Skip to content

Kristo Intelligence MCP server

io.github.hristovdimitri2-hub/kristo-intelligencehristovdimitri2-hubstreamable-httpv6.3.0Scanned

Pay-per-call DeFi intelligence for AI agents on Base — x402, USDC, no keys.

7 tools: 7 only read.

Tools: 0 delete, 0 irreversible, 0 write, 7 read.
  • Reads private data · 0
  • Reads text others write · 7
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

  • 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 Kristo Intelligence MCP server can do

The Kristo Intelligence MCP server is published by the GitHub account hristovdimitri2-hub. It has 7 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

7 tools bring in text other people can write (get_market_stats, get_onchain_sales, get_bot_status and 4 more).

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 2 times since Anlyon Radar first saw them.

Last scanned Nov 20, 2026, version 6.3.0.

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.

7 tools

Only reads 7Show 7 read-only tools
  • get_arbitrage_opportunitiesRead-only operation — no side effects, no parameters.Reads text others writeNo findings

    Why it is in this group

    • The name "get_arbitrage_opportunities" 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
    Read-only operation — no side effects, no parameters. Returns live cross-DEX arbitrage spreads on Base, refreshed every 60 seconds. Use it for executable price gaps between venues; use get_market_stats for aggregate prices or get_trading_signal for directional calls.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
  • get_bot_statusRead-only operation — no side effects, no parameters.Reads text others writeNo findings

    Why it is in this group

    • The name "get_bot_status" 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
    Read-only operation — no side effects, no parameters. Returns the service's Telegram integration status as JSON: telegram_bot_running, telegram_token_configured, last_heartbeat, uptime_started, messages_sent, active_users, commands_processed, vip_invites_sent, plus the wallet state. Use it to confirm this service's own monitoring is alive (and its heartbeat recent) before trusting other outputs; use get_market_stats for market data or get_onchain_sales for provable revenue.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
  • get_market_statsRead-only operation — no side effects, no parameters.Reads text others writeNo findings

    Why it is in this group

    • The name "get_market_stats" 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
    Read-only operation — no side effects, no parameters. Returns the live Base market snapshot: aggregated activity, daily request/sales counters, the official agent catalog, and real-time market data (CoinGecko, DEXScreener, Fear & Greed). Use it for market context and price/indicator lookups; use get_onchain_sales for paid-call revenue and get_bot_status for integration health.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
  • get_onchain_salesRead-only operation — no side effects, no parameters.Reads text others writeNo findings

    Why it is in this group

    • The name "get_onchain_sales" 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
    Read-only operation — no side effects, no parameters. Returns the real on-chain payment history to this service's fee receiver on Base: total_volume_usd, total_sales, by_token, up to 100 history rows (tx hash, payer, amount, block, timestamp), source="real_blockchain", plus the wallet state and a market snapshot. Use it when you need provable revenue or settlement evidence; use get_market_stats for prices and get_bot_status for integration health.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
  • get_trading_signalRead-only operation — no side effects, no parameters.Reads text others writeNo findings

    Why it is in this group

    • The name "get_trading_signal" 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
    Read-only operation — no side effects, no parameters. Returns this service's flagship trading-agent signals for ETH, ONDO, KAITO and DEGEN: action, confidence, price_usd and the model's reasoning. Use it when you need a directional call rather than raw market data; use get_whale_flow for large-transfer flow and get_arbitrage_opportunities for cross-DEX spreads.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
  • get_whale_flowRead-only operation — no side effects, no parameters.Reads text others writeNo findings

    Why it is in this group

    • The name "get_whale_flow" 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
    Read-only operation — no side effects, no parameters. Returns network-wide USDC whale flow on Base: transfers of $5M or more, refreshed every 60 seconds, with labelled counterparties. Use it to see where size is moving; use get_trading_signal for directional calls or get_market_stats for broad context.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
  • verify_seller_receiverRead-only; REQUIRES `receiver`.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "read": 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
    Read-only; REQUIRES `receiver`. Audits ANY receiver's incoming USDC on Base: distinct payers, repeat payers, concentration, probes vs customers. Decides whether a seller is safe to pay. Reports partial/failed, never a zero it did not measure.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true

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 write7
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, 19:05 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
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
yes
Dynamic client registration
not observed
Client ID metadata documents
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. Tools1 added, 6 changed.+1 added~6 changedView diff
  2. Tools3 added.+3 addedView diff

Install

Pinned to version 6.3.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http kristo-intelligence https://kristo-intelligence-api.onrender.com/mcp
claude mcp add --transport http kristo-intelligence https://kristo-intelligence-api.onrender.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__kristo-intelligence__get_market_stats",
      "mcp__kristo-intelligence__get_onchain_sales",
      "mcp__kristo-intelligence__get_bot_status",
      "mcp__kristo-intelligence__get_trading_signal",
      "mcp__kristo-intelligence__get_whale_flow",
      "mcp__kristo-intelligence__get_arbitrage_opportunities",
      "mcp__kristo-intelligence__verify_seller_receiver"
    ],
    "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 kristo-intelligence. Review it before you use it.

Capability tags behind 7 rules
  • mcp__kristo-intelligence__get_market_stats untrusted-input
  • mcp__kristo-intelligence__get_onchain_sales untrusted-input
  • mcp__kristo-intelligence__get_bot_status untrusted-input
  • mcp__kristo-intelligence__get_trading_signal untrusted-input
  • mcp__kristo-intelligence__get_whale_flow untrusted-input
  • mcp__kristo-intelligence__get_arbitrage_opportunities untrusted-input
  • mcp__kristo-intelligence__verify_seller_receiver 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.hristovdimitri2-hub/kristo-intelligence/verify?hash=14205269b05cc0e8154d83dd361ce833a727b4c8ba8f37bca787c29ee7dd309a" | jq -e '.changed == false'

Pinned hash 14205269b05c, from Nov 20, 2026, 18:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.hristovdimitri2-hub/kristo-intelligence/changes.xml

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

Badge

Anlyon Radar badge for io.github.hristovdimitri2-hub/kristo-intelligence
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.hristovdimitri2-hub/kristo-intelligence.svg)](https://radar.anlyon.com/servers/io.github.hristovdimitri2-hub/kristo-intelligence)

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

Kristo Intelligence MCP server: questions and answers

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

Is the Kristo Intelligence MCP server safe?

No scan can promise that. What its definitions show: 7 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the Kristo Intelligence MCP server delete data?

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

Can the Kristo Intelligence 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 Kristo Intelligence MCP server have?

7 tools: 7 read. get_market_stats, get_onchain_sales, get_bot_status, get_trading_signal, get_whale_flow, get_arbitrage_opportunities and verify_seller_receiver.

Does the Kristo Intelligence MCP server need sign-in or OAuth?

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

Does the Kristo Intelligence MCP server send data to outside services?

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

Has the Kristo Intelligence MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.