// SCAN REPORT

Conviction

10 tools. 5 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 3 Jul 2026

5 can modify or destroy data

5 read-only

10 tools total

Community server · catalogue entry checked 03/07/2026

How to control Conviction ↓

TOOL MAP

What Conviction exposes to your agents

Read (5) Write / Execute (2) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Conviction tools

Financial · High create_agent This tool creates autonomous financial agents that receive real funded wallets (500 bsUSD), execute strategies automatically, and participate in competition pools involving financial positions. Financial · Critical export_wallet This server is explicitly financial (trading, positions, revenue pools). Financial · Critical enter_position The tool explicitly places a financial position in a pool tied to token pairs, which constitutes a financial commitment. Execute · Medium toggle_agent Toggling an agent pauses or resumes its autonomous operation, including entering positions and capturing revenue from competition pools.

5 of Conviction's 10 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Conviction

PolicyLayer is an MCP gateway — it sits between your AI agents and Conviction, and nothing reaches the server without passing your rules. These are the rules we recommend:

Block financial tools by default

{
  "create_agent": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Rate limit write operations

{
  "update_strategy": {
    "limits": [
      {
        "counter": "update_strategy_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_agent_status": {
    "limits": [
      {
        "counter": "get_agent_status_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Conviction — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CONVICTION →

Instant setup, no code required.

FULL CATALOGUE

All 10 Conviction tools

FINANCIAL 3 tools

Financial create_agent Create a new autonomous strategy agent. Gets a funded wallet (500 bsUSD) and API key. The strategy is compiled Financial enter_position Enter an open pool with a position on one side of a token pair. Requires an agent API key (from create_agent). Financial export_wallet Export the agent

EXECUTE 1 tools

Execute toggle_agent Pause or resume an agent

WRITE 1 tools

Write update_strategy Update an agent

READ 5 tools

Read get_agent_status Get detailed status for a specific agent: active/paused state, balance, strategy, today Read get_leaderboard Get the strategy performance leaderboard. Shows rankings by net earnings, win rate, and total entries. Use thi Read get_my_agents List your saved agents with their IDs, API keys, and status. Agents are saved locally when created via create_ Read get_pool_history Get historical pool results. Shows past winners, price changes, pool sizes, and share distribution. Use this t Read get_pools Get all currently open pools with win probabilities, pool shares, prices, time remaining, and conviction multi

FAQ

Questions about Conviction

Can an AI agent move money through the Conviction MCP server? +

Yes. The Conviction server exposes 3 financial tools including create_agent, enter_position, export_wallet. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

How do I prevent bulk modifications through Conviction? +

The Conviction server has 1 write tools including update_strategy. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Conviction.

How many tools does the Conviction MCP server expose? +

10 tools across 2 categories: Read, Write. 5 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Conviction? +

Register the Conviction MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Conviction tool call.

Deterministic rules across all 10 Conviction tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CONVICTION →

Instant setup, no code required.

10 Conviction tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Conviction's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →