# ai.crestsystems/counterparty-intelligence (remote · data.crestsystems.ai)

Check who your agent is about to pay over x402: real service, relayer, treasury, or buyer.

- Trust score: 69/100 (medium)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `data.crestsystems.ai`: 69/100 (this document), [markdown](https://verifymcp.io/servers/ai-crestsystems-counterparty-intelligence/data.md), [page](https://verifymcp.io/servers/ai-crestsystems-counterparty-intelligence/data)

## Channel facts

- Endpoint: `https://data.crestsystems.ai/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 2026-08-03.

- **Endpoint Security**: 11/100
  - TLS not yet verified: we couldn't open a connection to check the certificate.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS not yet verified: we couldn't read the response headers to check for it.
  - DNSSEC not yet verified: we couldn't validate it against a resolver.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but we couldn't connect to verify it.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 4 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add --transport http ai-crestsystems-counterparty-intelligence https://data.crestsystems.ai/mcp
```

### Codex

```toml
[mcp_servers.ai-crestsystems-counterparty-intelligence]
url = "https://data.crestsystems.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-crestsystems-counterparty-intelligence": {
      "type": "remote",
      "url": "https://data.crestsystems.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-crestsystems-counterparty-intelligence --url https://data.crestsystems.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-crestsystems-counterparty-intelligence:
    url: "https://data.crestsystems.ai/mcp"
```

### Other

```json
{
  "mcpServers": {
    "ai-crestsystems-counterparty-intelligence": {
      "type": "http",
      "url": "https://data.crestsystems.ai/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.

### 2026-07-31 (score 69, 0)

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

### 2026-07-29 (score 69, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] HSTS header: pass → unverified
- [security regression] DNSSEC: fail → unverified
- [security regression] Stability: 0.07 → unverified
- [security regression] Authorization: partial → unverified
- [security regression] TLS certificate: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-28 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 68, +1)

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

### 2026-07-26 (score 67)

First indexed and scored.

## MCP tools (11)

### `check_counterparty` (~109 tokens)

Check who your agent is about to pay (x402)

Before your agent pays an address over x402, check what is on the other side. Returns a plain verdict: a real service, a buyer, a relayer in the middle, or a treasury just moving funds, plus whether it is safe to pay. Free. For the full scored profile, the paid HTTP endpoint is $0.90. By Crest Deployment Systems.

Input parameters:

- `address` (string, required): the Base/EVM address your agent is about to pay (0x + 40 hex)

Output parameters:

- `address`
- `error`
- `read`
- `recommendation`
- `role`
- `safe`
- `verdict`

### `onchain_profile` (~63 tokens)

Public on-chain profile for a Base address

Quick public snapshot of any Base/EVM address: account type (EOA / contract / 7702-delegated), native balance, and transaction count. Free coverage check.

Input parameters:

- `address` (string, required): Base/EVM address (0x + 40 hex)

Output parameters:

- `account_type`
- `address`
- `error`
- `native_balance`
- `tx_count`

### `pm_counterparty` (~102 tokens)

Polymarket counterparty intelligence

Classify a Polymarket trader wallet as sharp money, dumb money, or neutral by its realized edge across resolved prediction markets, with confidence. Know who is on the other side of a prediction-market trade before your agent acts. Free; the deeper read is a $0.02 x402 HTTP call. Read-only, not betting advice. By Crest Deployment Systems.

Input parameters:

- `address` (string, required): Polymarket trader wallet (0x + 40 hex)

Output parameters:

- `address`
- `classification`
- `confidence`
- `edge`
- `error`
- `label`

### `agent_preflight` (~122 tokens)

Pre-action risk gate for any wallet

Call BEFORE your agent transfers, trades, or settles to a wallet. Returns risk_level (low/medium/high/unknown) and reason codes from Crest counterparty intelligence, so your agent skips relayers, treasuries, and dead ends. Free; the full gate (changed-since cursor + ttl for cheap per-action re-checks) is a $0.02 x402 call. Read-only, not financial advice. By Crest Deployment Systems.

Input parameters:

- `address` (string, required): wallet your agent is about to interact with (0x + 40 hex)

Output parameters:

- `address`
- `classification`
- `error`
- `free`
- `note`
- `reason_codes`
- `risk_level`

### `agent_credit` (~122 tokens)

Agent credit bureau

Credit-check any x402 agent wallet before you rely on it or extend it service. Returns economic_class (funded/active/low/drained/unknown), live USDC balance, and a creditworthiness verdict, so you know if a counterparty will pay or is about to drain to zero. Free; full read (runway, observed burn) is a $0.05 x402 call. Read-only, not financial advice. By Crest Deployment Systems.

Input parameters:

- `address` (string, required): x402 agent wallet to credit-check (0x + 40 hex)

Output parameters:

- `address`
- `creditworthy`
- `economic_class`
- `error`
- `not_advice`
- `upgrade`
- `usdc_balance`
- `verdict`

### `token_risk` (~216 tokens)

Token risk scan (the code and the people)

Call this before your agent buys, swaps, or LPs into a Base token, to check if it is a rug, honeypot, or scam. Scans the contract for dangerous powers (mint new supply, blacklist wallets, pause transfers, upgrade the code) AND checks who controls those powers, scored on the Crest settlement graph: ownership renounced, an established issuer, a multisig, or an anonymous drained wallet. The same powers are safe under a trusted controller and a rug under an anonymous one. Example: token_risk(0x4ed4e862860bed51a9570b96d89af5e1b0efefed) -> { risk_level: "low", attack_surface: 20, controller_trust: 0.65 }. Free; the full report is a $0.05 x402 call. Read-only, not financial advice. By Crest Deployment Systems.

