Skip to main content
Glama

Taifoon coordination layer

Read chain data

taifoon_chain

Reads blocks, transactions, logs, accounts and protocol state from the layer's own index and coord RPC. For a proof use taifoon_prove. Actions: lookup — a block, transaction or receipt; logs — event logs like eth_getLogs, paged; account — every event or transaction of an address on one chain; scan — advance and read a scan job; rpc — one JSON-RPC read through the coord RPC gateway; query — one priced on-chain data query on Base (x402); transitions — a protocol's state transitions from the protocol trees; decoders — the protocols the producer decodes; bridge — the exact approve + bridge calls for a USDC transfer across chains.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "taifoon_chain"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoblock: latest | finalized | a number | a block hash; tx and receipt: the 32-byte transaction hash (actions: lookup, scan)
toNoto (actions: logs, account)
keyNokey (actions: transitions)
txsNoblock: add the transaction hashes (actions: lookup)
fromNofrom (actions: logs, account)
kindNokind (actions: lookup)
viewNoview (actions: account)
chainNo8453 (Base); "base" works too (actions: query)
limitNolimit (actions: logs, account, scan, transitions)
speedNospeed (actions: bridge)
actionNowhat to do (default lookup): lookup | logs | account | scan | rpc | query | transitions | decoders | bridgelookup
amountNoamount (actions: bridge)
cursorNocursor (actions: logs, account, scan)
methodNomethod (actions: rpc)
paramsNoparams (actions: rpc, query)
senderNosender (actions: bridge)
topic0Notopic0 (actions: logs)
topic1Notopic1 (actions: logs)
topic2Notopic2 (actions: logs)
topic3Notopic3 (actions: logs)
addressNoaddress (actions: logs, account)
api_keyNoapi key (actions: lookup, logs, account, scan, rpc, transitions)
paymentNooptional: the x402 PAYMENT-SIGNATURE header value (base64) for the terms an unpaid call returns (actions: query)
chain_idNoany chain the layer reads: 8453, 5042, 1, 56, 43114, 42161, 137, 10, 4663, 42220, 36927, 3692781, 999, 99901, 2741, 196, 143, 100 (actions: lookup, logs, account, scan, rpc)
from_seqNofrom seq (actions: transitions)
protocolNoprotocol (actions: transitions)
questionNoquestion (actions: query)
recipientNorecipient (actions: bridge)
full_proofNoadd the multiproof itself (actions: lookup)
dst_chain_idNodst chain id (actions: bridge)
src_chain_idNosrc chain id (actions: bridge)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / chain_id / description
      Previous value: -"any chain the layer reads: 8453, 5042, 1, 56, 43114, 42161, 137, 10, 4663, 42220, 36927, 3692781, 2741, 196, 143, 100 (actions: lookup, logs, account, scan, rpc)"New value: +"any chain the layer reads: 8453, 5042, 1, 56, 43114, 42161, 137, 10, 4663, 42220, 36927, 3692781, 999, 99901, 2741, 196, 143, 100 (actions: lookup, logs, account, scan, rpc)"
  2. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety bar is lowered, and the description adds per-action behavior (paging on logs, x402 pricing on query, bridge returning approve+bridge calls). It omits anything about api_key requirements for six of the actions, rate limits, or what an unpaid query returns beyond the payment parameter. The "reads" framing also sits awkwardly against readOnlyHint=false without explaining that bridge merely builds calldata rather than sending it.

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?

Purpose is front-loaded in the first clause, then the nine actions are laid out as a scannable em-dash list. It is dense and long, but nearly every clause carries routing information. Slight deduction for the run-on single paragraph, which makes the action list harder to parse than separate lines would be.

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

Completeness3/5

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

For a 31-parameter, nine-action dispatcher with no output schema, the description explains what each action does but never what each returns (shape of a lookup vs a scan job vs a bridge payload) or what authentication each needs. Those are exactly the facts an agent cannot get from the schema alone. Adequate for picking an action, thin for predicting results.

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 coverage is 100%, so the baseline is 3 and the schema already scopes each parameter to its action. The description does add genuine meaning the schema lacks — what id means per kind, that logs are paged, that chain accepts "base" — but most of that enrichment lives in the schema descriptions rather than this text.

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?

Names a specific verb and resource set ("Reads blocks, transactions, logs, accounts and protocol state from the layer's own index and coord RPC") and then enumerates nine distinct actions with a one-line gloss each ("logs — event logs like eth_getLogs, paged"). That makes the dispatcher's scope concrete. It loses a point only because the umbrella framing is broad and the boundary against siblings like taifoon_account is not fully drawn.

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?

Explicitly routes the agent away from the wrong sibling: "For a proof use taifoon_prove." That is real exclusion guidance. It does not, however, explain when to prefer lookup over rpc, or how the "account" action relates to the sibling taifoon_account, so some inference is still required.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources