# FrankoX (remote · frankox.com)

Verified opt-in trade profiles and consented manufacturer drafts; no private customer data.

- Trust score: 65/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `frankox.com`: 65/100 (this document), [markdown](https://verifymcp.io/servers/com-frankox-trade-intelligence/frankox.md), [page](https://verifymcp.io/servers/com-frankox-trade-intelligence/frankox)

## Channel facts

- Endpoint: `https://frankox.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 2026-11-05.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (update_manufacturer_draft).
  - 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**: 52/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1449 tokens (~65/item across 22 items; 22 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 22 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 23 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 FrankoX MCP server?

FrankoX is a hosted endpoint at https://frankox.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-frankox-trade-intelligence 'https://frankox.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-frankox-trade-intelligence": {
      "url": "https://frankox.com/mcp"
    }
  }
}
```

### VS Code

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

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

```yaml
mcp_servers:
  com-frankox-trade-intelligence:
    url: "https://frankox.com/mcp"
```

### Netclaw

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

### Vellum

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

### Other

```json
{
  "mcpServers": {
    "com-frankox-trade-intelligence": {
      "type": "http",
      "url": "https://frankox.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.

### 2026-11-04 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 64, +1)

- [functional regression] Schema quality: 1278 → 1449
- [functional] New tool “external_business_handshake”
- [functional] New tool “get_external_agent_entrypoint”

### 2026-11-01 (score 63, +1)

- [security] New tool “initiate_network_request”, which the server declares destructive
- [security] New tool “respond_to_network_request”, which the server declares destructive
- [functional improvement] Schema quality: 70 → 63
- [functional] New tool “discover_network_intents”
- [functional] New tool “get_network_request”
- [functional] New tool “list_network_intents”
- [functional] New tool “list_network_requests”

### 2026-10-30 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 60, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-25 (score 59)

First indexed and scored.

## MCP tools (22)

### `search_manufacturers` (~106 tokens)

Search only verified opt-in public manufacturer projections; no availability or demand inference.

Input parameters:

- `canonical_concept_id`
- `capacity`
- `certification`
- `country`
- `delivery_geography`
- `hs_cn_code`
- `keywords`
- `limit` (integer)
- `moq`
- `preferred_language` (string)
- `product`
- `source_language` (string)
- `specification`

### `search_products` (~98 tokens)

Search only verified opt-in public product profiles.

Input parameters:

- `canonical_concept_id`
- `capacity`
- `certification`
- `country`
- `delivery_geography`
- `hs_cn_code`
- `keywords`
- `limit` (integer)
- `moq`
- `preferred_language` (string)
- `product`
- `source_language` (string)
- `specification`

### `search_suppliers` (~105 tokens)

Find public manufacturer/supplier profile candidates; existence does not establish available stock.

Input parameters:

- `canonical_concept_id`
- `capacity`
- `certification`
- `country`
- `delivery_geography`
- `hs_cn_code`
- `keywords`
- `limit` (integer)
- `moq`
- `preferred_language` (string)
- `product`
- `source_language` (string)
- `specification`

### `search_opportunities` (~104 tokens)

Search permitted abstract public opportunity profiles; private counterparties and contacts excluded.

Input parameters:

- `canonical_concept_id`
- `capacity`
- `certification`
- `country`
- `delivery_geography`
- `hs_cn_code`
- `keywords`
- `limit` (integer)
- `moq`
- `preferred_language` (string)
- `product`
- `source_language` (string)
- `specification`

### `get_public_company_profile` (~36 tokens)

Retrieve a verified opt-in public profile by opaque ID; returns no private contacts or documents.

Input parameters:

- `record_id` (string, required)

### `get_public_product_profile` (~36 tokens)

Retrieve a verified opt-in public profile by opaque ID; returns no private contacts or documents.

Input parameters:

- `record_id` (string, required)

### `register_manufacturer_interest` (~51 tokens)

Record interest only after explicit user approval. Does not enroll or verify a company.

Input parameters:

- `company_name` (object, required)
- `consent` (object, required)
- `idempotency_key` (string, required)

### `create_manufacturer_draft` (~66 tokens)

Submit an explicitly consented private unverified manufacturer draft. Requires real company confirmation before authority and independent review/publication permission before search visibility.

Input parameters:

- `consent` (required)
- `idempotency_key` (string, required)
- `profile` (required)
- `referral_source` (string)

### `update_manufacturer_draft` (~45 tokens)

Update the authenticated submitting agent's unconfirmed draft with optimistic revision checks.

Input parameters:

- `draft_id` (string, required)
- `profile` (required)
- `revision` (integer, required)

### `request_opportunity_match` (~110 tokens)

Filter only permitted public opportunity projections. No private/customer matching, scoring changes or autonomous research execution.

