Skip to content

xsignal MCP server

io.github.philpof102-svg/xsignalphilpof102-svgstreamable-httpv0.2.1Scanned

x402 pay-per-call data tools for Base agents. Flagship get_intent ABSTAINS instead of guessing.

6 tools: 6 only read.

Tools: 0 delete, 0 irreversible, 0 write, 6 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 0
  • 1 finding

Sign-in required, no OAuth metadata. Remote posture

Anlyon alternative

Run the operations that matter as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the xsignal MCP server can do

The xsignal MCP server is published by the GitHub account philpof102-svg. It has 6 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

2 tools bring in text other people can write (get_token_brief and get_signal).

The fixed checks matched 1 finding (base64-blob). Each one comes with the text it matched.

Last scanned Nov 6, 2026, version 0.2.1.

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.

6 tools

Only reads 6Show 6 read-only tools
  • get_intentFLAGSHIP.1 finding

    Why it is in this group

    • The name "get_intent" says "get": a word for reading.

    Findings

    • Warn

      The description contains a 42-character base64 string.

      Matched text

      description: "...e: GET /intent?addr=0x4ed4E862860beD51a9570b96d89aF5E1B0Efefed&min_confidence=0.7"

      What this check looks for
    Description, as the server wrote it
    FLAGSHIP. An outcome-priced momentum verdict that ABSTAINS below your confidence bar - the only x402 signal that refuses to answer (honestly) when it is not sure. Post {addr, min_confidence 0-1} then pay $0.01, and get a mechanical momentum verdict "gaining" or "fading" IF the signal agreement clears your bar, else a calibrated "abstain". Paid answers carry a keyless tamper-evidence receipt. confidence is a transparent heuristic, NOT a prediction; not financial advice. x402-paid at GET/POST /intent (3 free calls per wallet via ?wallet=0x…). Example: GET /intent?addr=0x4ed4E862860beD51a9570b96d89aF5E1B0Efefed&min_confidence=0.7
  • get_preflightThe Base PREFLIGHT: one call fuses MainStreet on-chain SAFETY (SAFE/WATCH/AVOID + rug flags) with xsignal MOMENTUM (the abstaining read) into a single recommendation (GO / CAUTION …No findings

    Why it is in this group

    • The name "get_preflight" says "get": a word for reading.
    Description, as the server wrote it
    The Base PREFLIGHT: one call fuses MainStreet on-chain SAFETY (SAFE/WATCH/AVOID + rug flags) with xsignal MOMENTUM (the abstaining read) into a single recommendation (GO / CAUTION / AVOID / AVOID_ENTRY / NEUTRAL / UNVERIFIED) answering "is this token safe to touch AND moving?". Safety GATES momentum - never green-lights a token that can rug. x402-paid at GET/POST /preflight ($0.05; 3 free per wallet via ?wallet=0x…). Input: addr (0x Base token). Not financial advice.
  • get_screenBATCH watchlist screen: run the preflight (safety ⊕ momentum) over up to 10 Base tokens in one call → which are GO (safe + moving), plus a per-token verdict + a summary count.No findings

    Why it is in this group

    • The name "get_screen" says "get": a word for reading.
    Description, as the server wrote it
    BATCH watchlist screen: run the preflight (safety ⊕ momentum) over up to 10 Base tokens in one call → which are GO (safe + moving), plus a per-token verdict + a summary count. For an agent screening a watchlist. x402-paid at GET/POST /screen ($0.10; 3 free per wallet via ?wallet=0x…). Input: addrs (array or comma-separated 0x addresses). Not financial advice.
  • get_signalReal-time X/social signal for a topic: scored (virality + freshness) and CITED (source urls), deduped and ranked.Reads text others writeNo findings

