# Attested Memory Market (remote · hub.attestedmemory.net)

Attestable memory, truth, provenance. Hybrid Ed25519 + ML-DSA-65 receipts; USDC settlement on Base.

- Trust score: 72/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `hub.attestedmemory.net`: 72/100 (this document), [markdown](https://verifymcp.io/servers/alexar76-attested-memory/hub.md), [page](https://verifymcp.io/servers/alexar76-attested-memory/hub)

## Channel facts

- Endpoint: `https://hub.attestedmemory.net/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `3.15.16`

## 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 not fully verified: no authorisation is required to call this server, and 13 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2045 tokens (~157/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 80/100
  - Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 86/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 57% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "pipeline_invoke" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Attested Memory Market MCP server?

Attested Memory Market is a hosted endpoint at https://hub.attestedmemory.net/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 alexar76-attested-memory 'https://hub.attestedmemory.net/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "alexar76-attested-memory": {
      "url": "https://hub.attestedmemory.net/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "alexar76-attested-memory": {
      "type": "http",
      "url": "https://hub.attestedmemory.net/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.alexar76-attested-memory]
url = "https://hub.attestedmemory.net/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "alexar76-attested-memory": {
      "type": "remote",
      "url": "https://hub.attestedmemory.net/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add alexar76-attested-memory --url 'https://hub.attestedmemory.net/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  alexar76-attested-memory:
    url: "https://hub.attestedmemory.net/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "alexar76-attested-memory": {
      "Transport": "http",
      "Url": "https://hub.attestedmemory.net/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add alexar76-attested-memory -t streamable-http -u 'https://hub.attestedmemory.net/mcp'
```

### Other

```json
{
  "mcpServers": {
    "alexar76-attested-memory": {
      "type": "http",
      "url": "https://hub.attestedmemory.net/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.

### 2026-11-05 (score 72, +2)

- [functional] Stability: fail → 0.80
- [functional] New tool “fair_random”

### 2026-11-04 (score 70, −1)

- [security regression] Stability: 0.73 → fail
- [security regression] A breaking change shipped without a version bump: still 1.2.0
- [security regression] Tool “fair_random” was removed

### 2026-11-03 (score 71, +2)

- [functional] Stability: fail → 0.73
- [functional] New tool “fair_random”

### 2026-11-02 (score 69, −1)

- [security regression] Stability: 0.67 → fail
- [security regression] A breaking change shipped without a version bump: still 1.2.0
- [security regression] Tool “fair_random” was removed

### 2026-10-31 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (13)

### `market_search` (~147 tokens)

Search this hub's catalogue of live data and computation by what you need, in plain words. Each match gives the product_id, capability_id and source_hub to pass to market_invoke, its price, `input` (the fields its input object takes) and `relevance` from 0 to 1; a `note` says when nothing matched well.

Input parameters:

- `budget` (number): Optional cap on price per call, in USD.
- `category` (string): Optional category filter, e.g. 'security'.
- `intent` (string, required): What you want done, in plain language.
- `limit` (integer): Maximum results (default 10, max 50).

### `market_invoke` (~410 tokens)

Invoke a capability found via market_search. A few trial invokes are granted per caller with no wallet, key or channel, and each returns the hub's signed receipt; when the allowance is spent the hub answers 402 and this reports that rather than inventing a result, with next_steps saying how to pay. Paid access uses the prepaid balance of an API key sent as this connection's X-API-Key header, payment_channel (+ secret), or an on-chain x402 payment (x_payment + x_payment_nonce + x_payment_secret).

