// SCAN REPORT

Tachibot

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

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

Last updated: 6 Jun 2026

10 can modify or destroy data

94 read-only

104 tools total

Free to start. No card required.

TOOL MAP

Read (94) Write / Execute (8) Destructive / Financial (2)

WHAT CAN GO WRONG

Destructive tools (focus_clear_old_sessions, usage_stats) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (commit_guardian, create_workflow, focus_export_session) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (execute_prompt_technique, workflow, workflow_start) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

RECOMMENDED RULES

Deny destructive operations

{
  "focus_clear_old_sessions": {
    "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

{
  "commit_guardian": {
    "limits": [
      {
        "counter": "commit_guardian_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ai": {
    "limits": [
      {
        "counter": "ai_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

ALL 104 TACHIBOT TOOLS

DESTRUCTIVE 2 tools

Destructive focus_clear_old_sessions Destructive usage_stats

EXECUTE 3 tools

Execute execute_prompt_technique Execute workflow Execute workflow_start

WRITE 5 tools

Write commit_guardian Write create_workflow Write focus_export_session Write planner_maker Write planner_runner

READ 94 tools

Read ai Read ai_analyze Read ai_code Read architect Read auditor Read basic-response Read brainstorm Read cached-results Read cheaper-model Read code_reviewer Read code-review Read continue_focus Read continue_workflow Read cyberpunk Read debug-assistant Read devlog Read diagnostic_test Read documentation_writer Read focus Read focus_analyze_sessions Read focus_find_similar Read focus_list_sessions Read focus_recommend Read focus_replay_session Read focus_session_status Read gemini_analyze_code Read gemini_analyze_text Read gemini_brainstorm Read gemini_image_prompt Read gemini_judge Read gemini_query Read gemini_search Read gemini_summarize Read gpt5_mini_reason Read gpt5_reason Read grok_architect Read grok_brainstorm Read grok_code Read grok_debug Read grok_function Read grok_reason Read grok_reason_v4 Read grok_scout Read grok_search Read jury Read kimi_code Read kimi_decompose Read kimi_long_context Read kimi_thinking Read legacy Read list_plans Read list_prompt_techniques Read list_workflows Read lmstudio_chat Read lmstudio_code Read lmstudio_creative Read lmstudio_query Read lmstudio_reason Read mem0 Read minimal Read minimax_agent Read minimax_code Read nebula Read nextThought Read ocean Read openai_brainstorm Read openai_code_review Read openai_explain Read openai_reason Read openai_search Read openrouter_multi Read perplexity_ask Read perplexity_code_search Read perplexity_fact_check Read perplexity_reason Read perplexity_research Read preview_prompt_technique Read qwen Read qwen_algo Read qwen_coder Read qwen_competitive Read qwen_general Read qwen_reason Read qwq_reason Read reduced-scope Read simpler-tool Read tachi Read test Read test_architect Read think Read validate_workflow Read validate_workflow_file Read visualize_workflow Read workflow_status

FAQ

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

Yes. The Tachibot server exposes 2 destructive tools including focus_clear_old_sessions, usage_stats. 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 Tachibot? +

The Tachibot server has 5 write tools including commit_guardian, create_workflow, focus_export_session. 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 Tachibot.

How many tools does the Tachibot MCP server expose? +

104 tools across 4 categories: Destructive, Execute, Read, Write. 94 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Tachibot? +

Register the Tachibot 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.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies for each. Same risk classification, live on your fleet in minutes.

Enforce policy on every Tachibot tool call.

Deterministic rules across all 104 Tachibot tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

SECURE TACHIBOT →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

Tachibot

// TOOL MAP

// WHAT CAN GO WRONG

// RECOMMENDED RULES

// ALL 104 TACHIBOT TOOLS

// FAQ