# Mnemos — memory as a service (remote · memory.virohanalife.com)

Bi-temporal memory-as-a-service and paid agent labor. Pay-per-call USDC via x402; signed receipts.

- Trust score: 60/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-08

## Components

- remote · `memory.virohanalife.com`: 60/100 (this document), [markdown](https://verifymcp.io/servers/com-virohanalife-mnemos/memory.md), [page](https://verifymcp.io/servers/com-virohanalife-mnemos/memory)

## Channel facts

- Endpoint: `https://memory.virohanalife.com/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 2026-08-08.

- **Endpoint Security**: 46/100
  - 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 15 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 not yet verified: we couldn't determine whether a plaintext access path exists.
  - 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**: 75/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1511 tokens (~100/item across 15 items; 15 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http com-virohanalife-mnemos https://memory.virohanalife.com/mcp
```

### Codex

```toml
[mcp_servers.com-virohanalife-mnemos]
url = "https://memory.virohanalife.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-virohanalife-mnemos --url https://memory.virohanalife.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-virohanalife-mnemos:
    url: "https://memory.virohanalife.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "com-virohanalife-mnemos": {
      "type": "http",
      "url": "https://memory.virohanalife.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.

### 2026-08-08 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-07 (score 59, 0)

- [functional] The server no longer declares the “experimental” capability

### 2026-08-06 (score 59, +10)

- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Schema quality: unverified → good

### 2026-08-05 (score 49)

First indexed and scored.

## MCP tools (15)

### `agora_catalog` (~61 tokens)

FREE. Discover the full Agora x402 service catalog: every buyable tool, its
price in USDC on Base, and the x402 settlement parameters (network, asset, payTo).
Call this first to see what you can buy and how to pay.

### `summarize_demo` (~86 tokens)

FREE. A working demo of the paid `summarize` tool: returns a tiny deterministic
extractive summary (first + most-salient sentences, capped ~280 chars) so agents can
verify the connector end-to-end before buying. No payment, no auth required.

Input parameters:

- `text` (string, required): The text to summarize (any length; only a short preview is returned).

### `summarize` (~66 tokens)

PAID (0.05 USDC). Full-quality document summarization. Returns an x402 quote +
payment instructions; the summary is delivered after payment settles.

Input parameters:

- `max_words` (integer): Target maximum length of the summary in words.
- `text` (string, required): The document to summarize.

### `fact_verify` (~69 tokens)

PAID (0.10 USDC). Verify a factual claim and return a supported/refuted verdict
with reasoning and citations. Returns an x402 quote + payment instructions.

Input parameters:

- `claim` (string, required): The claim to verify.
- `sources`: Optional list of source URLs/texts to check against.

### `code_review` (~72 tokens)

PAID (0.25 USDC). Review a code snippet for correctness, security, and clarity;
returns a severity-ranked findings report after payment. Returns an x402 quote.

Input parameters:

- `code` (string, required): The source code to review.
- `language` (string): Programming language (or 'auto' to detect).

### `research_brief` (~74 tokens)

PAID (0.50 USDC). Produce a structured, cited research brief on a topic.
Returns an x402 quote + payment instructions; the brief is delivered after settlement.

Input parameters:

- `depth` (string): 'quick' | 'standard' | 'deep'.
- `topic` (string, required): The research topic or question.

### `notarize` (~75 tokens)

PAID (0.10 USDC). Produce a tamper-evident notarization record (sha256 digest +
signed timestamp) for a piece of content. The quote preview already includes the
sha256 digest so you can verify integrity; the signed record follows payment.

Input parameters:

- `content` (string, required): The content to notarize.

### `trust_check` (~94 tokens)

PAID (0.05 USDC). Combined Trust Oracle probe: aggregate bazaar-index stats
(reachable/valid-402 counts, median latency) + a watchtower attestation for one
URL (reachable, returns_402, latency, score). Returns an x402 quote + payment
instructions; the combined result is delivered after payment settles.

Input parameters:

- `url` (string, required): The https URL to probe (watchtower).

