# U2A Entity Name Matching

> U2A Entity Name Matching is a paid API for AI agents from www.u2a.com.au, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-10).

Fuzzy-matches vendor, fund, company, or account names across two datasets using normalized and conservative similarity scoring.

## Facts

- Endpoint: POST https://www.u2a.com.au/api/mcp/entity-match?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/u2a-entity-name-matching-dd8cf622
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FGWbTKS_bC-EmYoTQpQYd

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 u2a-entity-name-matching-dd8cf622 -d '<json body>'
```

Example prompt: Match my vendor list against our bank's supplier master list to find which names correspond — use a similarity threshold of 88, the name column in my vendor list is 'vendor_name' and in the bank list it's 'supplier_name'.

## When to prefer this

Use this endpoint when you need to link or reconcile entity names (vendors, funds, companies, accounts) across two datasets where names may differ due to abbreviations, typos, formatting differences, or inconsistent conventions — particularly in financial workflows like accounts payable, vendor onboarding, fund administration, or ledger reconciliation. Prefer this over exact-match joins when string equality will miss valid matches.

## Known failure modes

- Threshold set too high (e.g. 100) resulting in zero matches even for near-identical names
- leftNameField or rightNameField not matching actual keys in the provided records, causing errors
- Records arrays exceeding 1000 items per side, hitting the maxItems limit
- Names in completely different languages or scripts producing low similarity scores
- Very short or generic names (e.g. 'Corp', 'Ltd') generating false positives at low thresholds

## How this service works

Matches vendor, fund, company, or account names across two datasets using normalized and conservative fuzzy matching.

## Output

Returns matched pairs between leftRecords and rightRecords with similarity scores, indicating which names correspond across the two datasets above the specified threshold, along with any unmatched records from either side.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "threshold": {
   "type": "number",
   "default": 88,
   "maximum": 100,
   "minimum": 0,
   "description": "Minimum similarity score (0-100) to count as a match. Higher means stricter."
  },
  "leftRecords": {
   "type": "array",
   "items": {
    "type": "object"
   },
   "maxItems": 1000,
   "description": "Records whose names you want to match, e.g. your vendor list (max 1000)."
  },
  "rightRecords": {
   "type": "array",
   "items": {
    "type": "object"
   },
   "maxItems": 1000,
   "description": "Records to match against, e.g. a bank or supplier master list (max 1000)."
  },
  "leftNameField": {
   "type": "string",
   "description": "Field in leftRecords that holds the company, fund or account name."
  },
  "rightNameField": {
   "type": "string",
   "description": "Field in rightRecords that holds the name to compare against."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/u2a-entity-name-matching-dd8cf622/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from www.u2a.com.au](https://www.zero.xyz/host/www.u2a.com.au/llms.txt)