# zFinia Intelligence (remote · api.zfinia.com)

Machine-economy newswire and paid changes-since for agents. MCP is challenge-handoff, not a wallet.

- Trust score: 70/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-29

## Components

- remote · `api.zfinia.com`: 70/100 (this document), [markdown](https://verifymcp.io/servers/com-zfinia-api-intelligence/api.md), [page](https://verifymcp.io/servers/com-zfinia-api-intelligence/api)

## Channel facts

- Endpoint: `https://api.zfinia.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-29.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 7 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 54/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1639 tokens (~234/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 63/100
  - Stability observed for 19 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 81/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 32% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the zFinia Intelligence MCP server?

zFinia Intelligence is a hosted endpoint at https://api.zfinia.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-zfinia-api-intelligence 'https://api.zfinia.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-zfinia-api-intelligence": {
      "url": "https://api.zfinia.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-zfinia-api-intelligence": {
      "type": "http",
      "url": "https://api.zfinia.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-zfinia-api-intelligence]
url = "https://api.zfinia.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-zfinia-api-intelligence": {
      "type": "remote",
      "url": "https://api.zfinia.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-zfinia-api-intelligence --url 'https://api.zfinia.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-zfinia-api-intelligence:
    url: "https://api.zfinia.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-zfinia-api-intelligence": {
      "Transport": "http",
      "Url": "https://api.zfinia.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-zfinia-api-intelligence -t streamable-http -u 'https://api.zfinia.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-zfinia-api-intelligence": {
      "type": "http",
      "url": "https://api.zfinia.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-29 (score 70, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 1401 → 1639
- [functional] New tool “company_evidence_pack”

### 2026-09-28 (score 69, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-26 (score 68, 0)

- [functional improvement] Endpoint reachability: not serving MCP → reachable

### 2026-09-25 (score 68, +43)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 25, −43)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.47 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-09-23 (score 68, +2)

- [security] Tool “accessibility_contrast_calculator” rewrote its description, which is the text the model reads
- [security] Tool “data_compatibility_checker” rewrote its description, which is the text the model reads
- [security] Tool “machine_economy_changes_since” rewrote its description, which is the text the model reads
- [security] Tool “merchant_contract_regression_report” rewrote its description, which is the text the model reads
- [security] Tool “public_catalog_offer_evidence” rewrote its description, which is the text the model reads
- [functional] Schema quality: fair → good

### 2026-09-22 (score 66, −2)

- [security] Tool “accessibility_contrast_calculator” rewrote its description, which is the text the model reads
- [security] Tool “data_compatibility_checker” rewrote its description, which is the text the model reads
- [security] Tool “machine_economy_changes_since” rewrote its description, which is the text the model reads
- [security] Tool “merchant_contract_regression_report” rewrote its description, which is the text the model reads
- [security] Tool “public_catalog_offer_evidence” rewrote its description, which is the text the model reads
- [functional] Schema quality: good → fair
- [functional] MCP protocol: Implements a current MCP spec version (2026-07-28).
- [functional] MCP protocol version: 2025-11-25 → 2026-07-28
- [cosmetic] Tool “merchant_contract_regression_report” changed its title: merchant contract regression report → Merchant Contract Regression Report

## MCP tools (7)

### `company_evidence_pack` (~164 tokens)

Company Evidence Pack

Use this when an agent needs to vet a company by its website domain before outreach, onboarding or payment. Returns legal name, LEI, SEC CIK, industry, HQ, founding year, domain age, email provider and SPF/DMARC, public role emails and socials, plus an OFAC SDN and EU sanctions entity-name screen. Every field cites its source; unknowns are null with a reason. Company data only, no personal contacts. Unresolvable domains are not charged. Pay 60000 atomic USDC on Base via exact x402. MCP does not pay; it provides a challenge handoff.

Input parameters:

- `domain` (string, required): Company website domain or URL, e.g. "stripe.com" or "https://www.stripe.com/about".

