Skip to content

gtxagent-mcp server

com.gtxagent/gtxagent-mcpgtxagent.comstreamable-httpv0.4.1Scanned

Paid x402 crypto tools for AI agents. Installs keyless; a key adds Krokus and Prepa daily signals.

14 tools: 13 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 13 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

13 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 gtxagent-mcp server can do

The gtxagent-mcp server is published by gtxagent.com, a domain the MCP Registry verified. It has 14 tools. It can create or change data (13 tools: token_safety, token_price, market_open, agent_recommend and 9 more), but cannot delete data. 1 tool only reads.

None of its tools reads private data, brings in text other people write, or sends data out.

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, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 20, 2026, version 0.4.1.

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.

14 tools

Changes things 13Claude Code: ask
  • agent_recommendWhich x402 API should the agent call for this task?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.
    Description, as the server wrote it
    Which x402 API should the agent call for this task? A ranked, compact recommendation with rationale and price, so an agent spends once instead of probing five endpoints. Price $0.02 USDC, charged from your prepaid credits. A key is required: without one the call is refused, because the upstream purchase is real.
  • market_openIs this exchange open right now?No findings

    Why it is in this group

    • The name "market_open" says "open": a word for a change.
    Description, as the server wrote it
    Is this exchange open right now? Whether a named venue is trading at a given instant, with local time and the next holiday, so an agent never trades a closed market. Price $0.015 USDC, charged from your prepaid credits. A key is required: without one the call is refused, because the upstream purchase is real.
  • market_pulseWhat are Base tokens trading at right now?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.
    Description, as the server wrote it
    What are Base tokens trading at right now? Live USDC quotes for every supported token, with unavailable legs named. Price $0.01 USDC, charged from your prepaid credits. The first 3 calls per day are free without a key.
  • strategy_catalogWhich daily research signals does GTXAgent sell?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.
    Description, as the server wrote it
    Which daily research signals does GTXAgent sell? Krokus and Prepa: thesis, as_of, freshness, universe size and where to call them. Price $0.005 USDC, charged from your prepaid credits. The first 3 calls per day are free without a key.
  • strategy_krokusThe Krokus daily funding-flush signal: side, walk-forward thresholds, the features that decided it, the failed conditions for flat rows, OOS stats and the paper ledger, with as_of …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.
    Description, as the server wrote it
    The Krokus daily funding-flush signal: side, walk-forward thresholds, the features that decided it, the failed conditions for flat rows, OOS stats and the paper ledger, with as_of and a staleness flag. Research, not an execution instruction. Price $0.05 USDC, charged from your prepaid credits. The first 3 calls per day are free without a key.
  • strategy_prepaThe Prepa daily taker-flow signal: side, walk-forward thresholds, the features that decided it, the failed conditions for flat rows, OOS stats and the paper ledger, with as_of and …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.
    Description, as the server wrote it
    The Prepa daily taker-flow signal: side, walk-forward thresholds, the features that decided it, the failed conditions for flat rows, OOS stats and the paper ledger, with as_of and a staleness flag. Research, not an execution instruction. Price $0.05 USDC, charged from your prepaid credits. The first 3 calls per day are free without a key.
  • token_decisionShould I buy or skip this Base token?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.
    Description, as the server wrote it
    Should I buy or skip this Base token? One deterministic yes/no over 24h with confidence, reasons and sources. Price $0.01 USDC, charged from your prepaid credits. The first 3 calls per day are free without a key.
  • token_priceLive token price and market data for one or more coin ids or tickers, for agents that need a USD number before sizing a position.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.
    Description, as the server wrote it
    Live token price and market data for one or more coin ids or tickers, for agents that need a USD number before sizing a position. Price $0.04 USDC, charged from your prepaid credits. A key is required: without one the call is refused, because the upstream purchase is real.
  • token_quoteWhat is this token worth and where is it?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.
    Description, as the server wrote it
    What is this token worth and where is it? One token's contract, decimals and latest USDC quote. Price $0.002 USDC, charged from your prepaid credits. The first 3 calls per day are free without a key.
  • token_registryWhich tokens can I trade here?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.
    Description, as the server wrote it
    Which tokens can I trade here? Symbol, address, decimals and status for every allowed Base token. Price $0.005 USDC, charged from your prepaid credits. The first 3 calls per day are free without a key.
  • token_safetyIs this token safe to buy?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.
    Description, as the server wrote it
    Is this token safe to buy? Ownership powers, holder concentration, honeypot and liquidity flags for one token before an agent swaps, sends or accepts it. Price $0.03 USDC, charged from your prepaid credits. A key is required: without one the call is refused, because the upstream purchase is real.
  • whale_coverageCan this whale-flow dataset answer my question?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.
    Description, as the server wrote it
    Can this whale-flow dataset answer my question? Coverage summary with asset classes, symbol count and the exact time range, before an agent pays for data. Price $0.02 USDC, charged from your prepaid credits. A key is required: without one the call is refused, because the upstream purchase is real.
Only reads 1Show 1 read-only tool

