# entity-resolve

> entity-resolve is a paid API for AI agents from entity-resolve.x402supply.com, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Fuzzy-deduplicates a list of records into clusters of likely-duplicate entities, returning a merged canonical record per cluster with a confidence score.

## Facts

- Endpoint: POST https://entity-resolve.x402supply.com/mcp
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/entity-resolve-91d13734
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_S5RdW11nXlyQVRw5TlBk2

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability entity-resolve-91d13734 -d '<json body>'
```

Example prompt: Take this list of 500 customer records — some have slightly different spellings of the same name or phone number — and cluster them into groups of likely duplicates, giving me a merged canonical record and confidence score for each cluster.

## When to prefer this

Choose this endpoint when you need deterministic, auditable entity deduplication without LLM involvement — especially when reproducibility matters and you can't risk non-deterministic AI output. Ideal for cleaning CRM exports, merging data from multiple sources, or preprocessing datasets before analytics. Prefer this over LLM-based matching when you need consistent results across repeated runs or when cost predictability is important at $0.02 per call.

## Known failure modes

- Records with no overlapping tokens may not be blocked together and will be missed
- Very short or ambiguous names may produce false positives or false negatives
- Missing email/phone fields reduce match precision since those fields get exact matching
- Threshold misconfiguration can cause over-merging or under-merging of clusters
- Malformed input records (missing required fields) may cause processing errors
- Extremely large record lists may exceed per-call size limits

## How this service works

Fuzzy-dedupe a list of records into clusters of likely-duplicate entities. Blocks by normalized token prefix, scores with Jaro-Winkler + token-set matching (exact on email/phone), unions matches above threshold, and returns a merged canonical record per cluster with a confidence score. Deterministic, no LLM calls.

## Output

A list of entity clusters, each containing the matched records grouped together, a merged canonical record synthesizing the best available field values, and a confidence score (0–1) indicating how certain the algorithm is that the records refer to the same entity. No LLM inference is involved — results are deterministic based on Jaro-Winkler + token-set scoring and union-find clustering above a configurable threshold.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/entity-resolve-91d13734/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from entity-resolve.x402supply.com](https://www.zero.xyz/host/entity-resolve.x402supply.com/llms.txt)