Skip to main content
Glama
Sign In

JW3 MCP Server

by io.github.agnostic4321-ops
OverviewDiscussionsAdmin

JEV market verdict

analyze_market
Read-only

SERVER-EXECUTED, read-only: ask the JEV decision model for a typed verdict (verdict + agreement% + snapshot age). Pass family (cex | dex_perps | prediction) + venue + symbol. The server builds multi-timeframe candles itself for CEX (venue+symbol only); dex_perps needs snapshot.timeframes [{tf, candles:[{o,h,l,c,v?}]}]; prediction needs snapshot.brief ONLY — 2–6 research notes YOU assemble ({title, snippet, url, at} with real URLs you can vouch for): the server fetches the live book itself and grounds the call, so never paste prices as snapshot.market (a model-supplied market is ignored). Call this BEFORE any trade proposal and cite the verdict (agree/disagree + why) in the proposal thesis — uncertain/mixed verdicts mean no trade. NEVER narrate instead of calling it.

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": {
      "family": "<family>"
    },
    "name": "analyze_market"
  }
}

Input Schema

NameRequiredDescriptionDefault
pairNoAlias of symbol (chat compat).
venueNoVenue slug (e.g. binance, kucoin, polymarket). Required for cex unless the snapshot already carries timeframes; prediction defaults to polymarket.
familyYesMarket family matching the planned trade.
symbolNoPair, ticker, or condition id (e.g. BTC/USDT). Required for cex unless the snapshot already carries timeframes; prediction takes the Polymarket conditionId/slug or Opinion market id.
exchangeNoAlias of venue (chat compat).
snapshotNoOptional override: { timeframes: [{tf, candles: [{o,h,l,c,v?}]}] } for cex/dex_perps, { market, brief: [{title, snippet, url, at}] } for prediction. Omit for CEX — the server builds candles itself; dex_perps/prediction need the snapshot shapes above.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say readOnlyHint and openWorldHint; the description adds substantial behavior beyond them — that execution is server-side, that the server builds multi-timeframe candles for CEX, that for prediction the server fetches the live book itself, and that a model-supplied snapshot.market is silently ignored. That ignored-input disclosure is exactly the kind of trap an agent would otherwise fall into on a retry.

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?

Front-loaded with the operation and return type, then per-family requirements, then the workflow rule — a sensible ordering. It is dense but every clause carries a constraint; the ALL-CAPS emphasis is a style choice rather than wasted content, though the single undivided paragraph makes it slightly harder to scan.

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 6-parameter tool with nested objects and no output schema, the description covers the per-family input contract, the return fields, and the downstream workflow obligation. Nothing an agent needs in order to call it correctly on the first attempt is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the schema already carries the field shapes; the description nevertheless adds real constraints not in the schema — the 2–6 note brief size with real, vouchable URLs, and the warning that pasted prices are discarded. It partly restates the CEX 'omit snapshot' rule already in the schema, which keeps it just short of a 5.

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?

States a specific verb and resource — 'ask the JEV decision model for a typed verdict' — and immediately enumerates the return shape (verdict + agreement% + snapshot age). It is clearly distinguishable from every sibling: it is the model-authority gate, not an order/proposal tool.

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

Usage Guidelines5/5

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

Explicit sequencing rule ('Call this BEFORE any trade proposal'), explicit follow-on obligation ('cite the verdict ... in the proposal thesis'), and an explicit exclusion ('uncertain/mixed verdicts mean no trade'). It also preempts the failure mode of narrating instead of calling.

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

All JW3 MCP Server 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