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 untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:21 UTC, unchanged since Nov 20, 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
13
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 13 tools that change things (13 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://app.gtxagent.com/mcp: tools/list returned 14 tools to an anonymous client, including token_safety (write), token_price (write), market_open (write), agent_recommend (write), trending_coins (write) and 8 more

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • HTTP status of an anonymous initialize: 401 to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 13
    • Protocol version: none to 2025-06-18
    • WWW-Authenticate on 401: no to not observed

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.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 401 -> 200; tools/list served without credentials: no -> yes; Tools that change things, listed without credentials: 0 -> 13 (and 2 more).View diff
    • HTTP status of an anonymous initialize: 401 to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 13
    • Protocol version: none to 2025-06-18
    • WWW-Authenticate on 401: no to not observed
  2. Tools3 added.+3 addedView diff

Install

Pinned to version 0.4.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http gtxagent https://app.gtxagent.com/mcp
claude mcp add --transport http gtxagent https://app.gtxagent.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": [
      "mcp__gtxagent__x_search"
    ],
    "ask": [
      "mcp__gtxagent__token_safety",
      "mcp__gtxagent__token_price",
      "mcp__gtxagent__market_open",
      "mcp__gtxagent__agent_recommend",
      "mcp__gtxagent__trending_coins",
      "mcp__gtxagent__whale_coverage",
      "mcp__gtxagent__market_pulse",
      "mcp__gtxagent__token_registry",
      "mcp__gtxagent__token_decision",
      "mcp__gtxagent__token_quote",
      "mcp__gtxagent__strategy_catalog",
      "mcp__gtxagent__strategy_krokus",
      "mcp__gtxagent__strategy_prepa"
    ],
    "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 gtxagent. Review it before you use it.

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/com.gtxagent/gtxagent-mcp/verify?hash=fd8ef020be502443b75b28a5af2c6731d4191f92d54a4f3592290b9c66292cb5" | jq -e '.changed == false'

Pinned hash fd8ef020be50, from Nov 20, 2026, 17:18 UTC.

Watch

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

https://radar.anlyon.com/servers/com.gtxagent/gtxagent-mcp/changes.xml

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

Badge

Anlyon Radar badge for com.gtxagent/gtxagent-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/com.gtxagent/gtxagent-mcp.svg)](https://radar.anlyon.com/servers/com.gtxagent/gtxagent-mcp)

Source: MCP Registry. Synced Nov 20, 2026, 18:17 UTC.

gtxagent-mcp server: questions and answers

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

Is the gtxagent-mcp server safe?

No scan can promise that. What its definitions show: 14 tools, 13 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 gtxagent-mcp server delete data?

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

Can the gtxagent-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 gtxagent-mcp server have?

14 tools: 13 write, 1 read. token_safety, token_price, market_open, agent_recommend, trending_coins, whale_coverage, market_pulse, token_registry and 6 more.

Does the gtxagent-mcp server need sign-in or OAuth?

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

Does the gtxagent-mcp server send data to outside services?

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

Has the gtxagent-mcp server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.