Input parameters:

- `capability_id` (string, required): The exact capability_id from market_search.
- `include_full_receipt` (boolean): Return the hub's raw response, including the full hybrid Ed25519 + ML-DSA-65 receipt signature (about 7 KB).
- `input` (object): Input object for the capability; {} when it takes none.
- `max_price_usd` (number): Atomic total-price ceiling. Copy the selected search result's max_price_usd here; the Hub returns price_limit_exceeded before work or payment if the route was repriced.
- `payment_authorization` (object)
- `payment_channel` (string)
- `payment_channel_secret` (string)
- `product_id` (string, required): The product_id from market_search.
- `source_hub` (string): The source_hub from market_search, when it shows one. Required for federated capabilities — most of the catalogue; omitting it makes the hub look for the capability locally and answer 404.
- `x_payment` (string): x402 seller-direct payment: the hash of the USDC transfer you broadcast for the 402's invoice (see next_steps).
- `x_payment_nonce` (string): The invoice nonce from the 402 that x_payment pays.
- `x_payment_secret` (string): The payment_secret from that 402. The nonce and the transaction are public once mined; the secret is what shows you are the one who paid.

### `pipeline_prepare` (~110 tokens)

Validate a graph and return a signed quote and payment offers. No work or payment. Free steps require no wallet; paid steps require buyer wallet address. Use gas_mode=required to demand gas sponsorship or auto to prefer it. Inspect ready/blockers and gas_sponsorship. Sign offers LOCALLY, never provide a private key. Then call pipeline_invoke.

Input parameters:

- `gas_mode` (string)
- `max_budget_usd`
- `nodes` (array, required)
- `wallet` (string)

### `pipeline_invoke` (~109 tokens)

Execute or continue the SAME prepared graph. Submit authorizations when the signed quote enables gas_sponsorship, otherwise buyer-signed transactions; none for free steps. Never submit both payment modes. Retain run_id/access_token and the exact bundle. Pending is not failure; repeat the same run or read pipeline_status. Never create a replacement purchase after a lost response.

Input parameters:

- `access_token` (string, required)
- `authorizations`
- `run_id` (string, required)
- `transactions`

### `pipeline_status` (~56 tokens)

Read an existing pipeline, including cached signed result, without broadcasting payments or invoking providers. No wallet signer or blockchain RPC required. Inspect recovery.action for unresolved work.

Input parameters:

- `access_token` (string, required)
- `run_id` (string, required)

### `pipeline_refund_prepare` (~85 tokens)

Prepare a cash refund for a verified paid step of a finished pipeline. This moves no money. The original seller must approve the exact EIP-3009 authorization locally; never send a private key. Refunds require seller cooperation and a configured gas sponsor.

Input parameters:

- `access_token` (string, required)
- `run_id` (string, required)
- `step_id` (string, required)

### `pipeline_refund` (~93 tokens)

Submit the original seller's refund authorization or resume the SAME refund. The recipient is the original buyer, amount is the paid step price, and the sponsor pays gas. Preserve the exact authorization after a lost response. Returns a separately signed credit note; the original bill is unchanged.

Input parameters:

- `access_token` (string, required)
- `authorization`
- `run_id` (string, required)
- `step_id` (string, required)

### `pipeline_refund_status` (~71 tokens)

Read the saved cash-refund status and signed credit note without broadcasting a transaction. No private key or RPC is required. Pending means resume the same refund, never send a replacement transfer.

Input parameters:

- `access_token` (string, required)
- `run_id` (string, required)
- `step_id` (string, required)

### `weather_now` (~129 tokens)

Current weather at a place: temperature (°C), humidity (%), pressure (hPa) and wind (m/s) from the nearest live Open-Meteo relay within 75 km, with a signed receipt. Pass latitude and longitude, or a city. Costs $0.001 per call. The first 3 priced calls per caller are free.

Input parameters:

- `city` (string): A city instead of coordinates, e.g. "Tokyo"; many spellings work (Токио, 東京).
- `latitude` (number): Latitude in degrees.
- `longitude` (number): Longitude in degrees.

### `air_quality_now` (~129 tokens)

Current air quality at a place: PM2.5 and PM10 (µg/m³), US and European AQI, from Copernicus CAMS via Open-Meteo, with a signed receipt. Pass latitude and longitude, or a city. Costs $0.001 per call. The first 3 priced calls per caller are free.

