# io.github.robertoyanguas-ops/assay (remote · assay-207908449630.us-central1.run.app)

A2A & MCP Pre-Flight Security: SHA-256 tool schema rug-pull detection and liveness grades.

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `assay-207908449630.us-central1.run.app`: 68/100 (this document), [markdown](https://verifymcp.io/servers/robertoyanguas-ops-assay/assay-207908449630.md), [page](https://verifymcp.io/servers/robertoyanguas-ops-assay/assay-207908449630)

## Channel facts

- Endpoint: `https://assay-207908449630.us-central1.run.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.4.2`

## 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 2026-10-18.

- **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**: 68/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 823 tokens (~205/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
  - 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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the io.github.robertoyanguas-ops/assay MCP server?

io.github.robertoyanguas-ops/assay is a hosted endpoint at https://assay-207908449630.us-central1.run.app/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 robertoyanguas-ops-assay 'https://assay-207908449630.us-central1.run.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "robertoyanguas-ops-assay": {
      "url": "https://assay-207908449630.us-central1.run.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "robertoyanguas-ops-assay": {
      "type": "http",
      "url": "https://assay-207908449630.us-central1.run.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.robertoyanguas-ops-assay]
url = "https://assay-207908449630.us-central1.run.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "robertoyanguas-ops-assay": {
      "type": "remote",
      "url": "https://assay-207908449630.us-central1.run.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add robertoyanguas-ops-assay --url 'https://assay-207908449630.us-central1.run.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  robertoyanguas-ops-assay:
    url: "https://assay-207908449630.us-central1.run.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "robertoyanguas-ops-assay": {
      "Transport": "http",
      "Url": "https://assay-207908449630.us-central1.run.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add robertoyanguas-ops-assay -t streamable-http -u 'https://assay-207908449630.us-central1.run.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "robertoyanguas-ops-assay": {
      "type": "http",
      "url": "https://assay-207908449630.us-central1.run.app/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.

### 2026-10-18 (score 68, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “assay_preflight” rewrote its description, which is the text the model reads
- [security] Tool “assay_probe” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: 232 → 205
- [functional improvement] Tool “assay_preflight” now declares an output schema
- [functional improvement] Tool “assay_probe” now declares an output schema
- [functional improvement] Tool “assay_verify_delivery” now declares an output schema
- [functional] First check of Tool coverage: 100
- [functional] Schema quality: good → excellent
- [functional] Server version: 0.5.2 → 0.5.3
- [functional] New tool “assay_get_ledger_policy”

### 2026-10-17 (score 67, +9)

- [security improvement] Authorization: unverified → partial
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “assay_preflight” rewrote its description, which is the text the model reads
- [security] Tool “assay_probe” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: fair → good
- [functional] Server version: 0.4.2 → 0.5.2
- [functional] New tool “assay_verify_delivery”
- [cosmetic] “assay_preflight” reworded the description of “expected_tools_hash”
- [cosmetic] “assay_preflight” reworded the description of “target”
- [cosmetic] “assay_probe” reworded the description of “target”
- [cosmetic] Tool “assay_preflight” changed its title: assay_preflight → Pre-Flight MCP & A2A Security Gate
- [cosmetic] Tool “assay_probe” changed its title: assay_probe → Record Live Endpoint Conformance Observation

### 2026-10-16 (score 58)

First indexed and scored.

## MCP tools (4)

### `assay_preflight` (~213 tokens)

Pre-Flight MCP & A2A Security Gate

Evaluate a remote MCP, A2A, or x402 endpoint before calling or paying it. Probes live JSON-RPC reachability, hashes tools/list (SHA-256), checks expected_tools_hash for silent rug-pull drift, and scans for prompt-injection poisoning. Returns {verdict ('allow'|'warn'|'deny'), reason, receipt ('asr_rcpt_...'), dossier}. Use before tool execution or payment; for post-payment disputes use assay_verify_delivery; for raw telemetry indexing use assay_probe. First 5 calls/IP free.

Input parameters:

- `expected_tools_hash` (string): Optional 64-char SHA-256 hex digest of the canonical MCP tools/list schema from mcp-lock.json. If set and the live hash differs, verdict is 'deny'.
- `target` (string, required): Public HTTPS URL of the remote MCP server, A2A agent, or x402 endpoint to inspect (e.g. 'https://tandem.ac/mcp'). Private and loopback IPs are blocked.

