Skip to content

Stelar Signals MCP server

io.github.StelarDigital/stelar-signals-mcpStelarDigitalstreamable-httpv1.1.3Scanned

Crypto market signals and portfolio telemetry. 6 tools pay-per-call in USDC, no API key.

12 tools: 11 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 11 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

11 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Stelar Signals MCP server can do

The Stelar Signals MCP server is published by the GitHub account StelarDigital. It has 12 tools. It can create or change data (11 tools: crypto_regime, crypto_sentiment, factcheck, pricecheck and 7 more), but cannot delete data. 1 tool only reads.

1 tool brings in text other people can write (summarize); 1 tool can send data out of your system (summarize).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 16, 2026, version 1.1.3.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

12 tools

Changes things 11Claude Code: ask
  • crypto_regimeMarket regime (chop / trend_up / trend_down / high_vol) for a major crypto pair, computed from live 24h market structure by a production-grade classifier.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Market regime (chop / trend_up / trend_down / high_vol) for a major crypto pair, computed from live 24h market structure by a production-grade classifier. Returns a grid_suitability verdict (good/poor/etc) telling an agent whether current conditions favor range-bound (grid) strategies or trend-following ones. Use this before deciding to deploy a grid bot, mean-reversion strategy, or trend-follow strategy on SOL, XLM, BTC, ETH, XRP, DOGE, LTC, or ADA.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • crypto_sentimentSentiment score (-1 to +1) with a bullish/neutral/bearish label, for either raw text or a crypto asset's recent price action, via an LLM.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Sentiment score (-1 to +1) with a bullish/neutral/bearish label, for either raw text or a crypto asset's recent price action, via an LLM. Give it EXACTLY ONE of `text` (free-form text to score) or `asset` (one of SOL, XLM, BTC, ETH, XRP, DOGE, LTC, ADA). Useful for agents building trading signals, news pipelines, or social-listening tools without running their own LLM sentiment call.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • factcheckFact-check verdict (true / false / uncertain) with a confidence score (0-1) and a 1-2 sentence reasoning for any factual claim, via an LLM.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Fact-check verdict (true / false / uncertain) with a confidence score (0-1) and a 1-2 sentence reasoning for any factual claim, via an LLM. Useful for content moderation, chatbot/agent guardrails, and misinformation screening. Returns 'uncertain' for opinions or claims requiring live/real-time data.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • gridparamsPAID PER CALL ($0.05 USDC on Base via x402).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    PAID PER CALL ($0.05 USDC on Base via x402). Recommended grid-trading parameters (range, spacing, order size) for a pair and capital amount, derived from live 24h market structure. Unpaid calls return the exact x402 payment terms.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • pricePAID PER CALL ($0.005 USDC on Base via x402).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    PAID PER CALL ($0.005 USDC on Base via x402). Current price, 24h/7d change, and a simple signal for a major crypto asset. Unpaid calls return the exact x402 payment terms.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • pricecheckCurrent price, 24h and 7d percent change, and a simple bullish/bearish/neutral signal for a major crypto asset.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Current price, 24h and 7d percent change, and a simple bullish/bearish/neutral signal for a major crypto asset. Low-latency market-data lookup for dashboards, bots, and alerts — one of SOL, XLM, BTC, ETH, XRP, DOGE, LTC, ADA.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • regimePAID PER CALL ($0.03 USDC on Base via x402).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    PAID PER CALL ($0.03 USDC on Base via x402). Market regime (chop / trend_up / trend_down / high_vol) plus a grid-suitability verdict, computed from live 24h market structure. Unpaid calls return the exact x402 payment terms.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • riskPAID PER CALL ($0.02 USDC on Base via x402).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    PAID PER CALL ($0.02 USDC on Base via x402). Volatility / drawdown risk regime (low / med / high) vs the 30-day baseline for a major crypto asset. Unpaid calls return the exact x402 payment terms.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • sentimentPAID PER CALL ($0.005 USDC on Base via x402).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    PAID PER CALL ($0.005 USDC on Base via x402). Sentiment score (-1..+1) with label for EXACTLY ONE of `text` or `asset`. Unpaid calls return the exact x402 payment terms.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • telemetryPAID PER CALL ($0.005 USDC on Base via x402 — no signup, no API key).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    PAID PER CALL ($0.005 USDC on Base via x402 — no signup, no API key). Telemetry for an AI-managed long-horizon crypto portfolio: allocation, reconciled profit-and-loss, signal votes, and the human-approval trail for every trade. Unpaid calls return the exact x402 payment terms.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • token_riskVolatility / drawdown risk regime (low / med / high) for a major crypto asset, extending the same classifier behind crypto_regime.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Volatility / drawdown risk regime (low / med / high) for a major crypto asset, extending the same classifier behind crypto_regime. Tells an agent whether current volatility is elevated vs its 30-day baseline — useful for position sizing and stop-placement logic. One of SOL, XLM, BTC, ETH, XRP, DOGE, LTC, ADA.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
Only reads 1Show 1 read-only tool
  • summarizeTight 3-5 sentence summary of a URL or a raw text block, via an LLM.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "summarize" says "summarize": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Tight 3-5 sentence summary of a URL or a raw text block, via an LLM. Give it EXACTLY ONE of `url` (a page to fetch and summarize) or `text` (raw text to summarize directly). For agents/pipelines that need a fast, information-dense digest without running their own LLM call or web fetch.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: 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.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:00 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
11
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 11 tools that change things (11 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.stelardigital.com/mcp: tools/list returned 12 tools to an anonymous client, including crypto_regime (write), crypto_sentiment (write), factcheck (write), pricecheck (write), token_risk (write) and 6 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.1.3. Values in angle brackets are yours to fill in.

claude mcp add --transport http stelar-signals https://api.stelardigital.com/mcp
claude mcp add --transport http stelar-signals https://api.stelardigital.com/mcp

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.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__stelar-signals__crypto_regime",
      "mcp__stelar-signals__crypto_sentiment",
      "mcp__stelar-signals__summarize",
      "mcp__stelar-signals__factcheck",
      "mcp__stelar-signals__pricecheck",
      "mcp__stelar-signals__token_risk",
      "mcp__stelar-signals__telemetry",
      "mcp__stelar-signals__regime",
      "mcp__stelar-signals__gridparams",
      "mcp__stelar-signals__sentiment",
      "mcp__stelar-signals__risk",
      "mcp__stelar-signals__price"
    ],
    "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 stelar-signals. Review it before you use it.

Capability tags behind 1 rule
  • mcp__stelar-signals__summarize untrusted-input, outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.StelarDigital/stelar-signals-mcp/verify?hash=1ae930a7fb6817eab6673b7960ed98beef2338d43e9f3afa1de43ab10291ef55" | jq -e '.changed == false'

Pinned hash 1ae930a7fb68, from Nov 16, 2026, 05:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.StelarDigital/stelar-signals-mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.StelarDigital/stelar-signals-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.StelarDigital/stelar-signals-mcp.svg)](https://radar.anlyon.com/servers/io.github.StelarDigital/stelar-signals-mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:21 UTC.

Stelar Signals MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Stelar Signals MCP server safe?

No scan can promise that. What its definitions show: 12 tools, 11 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Stelar Signals MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Stelar Signals MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Stelar Signals MCP server have?

12 tools: 11 write, 1 read. crypto_regime, crypto_sentiment, factcheck, pricecheck, token_risk, telemetry, regime, gridparams and 4 more.

Does the Stelar Signals MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Stelar Signals MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): summarize.

Has the Stelar Signals MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.