# Cleared Index (npm · @n747ai/clearedindex-mcp-server)

Cleared Check before pay: lookup_merchant, cleared_check, route_gateway for x402 agents.

- Trust score: 84/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-22

## Components

- npm · `@n747ai/clearedindex-mcp-server`: 84/100 (this document), [markdown](https://verifymcp.io/servers/com-clearedindex-mcp/n747ai-clearedindex-mcp-server.md), [page](https://verifymcp.io/servers/com-clearedindex-mcp/n747ai-clearedindex-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@n747ai/clearedindex-mcp-server`
- Version: `1.4.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-09-22.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 95 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 25 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 78/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1427 tokens (~95/item across 15 items; 15 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 97/100
  - Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 98% 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 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 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 Cleared Index MCP server?

Cleared Index runs locally as an npm package, launched with npx -y @n747ai/clearedindex-mcp-server. 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 com-clearedindex-mcp -- npx -y @n747ai/clearedindex-mcp-server
```

### Cursor

```json
{
  "mcpServers": {
    "com-clearedindex-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@n747ai/clearedindex-mcp-server"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-clearedindex-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@n747ai/clearedindex-mcp-server"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-clearedindex-mcp -- npx -y @n747ai/clearedindex-mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-clearedindex-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@n747ai/clearedindex-mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-clearedindex-mcp --command npx --arg -y --arg @n747ai/clearedindex-mcp-server
```

### Hermes

```yaml
mcp_servers:
  com-clearedindex-mcp:
    command: "npx"
    args: ["-y", "@n747ai/clearedindex-mcp-server"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-clearedindex-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@n747ai/clearedindex-mcp-server"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-clearedindex-mcp -t stdio -c npx -a -y @n747ai/clearedindex-mcp-server
```

### Other

