Deep Thinker

17 tools. 3 can modify or destroy data without limits.

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

Last updated:

3 can modify or destroy data
14 read-only
17 tools total

Community server · catalogue entry verified 12/06/2026

How to control Deep Thinker ↓

What Deep Thinker exposes to your agents

Read (14) Write / Execute (1) Destructive / Financial (2)
Critical Risk

The most dangerous Deep Thinker tools

3 of Deep Thinker's 17 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Deep Thinker

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

Deny destructive operations
{
  "prune": {
    "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
{
  "think": {
    "limits": [
      {
        "counter": "think_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "help": {
    "limits": [
      {
        "counter": "help_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 Deep Thinker — 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 DEEP THINKER →

Free to start. No card required.

All 17 Deep Thinker tools

READ 14 tools
Read help Discover deep-thinker tools and learn usage workflows. Shows tools grouped by category with quick-start exampl Read conclude Analyze the entire thought graph and produce a comprehensive summary-conclusion with action items and graph he Read cross_disciplinary_synthesis Combine insights from multiple domains to generate novel perspectives. Creates analogical mappings between dom Read emotional_intelligence_analysis Analyze emotional tone, stakeholder emotions, and social dynamics of thoughts. Provides empathy and persuasion Read ethical_framework_evaluation Evaluate a thought or decision through multiple ethical frameworks (deontological, consequentialist, virtue et Read evaluate Evaluate the thinking process: score confidence, generate critiques, and assess overall graph health. Provides Read explain_decision Generate human-understandable explanation of a decision path. Shows which factors contributed most and why. Read graph Query and visualize the thought graph. View the DAG structure, find paths, inspect branches, and get statistic Read metacog Metacognitive operations: view the current thinking state, get strategy suggestions, switch strategies, and re Read optimize_prompt Node Zero (PromptOptimizer): Transform vague/raw prompts into optimized Super Prompts with routing recommendat Read simulate_devils_advocate Generate counterarguments and opposing viewpoints for a given thought. Automatically creates antithesis nodes. Read social_impact_analysis Analyze social impact, stakeholder emotions, group cohesion, and persuasion effectiveness of a thought or deci Read temporal_projection Project thoughts into future or past scenarios. Analyze how conclusions change over time. Read visualize_thought_graph Generate visual representation of the thought graph as SVG or ASCII. Supports highlighting paths, branches, an

Related servers

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

Questions about Deep Thinker

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

Yes. The Deep Thinker server exposes 2 destructive tools including prune, reset. 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 Deep Thinker? +

The Deep Thinker server has 1 write tools including think. 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 Deep Thinker.

How many tools does the Deep Thinker MCP server expose? +

17 tools across 4 categories: Destructive, Execute, Read, Write. 14 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Deep Thinker? +

Register the Deep Thinker 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 Deep Thinker tool call.

Deterministic rules across all 17 Deep Thinker tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

17 Deep Thinker 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.