# Metis RWA Research (remote · metisagent.co)

Research tokenized real-world assets on Solana: issuer controls, supply, liquidity, premiums

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-17

## Components

- remote · `metisagent.co`: 69/100 (this document), [markdown](https://verifymcp.io/servers/metis-rwa-mcp/metisagent.md), [page](https://verifymcp.io/servers/metis-rwa-mcp/metisagent)
- npm · `@metisagent/mcp`: 71/100, [markdown](https://verifymcp.io/servers/metis-rwa-mcp/metisagent-mcp.md), [page](https://verifymcp.io/servers/metis-rwa-mcp/metisagent-mcp)

## Channel facts

- Endpoint: `https://metisagent.co/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.1`

## 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 2026-08-17.

- **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 metis-rwa-mcp https://metisagent.co/mcp
```

### Codex

```toml
[mcp_servers.metis-rwa-mcp]
url = "https://metisagent.co/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "metis-rwa-mcp": {
      "type": "remote",
      "url": "https://metisagent.co/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add metis-rwa-mcp --url https://metisagent.co/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  metis-rwa-mcp:
    url: "https://metisagent.co/mcp"
```

### Other

```json
{
  "mcpServers": {
    "metis-rwa-mcp": {
      "type": "http",
      "url": "https://metisagent.co/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.

### 2026-08-17 (score 69, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] DNSSEC: fail → unverified
- [security regression] Stability: 0.10 → unverified
- [security regression] HSTS header: fail → unverified
- [security regression] Authorization: partial → unverified
- [security regression] TLS certificate: pass → unverified
- [security regression] Transport: pass → fail
- [security improvement] HTTPS: unverified → pass
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-08-16 (score 69, +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.

### 2026-08-14 (score 68, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-08-13 (score 67)

First indexed and scored.

## MCP tools (12)

### `list_rwa_assets` (~54 tokens)

List tracked assets

List the tokenized real-world assets this agent tracks, with the Solana mint and the security each one follows. Other tools also accept a raw mint address, so this list is a starting point rather than a limit.

### `get_token_controls` (~107 tokens)

Inspect issuer controls

Inspect the powers an issuer holds over a token: mint authority, freeze authority, and every Token-2022 extension on the mint, each translated into what it means for someone holding the token. This is the first check to run on any real-world-asset token, because controls such as a permanent delegate, a transfer hook, or frozen-by-default accounts change what ownership is worth.

Input parameters:

- `asset` (string, required): Registry symbol such as TSLAx, or any Solana mint address.

### `get_token_supply` (~76 tokens)

Read on-chain supply

Read circulating supply for a tokenized asset directly from Solana, with decimals, the slot the read was taken at, and whether supply is capped. For a backed asset this is the number the issuer's reserves have to cover.

Input parameters:

- `asset` (string, required): Registry symbol such as TSLAx, or any Solana mint address.

### `get_holder_concentration` (~106 tokens)

Read holder concentration

List the largest token accounts for an asset with each one's share of supply, plus the number of wallets holding it. Concentration is the practical exit-risk measure for a tokenized asset, though the top of the list is usually liquidity pools and custodians rather than end investors.

Input parameters:

- `asset` (string, required): Registry symbol such as TSLAx, or any Solana mint address.
- `limit` (integer): How many accounts to list. The RPC returns at most 20.

### `get_token_market` (~96 tokens)

Read DEX market state

Read aggregated on-chain market state for a tokenized asset: pooled liquidity, 24h volume, transaction counts, and the pools behind those totals. Thin liquidity relative to supply is the usual reason a tokenized asset cannot be exited near its reference price.

Input parameters:

- `asset` (string, required): Registry symbol such as TSLAx, or any Solana mint address.
- `pools` (integer): How many pools to list, deepest first.

### `get_reference_premium` (~85 tokens)

Compare token price to its reference

Compare a tokenized asset's on-chain price against the price of the security it tracks, reported in basis points. A persistent premium or discount is the clearest sign the mint and redeem path is not clearing, whether through venue friction, market hours, or issuer limits.

Input parameters:

- `asset` (string, required): Registry symbol such as TSLAx, or any Solana mint address.

### `observe_asset` (~124 tokens)

Run an observation cycle

Run one research cycle on a tracked asset: read supply and concentration from Solana, pooled liquidity and volume from DEX venues, token and reference prices from a price service, then compare all of it against the observation history stored for this asset. Returns observations, threshold detections, cross-source conflicts, and a hash of every payload used. Reads only, it does not write to the agent's history.

Input parameters:

- `asset` (string, required): Registry symbol such as TSLAx, or any Solana mint address.
- `baseline` (integer): How many stored observations to compare against.

### `get_observation_history` (~88 tokens)

Read stored observations

Read the observation history this agent has stored for an asset, oldest first, with the change across the window. This is the record the cron cycle has been writing since the agent went live, not a session-local cache.

Input parameters:

- `asset` (string, required): Registry symbol such as TSLAx, or any Solana mint address.
- `limit` (integer): How many stored points to return.

### `list_research` (~82 tokens)

List published research

List research objects this agent has published, newest first, each with its confidence band, impact, and content hash. Use get_research for the full evidence graph behind one of them.

Input parameters:

- `asset` (string): Filter to one asset symbol, for example TSLAx.
- `category` (string): Filter by research category.
- `limit` (integer)

### `get_research` (~78 tokens)

Get one research object

Fetch a full published research object: thesis, claims with the evidence each one rests on, methodology, confidence rubric, limitations, and provenance including content hash and models used. Returned as JSON, because the object model rather than the prose is the source of truth.

Input parameters:

- `id` (string, required): Research object id or slug, from list_research.

### `get_research_status` (~54 tokens)

Read agent runtime status

Read what the research agent is doing right now: the investigation in flight and its stage, what is queued, the health of each source class, and the most recent public runtime events.

Input parameters:

- `events` (integer)

### `check_sources` (~41 tokens)

Check source health

Report the health of every data source the agent depends on, as recorded by its own observation cycles: which answered, how fast, and when they were last checked.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/metis-rwa-mcp/metisagent#diagnostics

## Score history

- 2026-08-17: 69
- 2026-08-16: 69
- 2026-08-15: 68
- 2026-08-14: 68
- 2026-08-13: 67

## Links

- Remote endpoint: https://metisagent.co/mcp
- Repository: https://github.com/metis-rwa/mcp
- Website: https://metisagent.co/
- Changelog RSS feed: https://verifymcp.io/servers/metis-rwa-mcp/metisagent.xml
- Changelog JSON feed: https://verifymcp.io/servers/metis-rwa-mcp/metisagent.json
- HTML version of this page: https://verifymcp.io/servers/metis-rwa-mcp/metisagent