# com.crossingkeyintelligence/crossingkey-mcp (remote · mcp.crossingkeyintelligence.com)

CrossingKey MCP for agent commerce, x402 payments, deterministic execution, and verifiable receipts.

- Trust score: 73/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `mcp.crossingkeyintelligence.com`: 73/100 (this document), [markdown](https://verifymcp.io/servers/com-crossingkeyintelligence-crossingkey-mcp/mcp.md), [page](https://verifymcp.io/servers/com-crossingkeyintelligence-crossingkey-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.crossingkeyintelligence.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.3.0`

## 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 2026-09-21.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 85/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1476 tokens (~82/item across 18 items; 18 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 6 days we've observed: 18 tool removals, 0 breaking changes, 0 auth/transport breaks, 10 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 18 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the com.crossingkeyintelligence/crossingkey-mcp server?

com.crossingkeyintelligence/crossingkey-mcp is a hosted endpoint at https://mcp.crossingkeyintelligence.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-crossingkeyintelligence-crossingkey-mcp 'https://mcp.crossingkeyintelligence.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-crossingkeyintelligence-crossingkey-mcp": {
      "url": "https://mcp.crossingkeyintelligence.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-crossingkeyintelligence-crossingkey-mcp": {
      "type": "http",
      "url": "https://mcp.crossingkeyintelligence.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-crossingkeyintelligence-crossingkey-mcp]
url = "https://mcp.crossingkeyintelligence.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-crossingkeyintelligence-crossingkey-mcp --url 'https://mcp.crossingkeyintelligence.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-crossingkeyintelligence-crossingkey-mcp:
    url: "https://mcp.crossingkeyintelligence.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-crossingkeyintelligence-crossingkey-mcp": {
      "Transport": "http",
      "Url": "https://mcp.crossingkeyintelligence.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-crossingkeyintelligence-crossingkey-mcp -t streamable-http -u 'https://mcp.crossingkeyintelligence.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-crossingkeyintelligence-crossingkey-mcp": {
      "type": "http",
      "url": "https://mcp.crossingkeyintelligence.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.

### 2026-09-21 (score 73, +50)

- [security regression] Stability: unverified → fail
- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass

### 2026-09-20 (score 23, −50)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: fail → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-09-19 (score 73, 0)

- [security regression] A breaking change shipped without a version bump: still 2.4.0
- [security regression] Tool “check_requirements” was removed
- [security regression] Tool “crossingkey.describe” was removed
- [security regression] Tool “discover_provider” was removed
- [security regression] Tool “estimate_cost” was removed
- [security regression] Tool “execution_preflight” was removed
- [security regression] Tool “fulfillment.get” was removed
- [security regression] Tool “fulfillment.status” was removed
- [security regression] Tool “get_offer” was removed
- [security regression] Tool “get_request_credit_links” was removed
- [security regression] Tool “list_capabilities” was removed
- [security regression] Tool “list_offers” was removed
- [security regression] Tool “list_request_services” was removed
- [security regression] Tool “payment.verify_onchain” was removed
- [security regression] Tool “preview_result_schema” was removed
- [security regression] Tool “xkey_validate_intake” was removed
- [security] Tool “capabilities.list” rewrote its description, which is the text the model reads
- [security] Tool “capability.quote” rewrote its description, which is the text the model reads
- [security] Tool “purchase.status” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: 1872 → 1476
- [functional] New tool “cost.estimate”
- [functional] New tool “credits.options”
- [functional] New tool “execution.preflight”
- [functional] New tool “offers.list”
- [functional] New tool “payment.verify”
- [functional] New tool “provider.describe”
- [functional] New tool “requirements.check”
- [functional] New tool “result.preview”
- [functional] New tool “services.list”
- [functional] New tool “xkey.validate”

