// SCAN REPORT

Mcp Bbs

70 tools. 38 can modify or destroy data without limits.

35 write tools that can modify data. Rate limits recommended.

Last updated:

38 can modify or destroy data
32 read-only
70 tools total

Community server · catalogue entry verified 29/06/2026

How to control Mcp Bbs ↓

TOOL MAP

What Mcp Bbs exposes to your agents

Read (32) Write / Execute (35) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
High Risk

The most dangerous Mcp Bbs tools

Execute · High force_action The description is empty, which significantly lowers confidence. Execute · High bbs_wait_for_prompt While the tool name alone suggests a passive read operation, the context of a telnet client designed for AI agents to interact with BBS systems indicates this is part of an Execute workflow. Execute · High bbs_connect This tool initiates an active telnet network connection to an external BBS system. Execute · Low bbs_disconnect Disconnecting from a BBS terminates the active connection session.

38 of Mcp Bbs's 70 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mcp Bbs

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

Rate limit write operations
{
  "assume_bot": {
    "limits": [
      {
        "counter": "assume_bot_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "analyze_combat_readiness": {
    "limits": [
      {
        "counter": "analyze_combat_readiness_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Mcp Bbs — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON MCP BBS →

Instant setup, no code required.

FULL CATALOGUE

All 70 Mcp Bbs tools

EXECUTE 15 tools
Execute bbs_connect Connect to a BBS via telnet (reuse existing session by default). Execute bbs_disconnect Disconnect from the BBS. Execute bbs_send bbs_send Execute bbs_set_size Set terminal size and send NAWS. Execute bbs_wait_for_prompt bbs_wait_for_prompt Execute bbs_wake Send a sequence of wake keys until the screen changes or becomes nonblank. Execute bootstrap Connect + login in one call for fast operator workflows. Execute connect Connect to a TWGS/TW2002 endpoint and enable TW2002 prompt detection. Execute force_action force_action Execute hijack_begin Acquire a lease-based hijack session for a running swarm bot. Execute hijack_heartbeat Extend a hijack lease. Execute hijack_release Release hijack session and resume bot automation. Execute hijack_send Send input to a hijacked bot, optionally guarded by prompt/regex. Execute hijack_step Single-step a hijacked bot loop. Execute login login
WRITE 20 tools
Write assume_bot Set active swarm bot context for takeover tools. Write bbs_auto_learn_enable Enable or disable auto-learn rules on every screen snapshot. Write bbs_auto_learn_menus Set auto-learn menu rules from JSON. Write bbs_auto_learn_namespace Set the auto-learn namespace (game folder name) or clear to use shared. Write bbs_auto_learn_prompts Set auto-learn prompt rules from JSON. Write bbs_keepalive Configure keepalive interval in seconds (<=0 disables). Write bbs_learn_flow Append a flow note entry to shared flow-notes.md. Write bbs_learn_menu Append a menu entry to shared menu-map.md. Write bbs_learn_prompt Append a prompt entry to shared prompt-catalog.md. Write bbs_learn_replay Append a replay session entry to shared replay-notes.md. Write bbs_learn_state Append a state entry to shared state-model.md. Write bbs_log_note Append a structured note into the JSONL session log. Write bbs_log_start Start logging session activity to a JSONL file. Write bbs_log_stop Stop logging session activity. Write bbs_save_prompt_pattern Append a new prompt pattern to the JSON file. Write bbs_set_context Set structured context that is embedded in JSONL logs. Write bbs_set_knowledge_root Override the knowledge root path at runtime. Write bbs_set_screen_saving Enable or disable saving screens to disk. Write set_active_session Select which MCP session TW2002 tools should target. Write set_directive set_directive
READ 32 tools
Read analyze_combat_readiness analyze_combat_readiness Read assumed_bot_status Get current assumed bot plus live status. Read bbs_auto_learn_discover Enable or disable auto-discovery of menus. Read bbs_debug_bot_state Get active bot's runtime state including strategy, errors, and progress. Read bbs_debug_learning_state Get learning engine state including loaded patterns and buffer status. Read bbs_debug_llm_stats Get LLM usage statistics including tokens, cost, and cache hit rates. Read bbs_debug_session_events Query recent events from session JSONL log. Read bbs_discover_menu Discover menu options from a screen buffer. Read bbs_get_knowledge_root Return the current knowledge root path. Read bbs_get_screen_saver_status Get screen saver status including saved count and directory. Read bbs_list_resumable_games List resumable game characters from local state. Read bbs_load_prompts_json Reload prompt patterns from JSON file. Read bbs_read Read output and return the current screen buffer. Read bbs_read_until_nonblank Read until the screen buffer contains non-whitespace content. Read bbs_read_until_pattern Read until the screen matches a regex pattern. Read bbs_status Return current session status. Read capabilities Describe TW2002 MCP capability groups and fastest task entrypoints. Read debug debug Read debug_screen debug_screen Read get_account_pool Fetch manager account-pool and identity summary. Read get_bot_health get_bot_health Read get_bot_session_data Fetch persisted identity/session lifecycle for one bot. Read get_bot_status get_bot_status Read get_goal_phases Return raw goal phase data (if the active strategy supports it). Read get_goal_visualization Return rendered goal visualization strings (compact/timeline/summary). Read get_goals get_goals Read get_intervention_status get_intervention_status Read get_trade_opportunities get_trade_opportunities Read hijack_read Read snapshot/events from an active hijack session. Read knowledge_status knowledge_status Read list_sessions List MCP sessions and which one is currently active. Read recover_bot recover_bot
OTHER 3 tools
Other ask_strategy ask_strategy Other set_goal set_goal Other trigger_manual_intervention trigger_manual_intervention
EXPLORE

Related servers

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

Yaver 1060 tools
adminautomation
Nodebench 824 tools
adminautomation
UnClick 813 tools
adminautomation
Binance MCP Server 734 tools
adminautomation
Fortimanager 584 tools
adminautomation
Crow 573 tools
adminautomation
Mcp 571 tools
adminautomation
GoHighLevel MCP Server 566 tools
adminautomation
FAQ

Questions about Mcp Bbs

How do I prevent bulk modifications through Mcp Bbs? +

The Mcp Bbs server has 20 write tools including assume_bot, bbs_auto_learn_enable, bbs_auto_learn_menus. 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 Mcp Bbs.

How many tools does the Mcp Bbs MCP server expose? +

70 tools across 4 categories: Destructive, Execute, Read, Write. 32 are read-only. 38 can modify, create, or delete data.

How do I enforce a policy on Mcp Bbs? +

Register the Mcp Bbs 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 Mcp Bbs tool call.

Deterministic rules across all 70 Mcp Bbs tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP BBS →

Instant setup, no code required.

70 Mcp Bbs tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.