oddly

The world, on the record. AI infrastructure built on the observed web.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
88%
Naming quality
90%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~1,112Tokens (tool definitions)
~826 BTypical response size
Moderate attention impact (0.87% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "oddly-corpus": {
      "url": "https://myoddly.com/api/public/mcp"
    }
  }
}

Remote endpoints

https://myoddly.com/api/public/mcpstreamable-http

What it can do

Tool inventory

Tools (6)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢record_subject_history(subject_key)

One subject's change history and current state from oddly's record, with both clocks on every row: observed_at (when the source says it was true) and fetched_at (when oddly looked), and the receipt hash of each row so any value can be checked with record_verify_receipt. Rate: meter data.history, US$0, attribution required (cite oddly and the subject). Returns an honest empty answer for a subject the record has never observed, which is never metered.

Input Schema

{
  "type": "object",
  "properties": {
    "subject_key": {
      "type": "string",
      "description": "The subject key exactly as the record prints it on /record/subject?key=..., e.g. 'benchmark-cell:commerce/baby/clothing|SG|*|local|*|*'."
    }
  },
  "required": [
    "subject_key"
  ],
  "additionalProperties": false
}
🟢record_verify_receipt(receipt_hash)

Recompute and check one receipt end to end: the row's receipt hash recomputed from its own sealed document, the link to the row before it, the day root its day folds into, and that root's anchor state (confirmed with a block height, or pending). Every check is named in the verdict, and a check that could not run says so rather than passing. Rate: never metered (verification is on the price book's never_metered list).

Input Schema

{
  "type": "object",
  "properties": {
    "receipt_hash": {
      "type": "string",
      "description": "The 64-character hex receipt hash, as printed on a receipt or returned by the other record tools."
    }
  },
  "required": [
    "receipt_hash"
  ],
  "additionalProperties": false
}
🟢record_answer(subject_key, attribute)

Answer one question from oddly's record: the newest observed value of one attribute of one subject, with its figure, both clocks, its source, its receipt and its scope. The figure is what the source published when oddly looked, not an estimate, a forecast or advice. Rate: meter data.answer, US$0.001 per answer, first 100 per month free. An unanswered question (a subject or attribute the record has not observed) is never metered.

Input Schema

{
  "type": "object",
  "properties": {
    "subject_key": {
      "type": "string",
      "description": "The subject key exactly as the record prints it on /record/subject?key=..., e.g. 'benchmark-cell:commerce/baby/clothing|SG|*|local|*|*'."
    },
    "attribute": {
      "type": "string",
      "description": "The attribute to answer, exactly as record_subject_history lists it."
    }
  },
  "required": [
    "subject_key",
    "attribute"
  ],
  "additionalProperties": false
}
🟢benchmark_categories

List the product categories the oddly corpus currently covers, with how many observations and metrics back each one. Call this FIRST to discover valid category paths before calling benchmark_lookup, rather than guessing a path.

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢benchmark_lookup(category, metric, market)

Observed price and assortment benchmarks for a product category: the median and the p25-p75 band across real public storefront listings, with the sample size, the currency, and the exact scope of each figure. Figures are observed market reference, not targets or advice. Returns an honest empty answer when a category has too little data to serve; it never estimates or fills a gap. This corpus does NOT hold conversion rates, revenue, or AOV, so do not ask it for those.

Input Schema

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "description": "Category path, e.g. 'commerce/baby/clothing'. Use benchmark_categories to list valid paths."
    },
    "metric": {
      "type": "string",
      "description": "Optional metric filter, e.g. 'price.romper'. Omit to get every servable metric for the category."
    },
    "market": {
      "type": "string",
      "description": "Optional ISO 3166-1 alpha-2 market filter, e.g. 'NZ', 'US'. Omit for the all-markets aggregate."
    }
  },
  "required": [
    "category"
  ],
  "additionalProperties": false
}
🟢store_audit(url)

Run oddly's free storefront audit against a public ecommerce domain and return the findings: detected platform, the checks that failed, and how the store's catalogue compares to observed category norms where the corpus can say. Reads the store's own public pages only, obeys robots.txt, and is rate limited. Use the bare domain (example.com). Never pass an internal host or an IP address.

Input Schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The storefront domain or URL to audit, e.g. 'example.com'."
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded6 tools
verifiedversion not recorded3 tools