    Why it is in this group

    • The name "get_signal" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Real-time X/social signal for a topic: scored (virality + freshness) and CITED (source urls), deduped and ranked. Input: query (topic) OR candidates[] (bring your own posts to score). x402-paid at GET/POST /signal ($0.01; 3 free per wallet via ?wallet=0x…). Example: GET /signal?q=base+memecoin
  • get_token_briefA fused MEAL: one call combines Base token market intel + real-time social signal into a single "what is happening with $TOKEN right now" brief - market flags + top CITED social po…Reads text others writeNo findings

    Why it is in this group

    • The name "get_token_brief" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
    Description, as the server wrote it
    A fused MEAL: one call combines Base token market intel + real-time social signal into a single "what is happening with $TOKEN right now" brief - market flags + top CITED social posts + a plain-language, non-advisory summary. Saves an agent the fetch-and-fuse work. x402-paid at GET/POST /brief ($0.05; 3 free per wallet via ?wallet=0x…). Example: GET /brief?addr=0x4ed4…&q=degen
  • get_token_intelBase token MARKET data (liquidity, 24h volume, price + change, pool age, buy/sell flow, mechanical flags) from public DEX pools.No findings

    Why it is in this group

    • The name "get_token_intel" says "get": a word for reading.
    Description, as the server wrote it
    Base token MARKET data (liquidity, 24h volume, price + change, pool age, buy/sell flow, mechanical flags) from public DEX pools. Market data, NOT a trust/safety rating. Best used as an input to get_token_brief. x402-paid at GET/POST /token ($0.01; 3 free per wallet via ?wallet=0x…).

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 write2
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.

Sign-in required, no OAuth metadata

Looked at Nov 20, 2026, 19:09 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
404
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
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

The probe stopped: initialize answered HTTP 404.

Posture changes

  1. Nov 13, 2026
    • HTTP status of an anonymous initialize: 200 to 404
    • tools/list served without credentials: yes to no
    • Protocol version: 2024-11-05 to none

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The description contains a 42-character base64 string.

    Matched text

    description: "...e: GET /intent?addr=0x4ed4E862860beD51a9570b96d89aF5E1B0Efefed&min_confidence=0.7"

    What this check looks for

History

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

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 404; tools/list served without credentials: yes -> no; Protocol version: 2024-11-05 -> none.View diff
    • HTTP status of an anonymous initialize: 200 to 404
    • tools/list served without credentials: yes to no
    • Protocol version: 2024-11-05 to none

Install

Pinned to version 0.2.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http xsignal https://xsignal-production.up.railway.app/mcp
claude mcp add --transport http xsignal https://xsignal-production.up.railway.app/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": [
      "mcp__xsignal__get_intent",
      "mcp__xsignal__get_token_brief",
      "mcp__xsignal__get_signal",
      "mcp__xsignal__get_token_intel",
      "mcp__xsignal__get_preflight",
      "mcp__xsignal__get_screen"
    ],
    "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 xsignal. Review it before you use it.

Capability tags behind 2 rules
  • mcp__xsignal__get_token_brief untrusted-input
  • mcp__xsignal__get_signal untrusted-input

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.philpof102-svg/xsignal/verify?hash=8ced75438fbf4cd52536440cffc13e18175079617347e6a2e6b8558324066826" | jq -e '.changed == false'

Pinned hash 8ced75438fbf, from Nov 6, 2026, 07:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.philpof102-svg/xsignal/changes.xml

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

Badge

Anlyon Radar badge for io.github.philpof102-svg/xsignal
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.philpof102-svg/xsignal.svg)](https://radar.anlyon.com/servers/io.github.philpof102-svg/xsignal)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:43 UTC.

xsignal MCP server: questions and answers

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

Is the xsignal MCP server safe?

No scan can promise that. What its definitions show: 6 tools, all of which only read, and 1 finding from fixed checks. Read-only tools can still pass private data to a model.

Can the xsignal MCP server delete data?

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

Can the xsignal 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 xsignal MCP server have?

6 tools: 6 read. get_intent, get_token_brief, get_signal, get_token_intel, get_preflight and get_screen.

Does the xsignal MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the xsignal MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the xsignal MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 6, 2026.