Skip to main content
Glama
Sign In

Iris

by io.github.0xVector0
OverviewDiscussionsAdmin

Analyze an address on Solana, an EVM chain, Bitcoin, Tron, dYdX or Noble

analyze_address
Read-only

Analyze a wallet with Iris: on Solana (also a token mint or a program), Ethereum, Base, Arbitrum, Robinhood Chain, BNB Chain, Polygon, Bitcoin, Tron, dYdX or Noble. The chain is read from the address (0x is Ethereum unless chain says another EVM chain). Costs 1 credit (2 when depth is over 1000), or without an API key $0.05 ($0.10 deep) paid per call with x402; refunded (never settled) if it fails. A token, or a wallet Iris hasn't read recently, can take about a minute. For a wallet: what it is (exchange, MEV bot, drainer, sniper, scam or poisoning wallet, personal wallet...), its risk score, the database's labels on it, its behaviours with example transactions, who sent it its first SOL (Solana), where its money came from and went (largest counterparties, labeled), look-alike (address poisoning) addresses, and the exchanges and mixers it moved money with, with the latest transaction for each (to use with trace_transfer). A Solana Privacy Rings user's steps there are read from the owners Rings publishes: what it deposited and for whom, whom it paid privately (amount hidden), who paid it, where its withdrawals went and whose fees it paid; a view tag alone is a lead, an anonymous policy ring is not traceable. For a token mint: its creator and the creator's funder, the launch bundle and who funded it, red flags, the wallets in its groups and its top holders. For a program: who can upgrade it, who deployed it, its top callers. Only the latest transactions (depth) are read. Returns a summary and a link to the full view on iriscan.app.

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": {
      "address": "<address>"
    },
    "name": "analyze_address"
  }
}

Input Schema

NameRequiredDescriptionDefault
chainNoThe chain, when the address's form doesn't say it: an EVM chain for a 0x address (ethereum by default). Read from the address otherwise.
depthNoHow many of the most recent transactions to read. Over 1000 is a deep analysis (2 credits, or $0.10 with x402). Smaller is faster: 200 is often enough for a first look.
addressYesThe address: Solana or Tron base58, 0x (EVM), Bitcoin (bc1, 1 or 3), dydx1 or noble1. On Solana also a token mint or a program.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / chain / enum
      Previous value: -[
-  "solana",
-  "ethereum",
-  "base",
-  "arbitrum",
-  "robinhood",
-  "bsc",
-  "bitcoin",
-  "tron",
-  "dydx",
-  "noble"
-]New value: +[
+  "solana",
+  "ethereum",
+  "base",
+  "arbitrum",
+  "robinhood",
+  "bsc",
+  "polygon",
+  "bitcoin",
+  "tron",
+  "dydx",
+  "noble"
+]
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnly and openWorld, and the description goes well beyond them with cost mechanics (1 credit, 2 over depth 1000; $0.05/$0.10 via x402), the failure policy (refunded, never settled), and latency expectations (a token or stale wallet can take about a minute). It also bounds the read scope with "Only the latest transactions (depth) are read" and qualifies what a view tag means versus an anonymous policy ring, which is real behavioural disclosure beyond the structured fields.

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

Conciseness4/5

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

The core action, cost and latency come first and every clause is informative rather than filler. It is dense and long, though, with the full chain list repeated across title, description and enum, and the wallet/mint/program branches would be easier to parse as separated lines than one flowing paragraph.

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

Completeness5/5

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

For a complex multi-chain, multi-object-type analyzer with no output schema, the description covers the returned payload in detail (summary, risk score, labels, behaviours, counterparties, poisoning look-alikes, exchanges/mixers) plus the iriscan.app link. Nothing an agent needs in order to decide to call it and interpret the shape of what comes back is missing.

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?

Schema description coverage is 100%, so all three parameters are already documented, including the chain default for 0x addresses and the depth credit cliff. The description restates both facts ("The chain is read from the address") and adds little syntax or format detail the schema lacks, so the baseline 3 applies.

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

Purpose5/5

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

The description gives a specific verb+resource ("Analyze a wallet with Iris") and extends it precisely to three address kinds — wallet, Solana token mint, program — on named chains. It then enumerates what each kind yields (risk score, labels, behaviours, counterparties for wallets; creator/funder/bundle for mints; upgrade authority/callers for programs), so an agent can tell exactly what this tool does that trace_transfer or find_token_insiders do not.

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?

Usage context is clear: it is the entry-point analysis for any address on the listed chains, and the phrase "with the latest transaction for each (to use with trace_transfer)" hand-off routes the agent onward. However there is no explicit when-not-to-use, and it never says whether get_connections or find_token_insiders should be preferred for specific intents, so it stops short of full alternative routing.

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

All Iris toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources