, squeeze-fragile. The mark price is a venue mark, NOT the stock price.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many names to return. |
No output schema declared.
No examples provided.
list_insider_trades Recent insider trades ~91
Corporate insider buys and sells from SEC filings, newest first, each linked to the filing it came from.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from a previous call. |
| limit | integer | – | How many trades to return. |
| since | string | – | ISO date; only records on or after it. |
| ticker | string | – | Restrict to one ticker, e.g. TSLA. |
No output schema declared.
No examples provided.
list_positioning Institutional and derivative positioning ~95
How large holders are positioned, newest first. Net figures can reflect hedges and cannot be read as a directional view on their own.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | next_cursor from a previous call. |
| limit | integer | – | How many records to return. |
| since | string | – | ISO date; only records on or after it. |
| ticker | string | – | Restrict to one ticker, e.g. TSLA. |
No output schema declared.
No examples provided.
rank_consensus Tickers ranked by consensus strength ~93
The names where independent actors agree most strongly, ranked. Use this to find candidates rather than to check one you already have in mind.
| Name | Type | Req | Description |
|---|---|---|---|
| direction | string | – | Restrict to one consensus direction. |
| limit | integer | – | How many rows to return. |
| min_agreement | number | – | Minimum agreement score, 0-1. |
| min_signals | integer | – | Minimum number of dimensions that voted. |
No output schema declared.
No examples provided.
screen Screen the universe ~198
Filter the whole equity universe and return matching tickers with their scores. The bulk discovery tool: use it for questions of the form 'which companies have X'. To rank by cross-signal agreement instead, use rank_consensus.
| Name | Type | Req | Description |
|---|---|---|---|
| flagged | boolean | – | Only entities carrying at least one risk flag. |
| limit | integer | – | How many rows to return. |
| min_completeness | number | – | Minimum data completeness, 0-1. |
| min_confidence | number | – | Minimum model confidence, 0-1. |
| order | string | – | Sort direction. |
| rating | string | – | Restrict to one house rating, e.g. buy, hold, sell. Requires a paid key. |
| sector | string | – | Restrict to one sector. |
| sort | string | – | Sort column. Defaults to confidence. house_rating_confidence requires a paid key. |
| state | string | – | Restrict to one overall state. |
No output schema declared.
No examples provided.
search_tickers Find a ticker by name or symbol ~49
Resolve a company name or partial symbol to tickers the platform covers. Use this first when the user names a company rather than a symbol.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | Company name or partial symbol. |
No output schema declared.
No examples provided.
What is the Compound Interesting — market intelligence MCP server?
Compound Interesting — market intelligence is an MCP server listed in the public MCP registry as ing.compoundinterest/market-intelligence. Source-backed US market signals: insider filings, Congress trades, institutions, consensus. This page covers its hosted endpoint (https://api.compoundinterest.ing/mcp).
Is the Compound Interesting — market intelligence MCP server safe to use?
Compound Interesting — market intelligence scores 74 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 Compound Interesting — market intelligence MCP server expose?
Compound Interesting — market intelligence exposes 16 tools: get_composite, get_demo_composite, get_evidence, get_house_rating, get_consensus, and 11 more. Their descriptions and schemas cost roughly 1,465 tokens of context every time the server is loaded.
Does the Compound Interesting — market intelligence MCP server require authentication?
No. We connected to Compound Interesting — market intelligence without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Compound Interesting — market intelligence MCP server still maintained?
Compound Interesting — market intelligence is still listed as active in the MCP registry. We last reached this channel on 26 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.