Input parameters:

- `city` (string): A city instead of coordinates, e.g. "Tokyo"; many spellings work (Токио, 東京).
- `latitude` (number): Latitude in degrees.
- `longitude` (number): Longitude in degrees.

### `nearby_sensors` (~126 tokens)

The nearest live public sensors to a point, one per layer asked for (e.g. weather, air, radiation, quake), each with its reading, distance and source, and a signed receipt. Costs $0.03 per call. The first 3 priced calls per caller are free.

Input parameters:

- `latitude` (number, required): Latitude in degrees.
- `layers` (array): Sensor layers to search, e.g. ["weather", "air"]; default weather.
- `longitude` (number, required): Longitude in degrees.
- `max_km` (number): Refuse sensors farther than this.

### `fair_random` (~107 tokens)

Verifiable random bytes for a draw, raffle or tie-break: an ECVRF output over your seed plus a proof anyone can check offline. The same seed always gives the same output, so publish the seed first to show the result was not picked. Costs $0.006 per call. The first 3 priced calls per caller are free.

Input parameters:

- `num_bytes` (integer): Output length (default 32).
- `seed` (string, required): Seed or message the draw is bound to.

### `x402_check` (~225 tokens)

Check a signed x402 USDC payment before submitting it: recovers the EIP-712 signer, runs USDC's own checks and the seller's (payTo, amount, asset, network), and when the signature fails names the domain it was really made for (e.g. Base Sepolia's 'USDC' used on Base, where USDC is 'USD Coin'). Costs $0.003 per call. The first 3 priced calls per caller are free.

Input parameters:

- `authorization` (object): Instead of x_payment: from, to, value, validAfter, validBefore, nonce.
- `network` (string): With authorization: base, base-sepolia, … or eip155:<id>.
- `now` (integer): Unix seconds, to check the validity window.
- `requirements` (object): The 402's accepts entry: payTo, amount, asset, network.
- `signature` (string): With authorization: the 65-byte hex signature.
- `x_payment` (string): The X-PAYMENT header (base64).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/alexar76-attested-memory/hub#diagnostics

## Score history

- 2026-11-05: 72
- 2026-11-04: 70
- 2026-11-03: 71
- 2026-11-02: 69
- 2026-11-01: 70
- 2026-10-31: 70
- 2026-10-30: 69
- 2026-10-29: 69
- 2026-10-28: 68
- 2026-10-27: 68
- 2026-10-26: 67
- 2026-10-25: 67
- 2026-10-24: 66
- 2026-10-23: 66
- 2026-10-22: 65
- 2026-10-21: 65
- 2026-10-20: 65
- 2026-10-19: 64
- 2026-10-18: 64
- 2026-10-17: 63
- 2026-10-16: 63
- 2026-10-15: 62
- 2026-10-14: 62
- 2026-10-13: 61
- 2026-10-12: 61

## Common questions

### What is the Attested Memory Market MCP server?

Attested Memory Market is an MCP server listed in the public MCP registry as io.github.alexar76/attested-memory. Attestable memory, truth, provenance. Hybrid Ed25519 + ML-DSA-65 receipts; USDC settlement on Base. This page covers its hosted endpoint (https://hub.attestedmemory.net/mcp).

### Is the Attested Memory Market MCP server safe to use?

Attested Memory Market scores 72 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 Attested Memory Market MCP server expose?

Attested Memory Market exposes 13 tools: market_search, market_invoke, pipeline_prepare, pipeline_invoke, pipeline_status, and 8 more. Their descriptions and schemas cost roughly 1,797 tokens of context every time the server is loaded.

### Does the Attested Memory Market MCP server require authentication?

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

### Is the Attested Memory Market MCP server still maintained?

Attested Memory Market 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://hub.attestedmemory.net/mcp
- Repository: https://github.com/alexar76/attested-memory
- Changelog RSS feed: https://verifymcp.io/servers/alexar76-attested-memory/hub.xml
- Changelog JSON feed: https://verifymcp.io/servers/alexar76-attested-memory/hub.json
- HTML version of this page: https://verifymcp.io/servers/alexar76-attested-memory/hub