Shingou
by shingou.io · remote · local (npm) · no sign-in to list tools · v0.3.2 · published by io.shingou
Hourly crypto news sentiment and typed market events, with sources on every signal.
4 tools: 4 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things0Claude Code: ask
- Only reads4Claude Code: allow: see these tools
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http sentiment https://api.shingou.io/mcp --header 'x-api-key: <your-x-api-key>'Tools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
4 tools
Only reads 4Claude Code: allow
get_eventsRecent classified market events for a symbol.Reads text others writeNo findings
Why it is in this group
- The name "get_events" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Recent classified market events for a symbol. Kill-switch trio: hack_exploit, regulation, delisting — the reference integrations stand aside for 24h after one. Report the event headline and source link, not just a risk flag.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_sentimentLatest news-sentiment signal per symbol (batch up to 50 in one call — one signal per asset per hour, so never poll faster than hourly).Reads text others writeNo findings
Why it is in this group
- The name "get_sentiment" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Latest news-sentiment signal per symbol (batch up to 50 in one call — one signal per asset per hour, so never poll faster than hourly). On the free plan, symbols outside BTC-USD/ETH-USD/SOL-USD are 24h delayed: check `timestamp` and disclose staleness.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_sentiment_historyPoint-in-time sentiment series for backtesting: `bucket` is the as-of time, no lookahead.Reads text others writeNo findings
Why it is in this group
- The name "get_sentiment_history" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Point-in-time sentiment series for backtesting: `bucket` is the as-of time, no lookahead. `from`/`to` are clamped to your plan's history window and to its per-request span, then echoed back — check them rather than assuming. `reconstructed: true` buckets were rebuilt from archival news, not live-collected; disclose the mix in any backtest.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_symbolsThe supported symbol universe with each symbol's free-plan freshness.No findings
Why it is in this group
- The name "get_symbols" says "get": a word for reading.
Description, as the server wrote it The supported symbol universe with each symbol's free-plan freshness. Static — costs no quota and needs no API key.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Oct 22, 2026, 15:09 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 0
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- none
- RFC 9728 protected resource metadata
- none
- Authorization servers
- none
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
Install
Pinned to version 0.3.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http sentiment https://api.shingou.io/mcp --header 'x-api-key: <your-x-api-key>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__sentiment__get_sentiment",
"mcp__sentiment__get_sentiment_history",
"mcp__sentiment__get_events",
"mcp__sentiment__get_symbols"
],
"ask": [],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as sentiment. Review it before you use it.
Capability tags behind 3 rules
- mcp__sentiment__get_sentiment untrusted-input
- mcp__sentiment__get_sentiment_history untrusted-input
- mcp__sentiment__get_events untrusted-input