```json
{
  "mcpServers": {
    "com-clearedindex-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@n747ai/clearedindex-mcp-server"
      ]
    }
  }
}
```

## 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.

### 2026-09-22 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-07 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (15)

### `lookup_merchant` (~105 tokens)

DEFAULT before pay — look up a merchant origin/slug on Cleared Index via Check (probe=false). Returns pass, score, payToMismatch, tier, profile URL, nextAction, and defaultNextTool. On PASS call route_gateway next (fee advisory). Call this before any x402 payment to an unknown merchant.

Input parameters:

- `origin` (string, required): Merchant origin URL, domain, or Cleared slug (e.g. https://api.example.com or coinbase-identity)

### `get_cleared_status` (~62 tokens)

Cleared status for a slug/domain — same payload as lookup_merchant (Check, probe=false). Prefer lookup_merchant in new agent loops.

Input parameters:

- `slug` (string, required): The slug or domain to check (e.g. 'coinbase-identity')

### `route_gateway` (~182 tokens)

DEFAULT before pay — Cleared Gateway: one call, best verified x402 endpoint. Routes by trust score, settle-tape tx gravity (Witness/on-chain), price, latency, and canary. Returns payTo URL + totalCost. Call after lookup_merchant / cleared_check. Prefer requireReceiptSettled=true in production. 100 free routes/month, no API key.

Input parameters:

- `capability` (string): Optional capability hint
- `category` (string, required): Capability category to route
- `maxPrice` (number): Max endpoint price in USD
- `minScore` (number): Minimum trust score (default 55; 70 recommended for production)
- `requireReceiptSettled` (boolean): Only route to endpoints with on-chain settlement proof
- `strategy` (string): Routing strategy (default: auto = market route-share; best_value = score/price)

### `check_domain_status` (~66 tokens)

Check if a domain/service is verified on ClearedIndex via Check (probe=false). Alias of get_cleared_status — prefer lookup_merchant for sandwich step 1.

Input parameters:

- `slug` (string, required): The slug or domain to check (e.g. 'coinbase-identity')

### `get_trust_score` (~51 tokens)

Get the detailed trust score breakdown for an origin/slug via Cleared Check (probe=false) — no full catalog load.

Input parameters:

- `slug` (string, required): The listing slug or origin to get score for

### `cleared_check` (~130 tokens)

Cleared Check — verify an origin before pay. Returns pass, score, payToMismatch, tier, card URL, provenance, nextAction (route_gateway + fee on PASS), and defaultNextTool=route_gateway. Uses probe=false by default (fast, catalog-safe). ALWAYS call route_gateway next on PASS before pay.

Input parameters:

- `certify`: Attach Certified Hash receipt (default true — tax_the_tx)
- `origin` (string, required): Merchant origin URL or domain (e.g. https://api.example.com)
- `probe` (boolean): Live-probe endpoints (default false — prefer false for agent farms)

### `report_delivery` (~91 tokens)

Report Gateway route delivery outcome — POST gateway/track with outcome delivered|not_delivered. Call after pay so Cleared can learn route quality.

Input parameters:

- `origin` (string): Merchant origin that was paid
- `outcome` (string, required): Whether the paid route delivered usable results
- `requestId` (string): Gateway request/route id if available
- `source` (string): Reporter label (default agent_report)

### `witness_settlement` (~119 tokens)

Witness an x402 USDC settlement on-chain. Call after pay with the settlement txHash. Returns a Cleared attestation receipt URL. Required sandwich step for verifiable agent spend.

Input parameters:

- `network` (string): Settlement network (default base) — all Cleared Witness rails
- `notify` (boolean): Notify operator when possible (default true)
- `origin` (string): Merchant origin that was paid (helps link Witness to listing)
- `txHash` (string, required): Base 0x… tx hash or Solana signature from the settlement

### `agent_read` (~82 tokens)

Cleared Agent Read — routing intelligence for a listing (verdict prefer/route/caution/skip, when-to-call, settle posture, endpoint hints, payToMismatch). Accepts slug or origin. Call after lookup_merchant before paying an unknown merchant.

Input parameters:

- `slug` (string, required): Cleared listing slug or origin (e.g. taylor-good-agents)

### `cleared_verdict` (~129 tokens)

Cleared Verdict — SwarmX-class 3-panel diligence (trust/settle/risk) before pay. Free preview by default. Set paid=true only after settling $0.10 USDC on /api/x402/verdict (or pass txHash). Call after lookup_merchant / cleared_check.

Input parameters:

- `origin` (string, required): Merchant origin URL to evaluate
- `paid` (boolean): If true, call paid /api/x402/verdict (expects prior settlement). Default false = free preview.
- `txHash` (string): Optional Base USDC settlement tx hash for paid Verdict

### `cleared_run_gate` (~105 tokens)

Cleared Run Gate — NodeRun-class spend firewall before compute/pay. Returns allow/abort/upgrade with Check + payTo + optional spend caps. Free. On upgrade, point agents at Gateway Pro Stripe.

Input parameters:

- `maxSpendUsd` (number): Hard spend ceiling in USD
- `minScore` (number): Minimum Cleared score (default 70)
- `origin` (string, required): Origin about to receive spend
- `spendUsd` (number): Planned spend in USD

### `cleared_arena` (~56 tokens)

Cleared Arena — boats-class repeat settle habit. Returns the forced sandwich steps (run_gate → verdict → gateway → pay → witness → repeat) for an origin.

Input parameters:

- `origin` (string): Optional origin to bind arena steps to

### `list_cleared_services` (~82 tokens)

List verified services on ClearedIndex, optionally filtered by category. Prefer cleared_check / lookup_merchant for single-origin sandwich steps — this loads the catalog.

Input parameters:

- `category` (string): Filter by category: identity, enrichment, compliance, regime, judgment, workflow, other
- `tier` (string): Filter by tier: listed, cleared, spotlight

### `submit_for_review` (~129 tokens)

Submit a new x402 endpoint/service to ClearedIndex for trust verification. Returns the listing URL and initial checks.

Input parameters:

- `category` (string, required)
- `contactEmail` (string, required): Contact email for verification
- `description` (string, required): Full description of what the service does
- `endpoints` (array, required): API endpoints the service exposes
- `name` (string, required): Service name
- `operator` (string, required): Company/person operating the service
- `origin` (string, required): Base URL of the service (e.g. https://api.example.com)
- `tagline` (string, required): One-line description

### `get_badge` (~38 tokens)

Get the ClearedIndex trust badge URL for a verified service. Useful for embedding verification status.

Input parameters:

- `slug` (string, required): The listing slug

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-clearedindex-mcp/n747ai-clearedindex-mcp-server#diagnostics

## Score history

- 2026-09-22: 84
- 2026-09-21: 83
- 2026-09-20: 83
- 2026-09-19: 83
- 2026-09-18: 82
- 2026-09-17: 82
- 2026-09-16: 81
- 2026-09-15: 81
- 2026-09-14: 80
- 2026-09-13: 80
- 2026-09-12: 79
- 2026-09-11: 79
- 2026-09-10: 78
- 2026-09-09: 78
- 2026-09-08: 77
- 2026-09-07: 77
- 2026-09-06: 76
- 2026-09-05: 76
- 2026-09-04: 76
- 2026-09-03: 75
- 2026-09-02: 75
- 2026-09-01: 74
- 2026-08-31: 70
- 2026-08-30: 70
- 2026-08-29: 70
- 2026-08-28: 70
- 2026-08-27: 70
- 2026-08-26: 70
- 2026-08-25: 69
- 2026-08-24: 69

## Common questions

### What is the Cleared Index MCP server?

Cleared Index is an MCP server listed in the public MCP registry as com.clearedindex/mcp. Cleared Check before pay: lookup_merchant, cleared_check, route_gateway for x402 agents. This page covers its npm package (@n747ai/clearedindex-mcp-server).

### Is the Cleared Index MCP server safe to use?

Cleared Index scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 September 2026. It declares no install or post-install scripts. 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 Cleared Index MCP server expose?

Cleared Index exposes 15 tools: lookup_merchant, get_cleared_status, route_gateway, check_domain_status, get_trust_score, and 10 more. Their descriptions and schemas cost roughly 1,427 tokens of context every time the server is loaded.

### Is the Cleared Index MCP server still maintained?

Cleared Index is still listed as active in the MCP registry. We last reached this channel on 22 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Cleared Index MCP server under?

Cleared Index declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@n747ai/clearedindex-mcp-server
- Socket report: https://socket.dev/npm/package/@n747ai/clearedindex-mcp-server
- Repository: https://github.com/N747AI/clearedindex-mcp
- Website: https://clearedindex.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-clearedindex-mcp/n747ai-clearedindex-mcp-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-clearedindex-mcp/n747ai-clearedindex-mcp-server.json
- HTML version of this page: https://verifymcp.io/servers/com-clearedindex-mcp/n747ai-clearedindex-mcp-server