### 2026-09-18 (score 73, +50)

- [security regression] Stability: unverified → fail
- [security regression] Tool “get_fulfillment_status” was removed
- [security regression] Tool “get_stripe_checkout_link” was removed
- [security regression] Tool “list_stripe_offers” was removed
- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [security] Tool “capabilities.list” rewrote its description, which is the text the model reads
- [security] Tool “capability.get” rewrote its description, which is the text the model reads
- [security] Tool “capability.quote” rewrote its description, which is the text the model reads
- [security] Tool “check_requirements” rewrote its description, which is the text the model reads
- [security] Tool “crossingkey.describe” rewrote its description, which is the text the model reads
- [security] Tool “discover_provider” rewrote its description, which is the text the model reads
- [security] Tool “entitlement.inspect” rewrote its description, which is the text the model reads
- [security] Tool “estimate_cost” rewrote its description, which is the text the model reads
- [security] Tool “execution_preflight” rewrote its description, which is the text the model reads
- [security] Tool “fulfillment.get” rewrote its description, which is the text the model reads
- [security] Tool “fulfillment.status” rewrote its description, which is the text the model reads
- [security] Tool “get_offer” rewrote its description, which is the text the model reads
- [security] Tool “get_request_credit_links” rewrote its description, which is the text the model reads
- [security] Tool “health” rewrote its description, which is the text the model reads
- [security] Tool “list_capabilities” rewrote its description, which is the text the model reads
- [security] Tool “list_offers” rewrote its description, which is the text the model reads
- [security] Tool “list_request_services” rewrote its description, which is the text the model reads
- [security] Tool “payment.methods” rewrote its description, which is the text the model reads
- [security] Tool “payment.verify_onchain” rewrote its description, which is the text the model reads
- [security] Tool “preview_result_schema” rewrote its description, which is the text the model reads
- [security] Tool “purchase.status” rewrote its description, which is the text the model reads
- [security] Tool “receipt.verify” rewrote its description, which is the text the model reads
- [security] Tool “xkey_validate_intake” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 32 → 81
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: 0% → 100%
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] Schema quality: good → excellent
- [functional] Server version: 2.3.0 → 2.4.0
- [cosmetic] “capability.get” reworded the description of “name”
- [cosmetic] “capability.quote” reworded the description of “name”
- [cosmetic] “check_requirements” reworded the description of “id”
- [cosmetic] “entitlement.inspect” reworded the description of “id”
- [cosmetic] “estimate_cost” reworded the description of “id”
- [cosmetic] “execution_preflight” reworded the description of “id”
- [cosmetic] “fulfillment.get” reworded the description of “idempotency_key”
- [cosmetic] “fulfillment.status” reworded the description of “idempotency_key”
- [cosmetic] “get_offer” reworded the description of “id”
- [cosmetic] “list_capabilities” reworded the description of “access”
- [cosmetic] “list_offers” reworded the description of “kind”
- [cosmetic] “list_offers” reworded the description of “max_price_usd”
- [cosmetic] “list_offers” reworded the description of “query”
- [cosmetic] “payment.verify_onchain” reworded the description of “receiptId”
- [cosmetic] “payment.verify_onchain” reworded the description of “txHash”
- [cosmetic] “preview_result_schema” reworded the description of “id”
- [cosmetic] “purchase.status” reworded the description of “idempotency_key”
- [cosmetic] “receipt.verify” reworded the description of “receipt”
- [cosmetic] “xkey_validate_intake” reworded the description of “idempotency_key”
- [cosmetic] “xkey_validate_intake” reworded the description of “raw_intake”

### 2026-09-17 (score 23, −44)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.03 → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-09-16 (score 67, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-15 (score 67)

First indexed and scored.

## MCP tools (18)

### `provider.describe` (~72 tokens)

Discover CrossingKey Intelligence

FREE, read-only provider discovery. Use this first to learn CrossingKey identity, commerce model, payment rails, authority boundaries, and recommended next actions; it never creates a payment or executes paid work. For offer-specific data use offers.list and capability.get, and for x402 terms use capability.get/capability.quote.

### `offers.list` (~139 tokens)

Discover CrossingKey offers

FREE, read-only canonical offer search. Use this to find public digital or service offers by query, kind, or maximum USD price before payment; it returns metadata only and creates no checkout session. Use capability.get only for x402 capability detail; offer details are returned by offers.list.