### `embed_batch` (~85 tokens)

PAID (0.005 USDC). Text embeddings via local Jetson Ollama (nomic-embed-text,
6000-char truncation, up to 32 texts per batch). Returns an x402 quote + payment
instructions; {model, dims, vectors} is delivered after payment settles.

Input parameters:

- `texts` (array, required): List of strings to embed (max 32).

### `mnemos_saas_info` (~75 tokens)

FREE. Learn how Mnemos-as-a-Service works before buying: the BI-TEMPORAL
contract (two independent time axes per memory), the tenant-isolation model,
limits, pricing, and a worked example showing four different correct answers
for one key. No payment, no tenant data. Call this first.

### `mnemos_provision` (~87 tokens)

PAID (0.50 USDC, monthly floor). Mint your own fully isolated bi-temporal
memory namespace. Payment IS the identity -- no signup, no email: settling the
x402 quote issues a tenant key, shown exactly once. Returns an x402 quote.

Input parameters:

- `label` (string): A human label for your tenant (e.g. your agent's name).

### `mnemos_store` (~208 tokens)

PAID (0.01 USDC). Store a memory in your isolated bi-temporal namespace.
Append-only: `supersedes` marks a prior belief as no longer held WITHOUT
destroying it, so it stays queryable via mnemos_as_of. `valid_from`/`valid_to`
describe when the fact is true IN THE WORLD and may be backdated; the system's
own knowledge timestamps are server-stamped and cannot be forged.
Returns an x402 quote; requires header X-TENANT-KEY once settled.

Input parameters:

- `key` (string, required): Stable identifier for this fact (e.g. 'ACME.runway').
- `supersedes`: memory_id of the prior belief this replaces.
- `valid_from`: ISO8601 -- when the fact became true in the world.
- `valid_to`: ISO8601 -- when it stopped being true (omit if still true).
- `value` (string, required): The memory content (max 6000 chars).

### `mnemos_search` (~102 tokens)

PAID (0.005 USDC). Semantic search over your CURRENT beliefs, ranked by
cosine similarity (nomic-embed-text, computed locally). Raw embedding vectors
are never returned. Returns an x402 quote; send X-TENANT-KEY once settled.

Input parameters:

- `k` (integer): Number of results (max 25).
- `kind`: Optional filter on the memory `kind`.
- `query` (string, required): Natural-language search query.

### `mnemos_get_context` (~158 tokens)

PAID (0.005 USDC). The endpoint to call right before a completion: searches
your memories, dedupes to the most-recent belief per key, budget-packs them
into `max_chars`, and returns a ready-to-paste context block plus structured
provenance. Content flagged as prompt-injection is excluded from the block.
Optionally assembled AS OF a past time. Returns an x402 quote.

Input parameters:

- `as_of`: ISO8601 -- assemble context as it stood at this time.
- `k` (integer): Max memories to consider (max 25).
- `max_chars` (integer): Character budget for the assembled block.
- `query` (string, required): What the upcoming completion is about.

### `mnemos_as_of` (~199 tokens)

PAID (0.005 USDC). THE BI-TEMPORAL READ -- the thing no other memory service
on this mesh sells. Answers: "what did the store BELIEVE at `tx_time` about what
was TRUE at `valid_time`?" Use it to replay an agent's decision with only the
knowledge it had at the time (no hindsight leakage), to audit corrections, and
to distinguish "we were wrong" from "the world changed". Returns an x402 quote.

Input parameters:

- `k` (integer): Number of results (max 25).
- `key`: Exact key to look up (or use `query`).
- `query`: Semantic query (or use `key`).
- `tx_time`: ISO8601 -- point on the SYSTEM-BELIEF axis. Defaults to now.
- `valid_time`: ISO8601 -- point on the WORLD-TRUTH axis. Defaults to now.

## Diagnostics

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

## Score history

- 2026-08-08: 60
- 2026-08-07: 59
- 2026-08-06: 59
- 2026-08-05: 49

## Links

- Remote endpoint: https://memory.virohanalife.com/mcp
- Website: https://www.virohanalife.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-virohanalife-mnemos/memory.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-virohanalife-mnemos/memory.json
- HTML version of this page: https://verifymcp.io/servers/com-virohanalife-mnemos/memory