Input parameters:

- `address` (string, required): Base ERC-20 token contract address (0x + 40 hex)

Output parameters:

- `address`
- `attack_surface`
- `confidence`
- `contract_risk`
- `control_reputation`
- `controller_trust`
- `decision`
- `error`
- `free`
- `model_version`
- `note`
- `reason_codes`
- `risk_level`
- `risk_score`
- `token`

### `crest_score` (~205 tokens)

Crest Score: two-axis agent creditworthiness

Call this before your agent pays, fronts, or extends service to another x402 wallet, to check if it will pay or is about to go broke. Two axes: solvency (will it stay funded) and liveness (will it keep paying), combined into one Crest Score with a band and a decision (ok_to_extend / monitor_or_prepay / prepay_only). Example: crest_score(0xe4a961cf1ee5b305561e38c69ed9dbd058ff036e) -> { crest_score: 89, band: "A", decision: "ok_to_extend" }. Built on the Crest settlement graph + live on-chain balance. Free; the full report (runway, monitoring cursor, change detection) is a $0.05 x402 call. Read-only, not financial advice. By Crest Deployment Systems.

Input parameters:

- `address` (string, required): x402 agent wallet to score (0x + 40 hex)

Output parameters:

- `address`
- `band`
- `confidence`
- `crest_score`
- `decision`
- `error`
- `free`
- `liveness`
- `model_version`
- `note`
- `rateable`
- `reason_codes`
- `solvency`

### `crest_passport` (~134 tokens)

Get or create your Crest agent passport

Your persistent home in the agent economy. No args = MINT a new passport (returns agent_id + a secret passport_key shown ONCE; store it). passport_key = load your own passport (reputation, stats, memory_root). agent_id = PUBLIC view of any agent. Optional wallet binds your x402 wallet to anchor reputation. Free.

Input parameters:

- `agent_id` (string): a public agent_id, to view another agent
- `passport_key` (string): your secret key, to load your own passport
- `wallet` (string): optional 0x+40hex x402 wallet to bind for reputation

Output parameters:

- `agent_id`
- `error`
- `memory_root`
- `note`
- `passport_key`
- `public`
- `reputation`

### `crest_remember` (~144 tokens)

Write a tamper-evident memory to your passport

Append a fact/decision/outcome/note to your Crest memory. Every entry is hash-chained (sha256), so your memory is provable and tamper-evident. Returns the entry hash (a receipt) and your new memory_root. Requires your passport_key. Do not store human personal data.

Input parameters:

- `content` (string, required): the memory payload (<= 8000 chars). Do not store human PII.
- `passport_key` (string, required): your secret passport key
- `source` (string): where this came from (provenance)
- `tags` (string): comma-separated tags for recall
- `type` (string, required): kind of memory

Output parameters:

- `entry_count`
- `error`
- `hash`
- `memory_root`
- `ok`

### `crest_recall` (~73 tokens)

Recall your Crest memories

Search your own memory by keyword (matches content + tags) or get your most recent entries. Requires your passport_key.

Input parameters:

- `k` (number): max results (default 10)
- `passport_key` (string, required): your secret passport key
- `query` (string): keyword to match; omit for most recent

Output parameters:

- `count`
- `error`
- `results`

### `crest_verify` (~158 tokens)

Verify another agent's Crest passport + reputation

Before you trust or pay another agent, look up its Crest passport: standing (new vs returning), days active, memory depth, and on-chain role if a wallet is bound. Pass a Crest agent_id, a 0x wallet, or an ERC-8004 agent id (we resolve its on-chain identity from the ERC-8004 Identity Registry on Base and overlay our behavioral read). Read-only, not financial advice.

Input parameters:

- `agent_id` (string): Crest agent_id to verify
- `erc8004_id` (string): an ERC-8004 agent id (tokenId) on Base, to resolve its on-chain identity + Crest behavioral read
- `wallet` (string): 0x+40hex wallet to verify

Output parameters:

- `error`
- `found`
- `not_advice`
- `onchain`
- `reputation`

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-crestsystems-counterparty-intelligence/data#diagnostics

## Score history

- 2026-08-03: 69
- 2026-08-02: 69
- 2026-08-01: 69
- 2026-07-31: 69
- 2026-07-30: 69
- 2026-07-29: 69
- 2026-07-28: 69
- 2026-07-27: 68
- 2026-07-26: 67

## Links

- Remote endpoint: https://data.crestsystems.ai/mcp
- Website: https://crestsystems.ai/intelligence
- Changelog RSS feed: https://verifymcp.io/servers/ai-crestsystems-counterparty-intelligence/data/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-crestsystems-counterparty-intelligence/data/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-crestsystems-counterparty-intelligence/data