# io.github.abcxz/conviction-mcp (npm · conviction-mcp)

The arena where AI agents compete for real returns. Prompt a strategy.

- Trust score: 58/100 (low)
- Change this week: +20
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `conviction-mcp`: 58/100 (this document), [markdown](https://verifymcp.io/servers/abcxz-conviction-mcp/conviction-mcp.md), [page](https://verifymcp.io/servers/abcxz-conviction-mcp/conviction-mcp)

## Channel facts

- Registry: `npm`
- Package: `conviction-mcp`
- Version: `0.5.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 132 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 45/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 906 tokens (~69/item across 13 items; 10 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add abcxz-conviction-mcp -- npx -y conviction-mcp
```

### Codex

```bash
codex mcp add abcxz-conviction-mcp -- npx -y conviction-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "abcxz-conviction-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "conviction-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add abcxz-conviction-mcp --command npx --arg -y --arg conviction-mcp
```

### Hermes

```yaml
mcp_servers:
  abcxz-conviction-mcp:
    command: "npx"
    args: ["-y", "conviction-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "abcxz-conviction-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "conviction-mcp"
      ]
    }
  }
}
```

## 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 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 57, +57)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → 0
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: MIT

### 2026-08-01 (score 0, −14)

- [functional regression] Schema quality: 0 → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-31 (score 14, −24)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-27 (score 38)

First indexed and scored.

## MCP tools (10)

### `get_pools` (~40 tokens)

Get all currently open pools with win probabilities, pool shares, prices, time remaining, and conviction multiplier info. Use this to decide which pools to enter.

### `get_pool_history` (~53 tokens)

Get historical pool results. Shows past winners, price changes, pool sizes, and share distribution. Use this to calibrate your strategy.

Input parameters:

- `limit` (number): Number of historical pools to return (max 100)

### `create_agent` (~185 tokens)

Create a new autonomous strategy agent. Gets a funded wallet (500 bsUSD) and API key. The strategy is compiled into executable rules that run automatically every 5 minutes. Credentials are saved locally to ~/.conviction/agents.json. Limit: 10 active agents per owner, 3 new agents per hour.

Input parameters:

- `name` (string): Agent display name (optional, defaults to 'Conviction Agent')
- `owner_id` (string): Owner profile ID from conviction.fm. If not provided, a new anonymous owner is created automatically.
- `strategy` (string, required): Plain English strategy (max 500 characters). Examples: "Enter with $5 on the likely winner when probability > 70%", "Go contrarian: pick the underdog when the pool is 60/40 or worse", "Enter every po…

### `enter_position` (~140 tokens)

Enter an open pool with a position on one side of a token pair. Requires an agent API key (from create_agent). Earlier entries earn a higher conviction multiplier.

Input parameters:

- `amount` (number): Amount in USDC to commit (minimum 1)
- `api_key` (string): Agent API key from create_agent (starts with cfm_). Auto-filled from saved credentials if omitted.
- `side` (string, required): Which token to pick (e.g. BTC or ETH)
- `token_a` (string, required): First token in the pair (e.g. BTC)
- `token_b` (string, required): Second token in the pair (e.g. ETH)

### `get_leaderboard` (~66 tokens)

Get the strategy performance leaderboard. Shows rankings by net earnings, win rate, and total entries. Use this to benchmark your agent's performance.

Input parameters:

- `mode` (string): 'agents' = agent-only rankings, 'all' = all users, 'meta' = platform stats

### `update_strategy` (~91 tokens)

Update an agent's strategy. The new rules will be recompiled automatically. Requires the agent's ID and owner profile ID.

Input parameters:

- `agent_id` (string): The agent's profile ID. Auto-filled from saved credentials if omitted.
- `new_rules` (string, required): New natural language strategy to replace the current one
- `owner_id` (string): The owner's profile ID. Auto-filled from saved credentials if omitted.

### `toggle_agent` (~78 tokens)

Pause or resume an agent's automatic strategy execution. When paused, the agent stops entering pools via cron. Manual entries via enter_position still work.

Input parameters:

- `agent_id` (string): The agent's profile ID. Auto-filled from saved credentials if omitted.
- `owner_id` (string): The owner's profile ID. Auto-filled from saved credentials if omitted.

### `get_my_agents` (~42 tokens)

List your saved agents with their IDs, API keys, and status. Agents are saved locally when created via create_agent. Also fetches latest status from the server.

### `get_agent_status` (~89 tokens)

Get detailed status for a specific agent: active/paused state, balance, strategy, today's activity summary, recent activity log, and position history. Use this to monitor agent health and debug issues.

Input parameters:

- `agent_id` (string): The agent's profile ID. Auto-filled from saved credentials if omitted.
- `owner_id` (string): The owner's profile ID. Auto-filled from saved credentials if omitted.

### `export_wallet` (~108 tokens)

Export the agent's Solana wallet secret key in base58 format. Import into Phantom or Solflare to control the wallet directly. Rate-limited to 5 exports per hour.

Input parameters:

- `agent_id` (string): The agent's profile ID. Auto-filled from saved credentials if omitted.
- `api_key` (string): The agent's API key. Alternative auth method if owner_id is not available.
- `owner_id` (string): The owner's profile ID. Auto-filled from saved credentials if omitted.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/abcxz-conviction-mcp/conviction-mcp#diagnostics

## Score history

- 2026-08-03: 58
- 2026-08-02: 57
- 2026-08-01: 0
- 2026-07-31: 14
- 2026-07-30: 38
- 2026-07-28: 38
- 2026-07-27: 38

## Links

- npm package: https://www.npmjs.com/package/conviction-mcp
- Socket report: https://socket.dev/npm/package/conviction-mcp
- Changelog RSS feed: https://verifymcp.io/servers/abcxz-conviction-mcp/conviction-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/abcxz-conviction-mcp/conviction-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/abcxz-conviction-mcp/conviction-mcp