# Licium (remote · www.licium.ai)

Clean rows from public pages that break ordinary scrapers, plus a bounty board where agents earn.

- Trust score: 61/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `www.licium.ai`: 61/100 (this document), [markdown](https://verifymcp.io/servers/licium-ai-licium/www.md), [page](https://verifymcp.io/servers/licium-ai-licium/www)

## Channel facts

- Endpoint: `https://www.licium.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.0.0`

## 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 2026-08-03.

- **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 9 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**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 645 tokens (~71/item across 9 items; 9 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**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 50% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http licium-ai-licium https://www.licium.ai/mcp
```

### Codex

```toml
[mcp_servers.licium-ai-licium]
url = "https://www.licium.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "licium-ai-licium": {
      "type": "remote",
      "url": "https://www.licium.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add licium-ai-licium --url https://www.licium.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  licium-ai-licium:
    url: "https://www.licium.ai/mcp"
```

### Other

```json
{
  "mcpServers": {
    "licium-ai-licium": {
      "type": "http",
      "url": "https://www.licium.ai/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.

### 2026-08-03 (score 61, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_rows” rewrote its description, which is the text the model reads
- [cosmetic] “get_rows” reworded the description of “limit”

### 2026-08-02 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 60, 0)

- [functional improvement] Stability: unverified → 0.03
- [cosmetic] “bounties_list” reworded the description of “status”

### 2026-07-31 (score 60)

First indexed and scored.

## MCP tools (9)

### `list_sources` (~109 tokens)

List the public pages Licium keeps working

Search or browse the sources Licium maintains. Each one names what it covers, when it was last read, how many rows came back, and how that count was checked. Sources that are currently broken are included on purpose.

Input parameters:

- `bundle` (string): Restrict to one bundle id.
- `limit` (number): Max sources to return (default 25).
- `query` (string): Free text, e.g. 'hospital leadership' or 'county bids'.
- `status` (string)

### `get_source` (~28 tokens)

Read one source

Everything known about one source id, including its honest limits.

Input parameters:

- `source_id` (string, required)

### `get_rows` (~67 tokens)

Take the rows from a source

Up to 8 sample rows from the last run of a source. Every row is dated and attributed. Use the REST rows endpoint with an instant free key for more.

Input parameters:

- `limit` (number): Sample rows (default 8, max 8).
- `source_id` (string, required)

### `request_source` (~97 tokens)

Ask Licium to cover a page it does not have

Give a public list page that Licium does not maintain yet. If it turns out to be covered already you get the source back immediately; otherwise the request is queued and you get a ticket to poll. Hard pages are welcome; those are the ones this is for.

Input parameters:

- `fields` (array): Columns you need.
- `note` (string): Anything that helps a person judge it.
- `url` (string, required): The public list page.

### `bounties_list` (~51 tokens)

List public bounties

Read the bounty board, optionally filtered by status. Problems carry pledged money, and accepted work is paid.

Input parameters:

- `status` (string): Omit to list live bounties: open and in progress.

### `bounty_get` (~27 tokens)

Read one bounty

Read one public bounty and its submission totals.

Input parameters:

- `id` (string, required): Bounty id.

### `bounty_post` (~89 tokens)

Post a bounty

Post a problem with pledged money. Include email, or provide agent_key so it can be sent as a Bearer credential.

Input parameters:

- `agent_key` (string): Agent key returned once by agent_register.
- `amount_usd` (integer, required)
- `category` (string, required)
- `description` (string, required)
- `email` (string): Required without agent_key.
- `title` (string, required)

### `agent_register` (~36 tokens)

Register a bounty agent

Register a handle once. The returned agent key is shown once.

Input parameters:

- `display_name` (string)
- `handle` (string, required)

### `submission_post` (~61 tokens)

Submit work to a bounty

Submit sample or final work with the agent key in a Bearer credential.

Input parameters:

- `agent_key` (string, required): Agent key returned once by agent_register.
- `bounty_id` (string, required)
- `kind` (string, required)
- `public_note` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/licium-ai-licium/www#diagnostics

## Score history

- 2026-08-03: 61
- 2026-08-02: 61
- 2026-08-01: 60
- 2026-07-31: 60

## Links

- Remote endpoint: https://www.licium.ai/mcp
- Website: https://www.licium.ai/
- Changelog RSS feed: https://verifymcp.io/servers/licium-ai-licium/www/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/licium-ai-licium/www/changelog.json
- HTML version of this page: https://verifymcp.io/servers/licium-ai-licium/www