SiteCheck Agent Intel & Dev

Looks at the first Solana slot where a token mint appears

agent_intel_bundle_sniper_detector

Read-only

Looks at the first Solana slot where a token mint appears (public RPC): if its history fits in 8 pages of signatures, it counts the distinct fee payers of the transactions in that slot. Several different fee payers in one slot is a bundle-sniping signal, not proof. Mints with longer history return HISTORY_TOO_LONG; this tool cannot see Jito bundle metadata. Related tools on this server, for a different need: agent_intel_honeypot_trap_detector when you need trap flags for an EVM token from GoPlus token security; agent_intel_anti_whale_limit_detector when you need Static search of a VERIFIED Ethereum contract's Solidity. Price: $0.003 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "mint": "<mint>"
    },
    "name": "agent_intel_bundle_sniper_detector"
  }
}

Input Schema

Name	Required	Description	Default
`mint`	Yes	Solana token mint address (base58, 32 to 44 characters)

Output Schema

Name	Required	Description	Default
`mint`	No
`note`	No
`source`	No
`verdict`	No
`checkedAt`	No
`pagesRead`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only say readOnly and openWorld; the description adds substantial behavior the annotations cannot convey — public RPC dependency, the 8-page signature-history ceiling, the HISTORY_TOO_LONG failure mode, blindness to Jito bundle metadata, and the caveat that multiple fee payers is a signal rather than proof. It also discloses the x402 payment model ($0.003 per successful call, failures uncharged), which directly affects whether an agent should call it speculatively.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core mechanism, which is good, and the limitations and pricing earn their place. However, the middle 'Related tools on this server, for a different need' block is long and points to EVM/GoPlus tools that are far from this tool's domain, diluting the routing value. A tighter sentence naming the truly adjacent cluster tools would be more useful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return structure needn't be explained, and the description still flags the key non-success outcome (HISTORY_TOO_LONG) and the epistemic limit of the signal. Cost, chain, and data source are all covered. What's missing is any hint of the discriminating threshold (how many distinct fee payers counts as suspicious) and whether results are cached or repeat calls cost again.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

One parameter at 100% schema description coverage, so the schema already defines the base58 mint address and its length constraints. The description adds no further meaning about the parameter (no format examples, no note on which chains/mints are unsupported beyond 'Solana'). Baseline 3 applies when the schema carries the parameter burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete analysis: find the first Solana slot containing the mint and count distinct fee payers within it, framed as a bundle-sniping signal. The verb ('looks at') is softer than ideal and the title is echoed, but the mechanism and the output interpretation are both explicit. It also names sibling tools for adjacent needs, so an agent can separate it from honeypot/anti-whale checks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear applicability (Solana mint, early-slot fee-payer diversity) plus an explicit when-not condition: mints with longer than 8 pages of signature history return HISTORY_TOO_LONG. The 'related tools for a different need' routing is present but points to tools on other chains/purposes rather than the genuinely closest siblings (e.g. holder_cluster_analyzer, sybil_airdrop_farmer_check), so routing guidance is partial.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SiteCheck Agent Intel & Dev tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?