Output parameters:

- `confidence`
- `contact` (object)
- `description` (string|null)
- `domain` (string)
- `domain_facts` (object)
- `employees` (integer|null)
- `evidence` (array)
- `founded` (string|null)
- `headquarters` (object)
- `industry` (string|null)
- `legal_name` (string|null)
- `name` (string|null)
- `null_reasons` (object)
- `pack_version`
- `registry` (object)
- `request_id` (string): Delivery request identifier; also returned in x-foundry-request-id.
- `resolved_url` (string|null)
- `retrieved_at` (string)
- `sanctions` (object)
- `service_id` (string): Canonical service identifier.
- `service_version` (string): Version of the invoked service.
- `socials` (object)
- `tech_hints` (array)

### `accessibility_contrast_calculator` (~120 tokens)

Accessibility Contrast Calculator

Calculate WCAG 2.x sRGB contrast for one caller-supplied foreground/background pair of hex colours (#RRGGBB). Returns JSON with the contrast ratio and AA/AAA threshold booleans for normal or large text. Does not assess a whole interface, support alpha colours or certify accessibility. Pay 1000 atomic USDC on Base via exact x402. MCP does not pay; it provides a challenge handoff.

Input parameters:

- `background` (string, required)
- `foreground` (string, required)
- `large_text` (boolean, required)

Output parameters:

- `contrast_ratio` (number)
- `large_text` (boolean)
- `limitations` (array)
- `request_id` (string): Delivery request identifier; also returned in x-foundry-request-id.
- `service_id` (string): Canonical service identifier.
- `service_version` (string): Version of the invoked service.
- `wcag_aa` (boolean)
- `wcag_aaa` (boolean)

### `data_compatibility_checker` (~140 tokens)

Data Compatibility Checker

Compare caller-supplied source and target flat field schemas before ingestion, migration, CI deployment or machine-to-machine handoff. Returns a deterministic JSON mismatch report with type incompatibilities, missing required fields, nullability warnings and remediation codes. Does not fetch data or validate nested schemas, data values or runtime API behaviour. Pay 3000 atomic USDC on Base via exact x402. MCP does not pay; it provides a challenge handoff.

Input parameters:

- `canonicalization` (string)
- `comparison_mode` (string)
- `contract_version` (string)
- `source_fields` (array, required)
- `target_fields` (array, required)

Output parameters:

- `assumptions` (array)
- `canonicalization` (object)
- `checked_source_fields` (integer)
- `checked_target_fields` (integer)
- `comparison_mode` (string)
- `compatible` (boolean)
- `contract_version` (string)
- `issue_count` (integer)
- `issues` (array)
- `limitations` (array)
- `remediations` (array)
- `request_id` (string): Delivery request identifier; also returned in x-foundry-request-id.
- `service_id` (string): Canonical service identifier.
- `service_version` (string): Version of the invoked service.

### `machine_economy_changes_since` (~194 tokens)

Machine Economy Changes Since

Return curated machine-economy developments covering x402 and agent commerce after a supplied cursor or since value. This delta feed includes material additions, corrections and retractions with provenance and nextCursor for caller-managed polling; an empty result is valid. No transaction feed, built-in scheduler, generic web search or exhaustive ecosystem monitoring. Pay 10000 atomic USDC on Base via exact x402. MCP does not pay; it provides a challenge handoff.

Input parameters:

- `cursor` (string): Previous nextCursor (opaque or ISO-8601). Required for the paid delta unless since is set. Pass this back on the next poll.
- `include_high_resolution` (boolean): When true, paid items include full evidence fields already present on the public newswire item.
- `maxItems` (integer)
- `since` (string): Alias of cursor. Use the previous nextCursor so only later material changes are returned.

Output parameters:

- `count` (integer)
- `generatedAt` (string)
- `highResolution` (boolean)
- `items` (array)
- `marketMovements` (object)
- `nextCursor` (string)
- `priceAtomic` (string)
- `product` (string)
- `request_id` (string): Delivery request identifier; also returned in x-foundry-request-id.
- `schema` (string)
- `schemaVersion` (string)
- `service_id` (string): Canonical service identifier.
- `service_version` (string): Version of the invoked service.
- `since` (string)
- `truncated` (boolean)
- `usageRights` (string)

### `merchant_contract_regression_report` (~130 tokens)

Merchant Contract Regression Report

Compare supplied baseline/current merchant API contracts for CI review. Returns a structured diff report with hashes, remediation, route/method checks, network/asset/payee policy checks, flat input/output compatibility and declared current price against the buyer maximum. No URL fetching, live or future-price guarantee, security audit or CI enforcement. Pay 50000 atomic USDC on Base via exact x402. MCP does not pay; it provides a challenge handoff.

