SweetAI — On-chain AI Agent Intelligence MCP server
com.tiamatcrypto.sweetai/agent-intelsweetai.tiamatcrypto.comstreamable-httpv1.4.0Scanned
Two pre-trade decisions: should-i-pay + token-verdict. ERC-8004 sybil forensics + live pool checks
2 tools: 1 do something that can't be undone and 1 change things.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
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 SweetAI — On-chain AI Agent Intelligence MCP server can do
The SweetAI — On-chain AI Agent Intelligence MCP server is published by sweetai.tiamatcrypto.com, a domain the MCP Registry verified. It has 2 tools. It can do things that cannot be undone, such as sending, paying or publishing (should_i_pay) and create or change data (1 tool: check_base_token_safety), but cannot delete data. None of its tools only reads.
2 tools bring in text other people can write (check_base_token_safety and should_i_pay).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 9, 2026, version 1.4.0.
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.
2 tools
Can't be undone 1Claude Code: ask
should_i_payPre-payment decision for any A2A payment: "should I pay this seller $N?".Reads text others write1 finding
Why it is in this group
- The name "should_i_pay" says "pay": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "should_i_pay" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "should_i_pay" says "pay": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Pre-payment decision for any A2A payment: "should I pay this seller $N?". Call it before every payment to an unknown agent or x402 seller — the agent-facing equivalent of a credit check: pay $0.01 to avoid paying a scammer $N. Answers with action PAY / CAUTION / SKIP, confidence and expected loss in USDC sized to your exact amount. Target by ERC-8004 agent_id, Solana pubkey, x402 seller_url or seller pay_to wallet. Agent targets use on-chain ERC-8004 evidence; seller targets use Bazaar demand (repeat payers/calls). For seller targets wallet_flow is marked not_available — demand data does not see seller→payer round trips. Use agent_interact_gate instead when the question is broader than payment. REST: GET /api/v1/should-i-pay ($0.01). Args: agent_id: ERC-8004 agent id of the payment TARGET (or use another target) solana_asset: Solana 8004 agent pubkey (alternative to agent_id) seller_url: x402 seller resource URL or domain (alternative target) pay_to: seller payTo wallet — EVM 0x… or Solana base58 (alternative target) amount_usd: the USDC amount you are about to pay Not investment advice.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
Changes things 1Claude Code: ask
check_base_token_safetyIs this Base token BASED / MID / COOKED / RADIOACTIVE?Reads text others writeNo 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.
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 Is this Base token BASED / MID / COOKED / RADIOACTIVE? Deterministic verdict before you buy: grade, action (ENTER_OK / CAUTION / SKIP), confidence, red flags (honeypot, sell tax, mintable supply, owner privileges, holder concentration, thin liquidity) and expected loss for your amount. Call it before swapping into any Base token. Fail-closed: an unknown token returns UNKNOWN, never "safe". Risk screen, not investment advice. REST: GET|POST /api/v1/token/verdict ($0.02). Args: token: ERC-20 contract address on Base (0x...) amount_usd: planned position size in USD (scales expected_loss_usd)
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 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.
Looked at Nov 20, 2026, 18:48 UTC, unchanged since Oct 29, 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
- 2
- 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://sweetai.tiamatcrypto.com/mcp: tools/list returned 2 tools to an anonymous client, including should_i_pay (irreversible), check_base_token_safety (write)
Posture changes
- Oct 29, 2026
- Tools that change things, listed without credentials: 11 to 2
Findings
Matches of fixed checks, with the text they matched.
- Warnshould_i_pay
The server marks "should_i_pay" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "should_i_pay" says "pay": a word that usually means money moves, which cannot be taken back.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 changed.~1 changedView diff
- Changed:should_i_payCan't be undonedescriptioninputSchema
PostureRemote posture changed. Tools that change things, listed without credentials: 11 -> 2.View diff
- Tools that change things, listed without credentials: 11 to 2
Tools32 removed, 2 changed.−32 removed~2 changedView diff
- Removed:agent_interact_gate
- Removed:agent_liveness
- Removed:check_agent_trust
- Removed:check_wallet_reputation
- Removed:get_a2a_relationships
- Removed:get_agent_liveness
- Removed:get_agent_sla
- Removed:get_agent_trust_passport
- Removed:get_bazaar_growth_stats
- Removed:get_bazaar_market_intel
- Removed:get_bazaar_organic_ranking
- Removed:get_bittensor_network_health
- Removed:get_bittensor_subnet_trust
- Removed:get_bittensor_trust_overview
- Removed:get_btc_grid_signal
- Removed:get_execution_health
- Removed:get_pump_alerts
- Removed:get_reputation_summary
- Removed:get_signals
- Removed:get_smart_money_feed
- Removed:get_solana_agents
- Removed:get_solana_forensics
- Removed:get_solana_trust_summary
- Removed:get_top_smart_buyers
- Removed:get_trading_decision
- Removed:get_trending_agents
- Removed:get_trust_forensics
- Removed:get_wallet_profile
- Removed:mint_rug_check
- Removed:reputation_origin
- Removed:verify_signal_proof
- Removed:x402_seller_verdict
- Changed:check_base_token_safetyChanges thingstitledescriptionannotations
- Changed:should_i_payCan't be undonetitledescriptionannotations
Install
Pinned to version 1.4.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-intel https://sweetai.tiamatcrypto.com/mcpclaude mcp add --transport http agent-intel https://sweetai.tiamatcrypto.com/mcpRun 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": [],
"ask": [
"mcp__agent-intel__check_base_token_safety",
"mcp__agent-intel__should_i_pay"
],
"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 agent-intel. Review it before you use it.
Capability tags behind 2 rules
- mcp__agent-intel__check_base_token_safety untrusted-input
- mcp__agent-intel__should_i_pay 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/com.tiamatcrypto.sweetai/agent-intel/verify?hash=9a37071d0b4b4129240b8aee40e0fb6566c4ad72465c0d010bf15bf2c8ed06bc" | jq -e '.changed == false'Pinned hash 9a37071d0b4b, from Nov 9, 2026, 03:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.tiamatcrypto.sweetai/agent-intel/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.tiamatcrypto.sweetai/agent-intel)Source: MCP Registry. Synced Oct 25, 2026, 01:17 UTC.
SweetAI — On-chain AI Agent Intelligence MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the SweetAI — On-chain AI Agent Intelligence MCP server safe?
- No scan can promise that. What its definitions show: 2 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the SweetAI — On-chain AI Agent 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 SweetAI — On-chain AI Agent Intelligence MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: should_i_pay.
What tools does the SweetAI — On-chain AI Agent Intelligence MCP server have?
- 2 tools: 1 irreversible, 1 write. should_i_pay and check_base_token_safety.
Does the SweetAI — On-chain AI Agent Intelligence MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the SweetAI — On-chain AI Agent 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 SweetAI — On-chain AI Agent Intelligence MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.