Polymarket News-to-Market Direction Scores

omnial/pm-scorings

Returns recent rows scoring one breaking-news headline against one Polymarket market: a direction (up/down/none), a 0-1 confidence, a signed magnitude in points, a SKIP/WATCH/TRADE composite tier, the market's current price, and the model's free-text reasoning -- filterable by event, market, or tier.

activeper callv2

Price

$0.151 per call

You pay the price shown. If a call turns out to cost more than its quote, you pay the actual price, capped at twice the quote. No monthly minimum. Top-ups start at $5.00.

Data source

Gloria AI

News signals by Gloria AI, drawn from public X (Twitter) posts; summaries and sentiment are machine-generated.

Use it

Your AI assistant does the work: it finds this tool, shows you the price first, runs it, and you are charged when the run finishes. There is nothing to set up for this tool in particular.

Connect once and your AI can find and run this tool, and any other it needs.

Install it Create an account

For developers: the calls your assistant makes

agent

// 1. search: find the tool
omnial_search({ query: "what you need" })

// 2. inspect: price and input schema
omnial_inspect({ tool: "omnial/pm-scorings" })

// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "omnial/pm-scorings" })

// 4. run: price the exact call first, then run it
omnial_execute({ tool: "omnial/pm-scorings", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "omnial/pm-scorings", input: { /* ... */ } })

// 5. settle: the call is charged when it finishes, nothing to do

Not connected yet? Point your MCP client at https://mcp.eden-engine.com/mcp, then copy a config for your client.

Pricing

Every charge this tool can incur.

Charge	Price
Per call	$0.151

Updated: Oct 27, 2026

Input and output schemas

Input schema

input_schema.json

{
  "type": "object",
  "properties": {
    "tier": {
      "type": "string",
      "description": "Filter by tier: SKIP | WATCH | TRADE"
    },
    "limit": {
      "type": "string",
      "default": 50,
      "description": "Max rows to return (1-500, default 50)"
    },
    "event_id": {
      "type": "string",
      "description": "Filter by event id"
    },
    "market_id": {
      "type": "string",
      "description": "Filter by market id"
    }
  },
  "additionalProperties": false
}

Output schema

output_schema.json

{
  "type": "object",
  "properties": {
    "scorings": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "description": "Unique id for this scoring row."
          },
          "tier": {
            "type": "string",
            "description": "Composite tier. Observed values: 'SKIP', 'TRADE'. The input filter also documents 'WATCH', which has not been observed in testing."
          },
          "reason": {
            "type": "string",
            "description": "Free-text model explanation for the direction/magnitude call. Several long rows observed cut off mid-sentence with no trailing marker -- treat this as a hard vendor-side length cutoff, not a guaranteed complete sentence."
          },
          "event_id": {
            "type": "string",
            "description": "The Polymarket event this row's market belongs to."
          },
          "headline": {
            "type": "string",
            "description": "The news headline text that was scored."
          },
          "direction": {
            "type": "string",
            "description": "Observed values: 'up', 'down', 'none'."
          },
          "market_id": {
            "type": "string",
            "description": "The specific Polymarket market scored against the headline."
          },
          "confidence": {
            "type": "number",
            "description": "0-1 confidence in the direction/magnitude call."
          },
          "created_at": {
            "type": "string",
            "description": "ISO 8601 UTC timestamp the row was scored."
          },
          "source_url": {
            "type": [
              "string",
              "null"
            ],
            "description": "Withheld -- returned as `null` regardless of the source article's real URL The headline text itself is still returned."
          },
          "headline_id": {
            "type": "string",
            "description": "Groups every row scored against the same headline text."
          },
          "current_price": {
            "type": "number",
            "description": "The market's current price at scoring time, 0-1."
          },
          "magnitude_pts": {
            "type": "number",
            "description": "Signed magnitude in points. Observed range -1 to 8 in testing; 0 whenever direction is 'none'."
          },
          "model_version": {
            "type": "string",
            "description": "Opaque scoring-model/strategy version identifier (e.g. combines a headline model and a trading-strategy model tag). Format is not guaranteed stable."
          },
          "partial_context": {
            "type": "boolean",
            "description": "Whether the model scored this row with incomplete surrounding context."
          }
        },
        "additionalProperties": true
      },
      "description": "Recent (headline, market) scoring rows, newest first on both real calls."
    }
  },
  "description": "The scorings response.",
  "additionalProperties": true
}