Input parameters:

- `baseline` (object, required)
- `current` (object, required)
- `merchant_service_id` (string, required)
- `policy` (object, required)

Output parameters:

- `checked_at` (string): Server evaluation time; distinct from caller-supplied observation times.
- `checks` (array)
- `conclusion` (string)
- `coverage` (object)
- `limitations` (array)
- `merchant_service_id` (string)
- `report_version` (string)
- `request_id` (string): Delivery request identifier; also returned in x-foundry-request-id.
- `security_audit_performed` (boolean)
- `service_id` (string): Canonical service identifier.
- `service_version` (string): Version of the invoked service.
- `snapshot` (object)

### `foundry_outcome_router` (~350 tokens)

Foundry Outcome Router

Use when you need an outcome and do not already know which zFinia utility to call. Send objective (aliases: goal, task, outcome, query) plus inputs. Top-level colour/field/html/cursor keys fold into inputs. tools/call quotes first and returns PAYMENT_REQUIRED for an already-live x402 resource at that resource's unchanged price (contrast 1000, DCC 3000, catalog-offer 100000, changes-since 10000). Batches are sequential pays on those same live rails. POST /v1/router/quote is unpaid. No URL fetching. MCP does not pay. GET /v1/router for the free contract.

Input parameters:

- `buyer_metadata` (object): Optional non-secret buyer hints. Secret-like keys are stripped and never persisted.
- `evidence` (string)
- `freshness` (string)
- `inputs` (object): Caller-supplied facts required to produce the outcome. Do not send secrets or ask Foundry to fetch URLs.
- `latency` (string)
- `max_price` (string): Optional maximum USDC atomic units the buyer will pay.
- `objective` (string, required): Outcome the buyer needs. Foundry chooses the execution plan; do not describe supplier topology. goal, task, outcome, and query are accepted aliases. Product names, service IDs, and live routes are va…
- `preferred_protocol` (string)
- `required_output` (object): Optional desired output shape or fields.

Output parameters:

- `economics` (object)
- `evidence` (object)
- `execution_id` (string)
- `latency_ms` (number)
- `limitations` (array)
- `outcome` (string)
- `plan` (object)
- `request_fingerprint` (string)
- `result` (object)
- `status` (string)
- `value_add` (object)

### `public_catalog_offer_evidence` (~118 tokens)

Catalog Offer Evidence Extractor

Extract schema.org Product JSON-LD structured data from caller-supplied authorized public product-page HTML. Returns deterministic normalized Product/Offer JSON, including supplied price and currency when present, with source HTML and record SHA-256 hashes. Performs no URL fetching or browser execution; hashes do not prove authenticity and supplied prices may be stale. Pay 100000 atomic USDC on Base via exact x402. MCP does not pay; it provides a challenge handoff.

Input parameters:

- `html` (string, required)
- `source_url` (string, required)

Output parameters:

- `capability_id`
- `evidence` (object)
- `product` (object)
- `source` (object)
- `version` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-zfinia-api-intelligence/api#diagnostics

## Score history

- 2026-09-29: 70
- 2026-09-28: 69
- 2026-09-27: 69
- 2026-09-26: 68
- 2026-09-25: 68
- 2026-09-24: 25
- 2026-09-23: 68
- 2026-09-22: 66
- 2026-09-21: 68
- 2026-09-20: 67
- 2026-09-19: 67
- 2026-09-18: 66
- 2026-09-17: 66
- 2026-09-16: 65
- 2026-09-15: 65
- 2026-09-14: 65
- 2026-09-13: 64
- 2026-09-12: 64
- 2026-09-11: 63
- 2026-09-10: 63
- 2026-09-09: 44
- 2026-09-08: 25

## Common questions

### What is the zFinia Intelligence MCP server?

zFinia Intelligence is an MCP server listed in the public MCP registry as com.zfinia.api/intelligence. Machine-economy newswire and paid changes-since for agents. MCP is challenge-handoff, not a wallet. This page covers its hosted endpoint (https://api.zfinia.com/mcp).

### Is the zFinia Intelligence MCP server safe to use?

zFinia Intelligence scores 70 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the zFinia Intelligence MCP server expose?

zFinia Intelligence exposes 7 tools: company_evidence_pack, accessibility_contrast_calculator, data_compatibility_checker, machine_economy_changes_since, merchant_contract_regression_report, and 2 more. Their descriptions and schemas cost roughly 1,216 tokens of context every time the server is loaded.

### Does the zFinia Intelligence MCP server require authentication?

No. We connected to zFinia Intelligence without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the zFinia Intelligence MCP server still maintained?

zFinia Intelligence is still listed as active in the MCP registry. We last reached this channel on 29 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.zfinia.com/mcp
- Website: https://zfinia.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-zfinia-api-intelligence/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-zfinia-api-intelligence/api.json
- HTML version of this page: https://verifymcp.io/servers/com-zfinia-api-intelligence/api