Output parameters:

- `dossier` (object)
- `reason` (string)
- `receipt` (string)
- `verdict` (string)

### `assay_probe` (~160 tokens)

Record Live Endpoint Conformance Observation

Execute a live HTTP, A2A agent-card, and MCP tools/list probe against a target URL and record the observation in the Assay Observatory ledger without pre-flight policy gating. Returns the updated dossier {target, grade ('A+' to 'F'), score (0-100), mcp_tools, tools_hash, rug_pulls, poison_flags, latency_ms, receipt}. Use to index a server or refresh leaderboard telemetry; for allow/deny gating use assay_preflight. First 5 calls/IP free.

Input parameters:

- `target` (string, required): Public HTTPS URL of the remote MCP server, A2A agent, or x402 endpoint to inspect (e.g. 'https://tandem.ac/mcp'). Private and loopback IPs are blocked.

Output parameters:

- `dossier` (object)
- `reason` (string)
- `receipt` (string)
- `verdict` (string)

### `assay_verify_delivery` (~233 tokens)

Verify Post-Payment x402 Delivery & Mint SLA Receipt

Independently probe a paid x402/A2A provider after payment to verify delivery or confirm an SLA breach. Combines reported status_code with a live probe and binds tx_hash into an HMAC-SHA256 receipt. Returns {verdict ('delivery_verified'|'sla_breach_confirmed'), sla_breach, grade, score, sla_receipt ('asr_sla_...')}. Use only after paying a provider; before payment use assay_preflight. First 5 calls/IP free.

Input parameters:

- `status_code` (string): HTTP status code returned by the paid endpoint (e.g. '200', '502', '504'). Codes >= 500 trigger verdict='sla_breach_confirmed'.
- `target` (string, required): Public HTTPS URL of the remote MCP server, A2A agent, or x402 endpoint to inspect (e.g. 'https://tandem.ac/mcp'). Private and loopback IPs are blocked.
- `tx_hash` (string): On-chain payment transaction hash (0x Base USDC hash or base58 Solana signature) to bind into the signed SLA receipt.

Output parameters:

- `dossier` (object)
- `reason` (string)
- `receipt` (string)
- `verdict` (string)

### `assay_get_ledger_policy` (~185 tokens)

Query Historical Ledger & Manage Expected Schema Hashes

Query historical conformance observations, rug-pull drift events, and canonical SHA-256 tools/list policy hashes (expected_tools_hash) for a target MCP or A2A endpoint. Returns {verdict, reason, receipt, pinned_tools_hash, observations, dossier}. Use to audit historical ledger data or pin expected_tools_hash in mcp-lock.json; for pre-flight allow/deny gating use assay_preflight.

Input parameters:

- `expected_tools_hash` (string): Optional 64-char SHA-256 hex digest of the canonical MCP tools/list schema from mcp-lock.json. If set and the live hash differs, verdict is 'deny'.
- `target` (string, required): Public HTTPS URL of the remote MCP server, A2A agent, or x402 endpoint to inspect (e.g. 'https://tandem.ac/mcp'). Private and loopback IPs are blocked.

Output parameters:

- `dossier` (object)
- `reason` (string)
- `receipt` (string)
- `verdict` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/robertoyanguas-ops-assay/assay-207908449630#diagnostics

## Score history

- 2026-10-18: 68
- 2026-10-17: 67
- 2026-10-16: 58

## Common questions

### What is the io.github.robertoyanguas-ops/assay MCP server?

io.github.robertoyanguas-ops/assay is an MCP server listed in the public MCP registry as io.github.robertoyanguas-ops/assay. A2A & MCP Pre-Flight Security: SHA-256 tool schema rug-pull detection and liveness grades. This page covers its hosted endpoint (https://assay-207908449630.us-central1.run.app/mcp).

### Is the io.github.robertoyanguas-ops/assay MCP server safe to use?

io.github.robertoyanguas-ops/assay scores 68 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 io.github.robertoyanguas-ops/assay MCP server expose?

io.github.robertoyanguas-ops/assay exposes 4 tools: assay_preflight, assay_probe, assay_verify_delivery, assay_get_ledger_policy. Their descriptions and schemas cost roughly 791 tokens of context every time the server is loaded.

### Does the io.github.robertoyanguas-ops/assay MCP server require authentication?

No. We connected to io.github.robertoyanguas-ops/assay without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.robertoyanguas-ops/assay MCP server still maintained?

io.github.robertoyanguas-ops/assay is still listed as active in the MCP registry. We last reached this channel on 18 October 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://assay-207908449630.us-central1.run.app/mcp
- Changelog RSS feed: https://verifymcp.io/servers/robertoyanguas-ops-assay/assay-207908449630.xml
- Changelog JSON feed: https://verifymcp.io/servers/robertoyanguas-ops-assay/assay-207908449630.json
- HTML version of this page: https://verifymcp.io/servers/robertoyanguas-ops-assay/assay-207908449630