Input parameters:

- `kind` (string): Optional offer-kind filter: 'all', 'digital', or 'service'. Defaults to 'all'.
- `max_price_usd` (number): Optional inclusive maximum advertised USD price, from 0 through 1000000.
- `query` (string): Optional case-insensitive text search across public offer metadata; 1-160 characters.

### `cost.estimate` (~79 tokens)

Estimate exact known cost

FREE, read-only cross-domain price lookup. Supply an offer or capability identifier to return the currently advertised USD price or request-credit cost; no payment, reservation, or credit consumption occurs. For x402 challenge terms use capability.quote instead.

Input parameters:

- `id` (string, required): Exact offer or paid-capability identifier returned by discovery; 1-160 characters.

### `result.preview` (~86 tokens)

Preview result or fulfillment schema

FREE, read-only result preview. Supply an offer or capability identifier to see the expected fulfillment or output shape without exposing paid content or executing work. Use this after offers.list or capabilities.list when an agent needs to evaluate the result contract before authorization.

Input parameters:

- `id` (string, required): Exact offer or paid-capability identifier whose result or fulfillment shape should be previewed; 1-160 characters.

### `requirements.check` (~78 tokens)

Check purchase or execution requirements

FREE, read-only prerequisite check. Supply an offer or capability identifier to receive payment, authorization, fulfillment, and idempotency requirements without creating a payment. Use execution.preflight for the final machine-readable go/no-go decision.

Input parameters:

- `id` (string, required): Exact offer or paid-capability identifier whose prerequisites should be checked; 1-160 characters.

### `execution.preflight` (~97 tokens)

Preflight an agent purchase or execution

FREE, read-only final preflight before any paid action. Supply an offer or capability identifier to receive payment method, exact advertised price, readiness, safety warnings, and next action; this tool never charges or executes. Call it after discovery and requirement checks, not as a replacement for paid execution.

Input parameters:

- `id` (string, required): Exact offer or paid-capability identifier to evaluate immediately before payment or credit-consuming execution; 1-160 characters.

### `credits.options` (~53 tokens)

Get request-credit payment links

FREE, read-only prepaid-credit purchase discovery. Returns available request-credit packs and their existing Stripe Payment Links; it does not open a checkout session or spend funds. Use this only when prepaid request credits are the intended payment rail.

### `services.list` (~49 tokens)

List paid request services

FREE, read-only service catalog. Returns only request services explicitly approved by the server's safety process and may legitimately be empty; it creates no order or payment. Use this when evaluating approved request-service availability.

### `capabilities.list` (~55 tokens)

FREE, read-only x402 capability list. Use this only for deterministic machine-commerce capabilities priced for x402 execution; it does not list the full CrossingKey offer/service catalog and never executes a capability. For public offers use offers.list.

### `capability.get` (~77 tokens)

FREE, read-only x402 capability detail lookup. Supply the exact capability name returned by capabilities.list to receive one deterministic capability definition and advertised price; no payment or execution occurs. Use capability.quote when x402 challenge requirements are needed.

Input parameters:

- `name` (string, required): Exact deterministic x402 capability name returned by capabilities.list; 1-160 characters.

### `capability.quote` (~82 tokens)

FREE, read-only x402 quote/challenge lookup. Supply the exact capability name returned by capabilities.list to receive v1 and v2 payment requirements without execution or settlement. Use capability.get for metadata only and execution.preflight for the cross-domain authorization decision.

Input parameters:

- `name` (string, required): Exact deterministic x402 capability name returned by capabilities.list; 1-160 characters.

### `payment.methods` (~54 tokens)

FREE, read-only payment-rail discovery. Returns supported Stripe, prepaid-credit, and x402 rails plus the receiver-only wallet authority boundary; it never signs or spends. Use this when selecting a payment rail before any authorization step.

### `purchase.status` (~86 tokens)

FREE, read-only x402 purchase-status lookup. Supply the original idempotency key to retrieve purchase state and integrity identifiers without revealing paid result content or changing state. The response includes purchase, entitlement, and result-integrity identifiers when available.

