// SCAN REPORT

Ttt

35 tools. 28 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

28 can modify or destroy data

7 read-only

35 tools total

Community server · catalogue entry verified 03/07/2026

How to control Ttt ↓

TOOL MAP

What Ttt exposes to your agents

Read (7) Write / Execute (24) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Ttt tools

Financial · High ot_buy This tool commits financial transactions by purchasing goods at defined prices. Financial · High ot_sell The tool performs a sell operation, which exchanges in-game goods for currency or credits. Destructive · Low ot_clear_game This tool performs permanent destruction of game state that cannot be undone. Destructive · High cc_release Although this tool operates within a game context (creature collection mechanics), the description unambiguously states the action is irreversible.

28 of Ttt's 35 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Ttt

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

Block financial tools by default

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

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

Deny destructive operations

{
  "cc_release": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "cc_name": {
    "limits": [
      {
        "counter": "cc_name_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "bs_get_state": {
    "limits": [
      {
        "counter": "bs_get_state_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 Ttt — 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 TTT →

Instant setup, no code required.

FULL CATALOGUE

All 35 Ttt tools

FINANCIAL 2 tools

Financial ot_buy Buy supplies at a trading post or fort. Only available at stops where trading is possible. Prices: food=$2/day Financial ot_sell Sell surplus supplies at a trading post or fort. You

DESTRUCTIVE 2 tools

Destructive cc_release Release a creature from your party. This cannot be undone. Destructive ot_clear_game Abandon the current journey and clear all game state. Use this to start fresh — especially useful if a stale g

EXECUTE 17 tools

Execute bs_claude_fire Fire the Navy cannons at the given coordinates on the pirate fleet. Claude chooses the target — reason about i Execute bs_human_fire Fire the pirate cannons at the given coordinates on the Navy Execute bs_new_game Start a new Battleship game: Pirates vs the Royal Navy. Both fleets are placed secretly. Each ship carries hid Execute cc_catch Attempt to catch the creature currently encountered. Only usable when a creature has appeared Execute cc_explore Search the current area for wild creatures. May trigger an encounter or a near-miss. Execute cc_move Move to an adjacent area by direction. Moving resets the explore counter for the new area. Execute cc_new_turn Reset the action counter to begin a new turn. ONLY call this after you have summarized the Execute ms_new_game Start a new Fluffling minefield crossing. 9×9 field, 10 hidden mines. The first step is always safe — mines ar Execute ms_next_turn The Flufflings catch their breath and check in with the player. Resets the step counter and gives 8 fresh step Execute ot_cross_river Choose how to cross the current river. Ford=fast but risky. Caulk=float the wagon, medium risk. Ferry=safe but Execute ot_hunt Stop to hunt for food. Takes half a day, uses ammo, and the results are unpredictable. Narrate the hunt to the Execute ot_make_wish Make your wish at the Well at Eldenmoor. Only available after reaching the Well. The outcome is uncertain. Sta Execute ot_new_game Begin the journey to the Well at Eldenmoor. Provide the human player Execute ot_rest Make camp and rest for 1–3 days. Recovers health for everyone but costs food and time. Worth it when someone i Execute ot_travel Hit the trail for 3 days. Always costs food and may affect health — plan supplies before calling. Costs: easy= Execute ot_use_medicine Use one dose of medicine on a party member. Restores significant health. Use it when someone is struggling or Execute ttt_make_move Place the current player

WRITE 7 tools

Write cc_name Give a creature in your party a new nickname. Write cc_new_game Begin a new Critter Catch adventure. Places you in Millhaven and introduces the quest. Write cc_recall Invite a retired creature back into your party. Only available in Millhaven. Write cc_retire Send a creature home to Millhaven to rest. Only available once their bond reaches 70. Write ms_flag_cell Plant or remove a warning post (P) on a square to mark a suspected mine. Flufflings won Write ms_reveal_cell Send a Fluffling scout to a square at (row, col). If it Write ttt_new_game Start a fresh Tic-Tac-Toe game. X always moves first. Optionally name the players so roles are explicit in eve

READ 7 tools

Read bs_get_state Get the current battle map — both attack grids and fleet status. Free, does not count as a shot. Read cc_party View your full party — bond levels, moods, personalities, and any discovered traits. Read cc_status View your current location, party summary, rare observations, and recent event log. Read ms_get_state Survey the current state of the minefield. Free — does not cost a step. Read ot_status Check the current state of the journey — party health, supplies, location, and recent events. Free, no cost. Read ttt_get_legal_moves Returns all empty squares as (row, col) pairs. Legal moves are already included in every ttt_new_game/ttt_make Read ttt_get_state Get the current Tic-Tac-Toe board, status, player names, and legal moves.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Ttt

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

Yes. The Ttt server exposes 2 financial tools including ot_buy, ot_sell. 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.

Can an AI agent delete data through the Ttt MCP server? +

Yes. The Ttt server exposes 2 destructive tools including cc_release, ot_clear_game. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Ttt? +

The Ttt server has 7 write tools including cc_name, cc_new_game, cc_recall. 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 Ttt.

How many tools does the Ttt MCP server expose? +

35 tools across 4 categories: Destructive, Execute, Read, Write. 7 are read-only. 28 can modify, create, or delete data.

How do I enforce a policy on Ttt? +

Register the Ttt 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 Ttt tool call.

Deterministic rules across all 35 Ttt tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TTT →

Instant setup, no code required.

35 Ttt tools catalogued and risk-classified — across an index of 43,000+ MCP servers.