Input parameters:

- `canonical_concept_id`
- `capacity`
- `certification`
- `country`
- `delivery_geography`
- `hs_cn_code`
- `keywords`
- `limit` (integer)
- `moq`
- `preferred_language` (string)
- `product`
- `source_language` (string)
- `specification`

### `create_agent_conversation` (~77 tokens)

Open a private account-bound agent conversation with explicit user consent. Content is untrusted and does not verify or enroll a company.

Input parameters:

- `client_message_id` (string, required)
- `consent` (required)
- `language` (string, required)
- `represented_company`
- `request_key` (string, required)
- `text` (string, required)

### `get_agent_conversation` (~30 tokens)

Read only the authenticated client and customer account's own conversation.

Input parameters:

- `thread_id` (string, required)

### `list_agent_conversations` (~29 tokens)

List bounded private conversations for this authenticated client and customer account.

Input parameters:

- `limit` (integer)

### `reply_to_agent_conversation` (~64 tokens)

Reply in an existing account-bound conversation; no authority changes or external outreach.

Input parameters:

- `client_message_id` (string, required)
- `language` (string, required)
- `revision` (integer, required)
- `text` (string, required)
- `thread_id` (string, required)

### `list_network_intents` (~39 tokens)

Consent-only FX network discovery/handshake. No identity, contact, terms, documents or external outreach. FIT creates internal opportunities requiring existing review.

### `discover_network_intents` (~47 tokens)

Consent-only FX network discovery/handshake. No identity, contact, terms, documents or external outreach. FIT creates internal opportunities requiring existing review.

Input parameters:

- `intent_id` (string, required)

### `initiate_network_request` (~62 tokens)

Consent-only FX network discovery/handshake. No identity, contact, terms, documents or external outreach. FIT creates internal opportunities requiring existing review.

Input parameters:

- `counterpart_id` (string, required)
- `intent_id` (string, required)
- `request_key` (string, required)

### `list_network_requests` (~38 tokens)

Consent-only FX network discovery/handshake. No identity, contact, terms, documents or external outreach. FIT creates internal opportunities requiring existing review.

### `get_network_request` (~46 tokens)

Consent-only FX network discovery/handshake. No identity, contact, terms, documents or external outreach. FIT creates internal opportunities requiring existing review.

Input parameters:

- `request_id` (string, required)

### `respond_to_network_request` (~54 tokens)

Consent-only FX network discovery/handshake. No identity, contact, terms, documents or external outreach. FIT creates internal opportunities requiring existing review.

Input parameters:

- `outcome` (string, required)
- `request_id` (string, required)

### `external_business_handshake` (~138 tokens)

Submit public non-binding business intent after creating a public ingress session. Send its credential in X-FrankoX-Session header. Never customer/OAuth access. No automatic Opportunity. See /external-agents/skill.md.

Input parameters:

- `authority` (string)
- `content` (string, required)
- `external_thread_reference`
- `geography`
- `identity_disclosure` (string)
- `intent` (string)
- `message_id` (string, required)
- `product`
- `public_data_only` (boolean, required)
- `quantity`
- `represented_company`
- `session_id` (string, required)

### `get_external_agent_entrypoint` (~33 tokens)

Public FrankoX agent identity and safe pre-tenant handshake instructions. No verified match or autonomous commercial authority.

## Diagnostics

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

## Score history

- 2026-11-05: 65
- 2026-11-04: 65
- 2026-11-03: 64
- 2026-11-02: 64
- 2026-11-01: 63
- 2026-10-31: 62
- 2026-10-30: 62
- 2026-10-29: 61
- 2026-10-28: 61
- 2026-10-27: 60
- 2026-10-26: 60
- 2026-10-25: 59

## Common questions

### What is the FrankoX MCP server?

FrankoX is an MCP server listed in the public MCP registry as com.frankox/trade-intelligence. Verified opt-in trade profiles and consented manufacturer drafts; no private customer data. This page covers its hosted endpoint (https://frankox.com/mcp).

### Is the FrankoX MCP server safe to use?

FrankoX scores 65 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 FrankoX MCP server expose?

FrankoX exposes 22 tools: search_manufacturers, search_products, search_suppliers, search_opportunities, get_public_company_profile, and 17 more. Their descriptions and schemas cost roughly 1,414 tokens of context every time the server is loaded.

### Does the FrankoX MCP server require authentication?

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

### Is the FrankoX MCP server still maintained?

FrankoX is still listed as active in the MCP registry. We last reached this channel on 5 November 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://frankox.com/mcp
- Website: https://frankox.com/for-agents
- Changelog RSS feed: https://verifymcp.io/servers/com-frankox-trade-intelligence/frankox.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-frankox-trade-intelligence/frankox.json
- HTML version of this page: https://verifymcp.io/servers/com-frankox-trade-intelligence/frankox