Input parameters:

- `idempotency_key` (string, required): Original client-generated idempotency key used for the paid x402 purchase; 8-160 characters.

### `entitlement.inspect` (~74 tokens)

FREE, read-only entitlement inspection. Supply a CrossingKey entitlement identifier to return current entitlement state without granting execution, download access, or paid result content. Use purchase.status when only an idempotency key is available.

Input parameters:

- `id` (string, required): CrossingKey entitlement identifier returned by a successful paid purchase; 1-200 characters.

### `receipt.verify` (~77 tokens)

FREE, read-only receipt integrity verification. Supply a CrossingKey receipt object to recompute and compare its deterministic result hash; this performs no payment, entitlement mutation, or network settlement. A true result verifies integrity only, not external payment finality.

Input parameters:

- `receipt` (object, required): Complete CrossingKey receipt object whose deterministic integrity binding should be recomputed.

### `health` (~52 tokens)

FREE, read-only MCP readiness check. Returns service, Stripe, machine-commerce, mainnet-gate, and receiver-only wallet readiness flags without contacting payment rails or changing state. Use this for operational readiness, not purchase status.

### `payment.verify` (~129 tokens)

Verify Base USDC payment on chain

FREE, read-only Base USDC verification. Provide a Base transaction hash, a CrossingKey receipt ID, or both to verify the receiver transfer and optionally reconcile an existing receipt; it never signs, sends, settles, swaps, bridges, or spends funds. Use receipt.verify for local receipt integrity without chain lookup.

Input parameters:

- `receiptId` (string): Optional CrossingKey receipt identifier beginning with ck_. Provide receiptId, txHash, or both.
- `txHash` (string): Optional Base transaction hash in 0x-prefixed 32-byte hexadecimal form. Provide txHash, receiptId, or both.

### `xkey.validate` (~137 tokens)

Validate structured XKEY intake

PAID bounded intake validation. Requires an authenticated prepaid-credit principal, an 8-160 character idempotency key, and 2-100000 characters of raw intake; one credit is committed only on verified success, while safe validation failures release the reservation. Do not call speculatively; use requirements.check and execution.preflight first.

Input parameters:

- `idempotency_key` (string, required): Unique client-generated key for safe retry/deduplication; 8-160 characters. Reuse only when retrying the same intake.
- `raw_intake` (string, required): Raw intake text to validate and normalize; 2-100000 characters.

## Diagnostics

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

## Score history

- 2026-09-21: 73
- 2026-09-20: 23
- 2026-09-19: 73
- 2026-09-18: 73
- 2026-09-17: 23
- 2026-09-16: 67
- 2026-09-15: 67

## Common questions

### What is the com.crossingkeyintelligence/crossingkey-mcp server?

com.crossingkeyintelligence/crossingkey-mcp is listed in the public MCP registry as com.crossingkeyintelligence/crossingkey-mcp. CrossingKey MCP for agent commerce, x402 payments, deterministic execution, and verifiable receipts. This page covers its hosted endpoint (https://mcp.crossingkeyintelligence.com/mcp).

### Is the com.crossingkeyintelligence/crossingkey-mcp server safe to use?

com.crossingkeyintelligence/crossingkey-mcp scores 73 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 com.crossingkeyintelligence/crossingkey-mcp server expose?

com.crossingkeyintelligence/crossingkey-mcp exposes 18 tools: provider.describe, offers.list, cost.estimate, result.preview, requirements.check, and 13 more. Their descriptions and schemas cost roughly 1,476 tokens of context every time the server is loaded.

### Does the com.crossingkeyintelligence/crossingkey-mcp server require authentication?

No. We connected to com.crossingkeyintelligence/crossingkey-mcp without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the com.crossingkeyintelligence/crossingkey-mcp server still maintained?

com.crossingkeyintelligence/crossingkey-mcp is still listed as active in the MCP registry. We last reached this channel on 21 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://mcp.crossingkeyintelligence.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-crossingkeyintelligence-crossingkey-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-crossingkeyintelligence-crossingkey-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-crossingkeyintelligence-crossingkey-mcp/mcp