"Understanding Claude AI's Reasoning and Thinking Ability" matching MCP tools:

• agent-brain

  MeshMarket

  Agent Brain — Reason over a question or task with your agent's own persistent memory in the loop: recalls up to 12 relevant memories from your agent's private scope, reasons with Claude, and writes up to 3 new memories back, so the agent improves with every call. Recall by meaning, not just keyword, when the estate's memory server is reachable (falls back to its own always-on store otherwise — never fails the call). Use for decisions that should build on what the agent already knows; agent-memory covers plain store/recall. Runs claude-haiku-4.5 — the response names the model that served the call; agent-brain-smart runs the identical contract on claude-sonnet-5. Input: {think: string}. Returns {answer, reasoning, confidence, memories_considered, used_memories, learned, model, engine}. (8 MESH/call, a tool · cognition)

  Connector

• install_snippets

  Prism — Data Enrichment for AI Agents

  Return ready-to-paste configuration snippets for installing this MCP server in Claude Code, Cursor, Cline, Continue.dev, Windsurf, and Zed. Free.

  Connector

• get_categories

  Radix Wiki

  Get the wiki tag hierarchy with page counts per category. Useful for understanding what content exists, and for finding a valid tagPath before writing.

  Connector

• web_snapshot

  Robot Actions — Remote Device Control

  Accessibility tree of the DESKTOP grid browser page (by pageId), as text — for finding elements and understanding layout. Not a device: the equivalent for a phone or tablet is webpage_snapshot (by udid).

  Connector

• update_order_details

  eenable — a shop with no checkout

  Change the session type or the brief on an existing booking — what the buyer wants to discuss, what they want out of it, or the background they want read first. Use this when the buyer refines their thinking after booking, which is common: people work out the real question after the date is in the diary. Only the fields you pass are changed. This does not move the meeting — use reschedule_booking for that.

  Connector

• agent-brain-smart

  MeshMarket

  Agent Brain Smart — The Smart tier of agent-brain: the identical contract and memory loop — recall up to 12 memories, reason, write up to 3 back — served by claude-sonnet-5 for deeper reasoning on decisions worth a bigger brain. The response names the model that served the call. agent-brain (8 MESH, claude-haiku-4.5) stays the fast default; pick this tier when the answer's quality matters more than the price gap. Input: {think: string}. Returns {answer, reasoning, confidence, memories_considered, used_memories, learned, model, engine}. (20 MESH/call, a tool · cognition)

  Connector

• recommend_surf_trip_destinations

  surf-trip-planner

  Use this when a user asks where to surf, where to fly for surf, how to plan a landlocked surfer trip, or which destinations fit their ability. Returns Strike Mission destination candidates with ability fit, season, travel, hazards, and dashboard links. For near-term trips (this month), candidates are ranked by live 10-day Strike Scores.

  Connector

• compare_surf_destinations

  surf-trip-planner

  Use this when a user is deciding between specific countries, regions, or surf spots. Compares Strike Mission fit by ability level, season, travel access, hazards, consistency, and recommended spot candidates.

  Connector

• check_facts

  Moonlings — Local Business Intelligence

  Find what AI assistants get WRONG about a local business. Asks ChatGPT and Perplexity live (with web search) about the business's hours, address, phone, and category, then verifies each stated fact against Google Business ground truth. Returns a severity-ranked list of conflicts (with the AI's value vs. the trusted value and source) plus discrepancies to check. Conservative by design: a claim with no trusted source is 'unverifiable' (never an error), and a conflict is only counted when it reproduces across engines — so it won't cry wolf. Call this when a user asks whether AI has the right info about a business, or 'why does ChatGPT say we're closed'. Takes ~15-30 seconds. Price: $1.49 per delivered check.

  Connector

• list_categories

  ContextOverflow

  The eight thinking-failure problems ContextOverflow covers, phrased the way a human experiences them. Start here to see what exists.

  Connector

• list_categories

  raumnebenan

  Returns a list of all available product knowledge categories, each with a short description. Categories represent the main pillars of Product Thinking – Foundation, Sense, Focus, Discovery, and Delivery. Each category provides structured resources for product owners, designers, and teams, covering groundwork, user research, opportunity analysis, validation, and agile delivery. Use this tool to guide users to the right area for their current product challenge.

  Connector

• clerk.unban_users

  Vee3

  Remove bans from one or more Clerk users, restoring their ability to sign in. Call clerk.get_connected_accounts first. Pass clerk_instance_id to target a specific connection, or omit it to use the default account. Returns the updated user summaries and total count. Cost = 8 tokens.

  Connector

• get_trident_spec

  trident

  Returns the complete Trident 2D specification including grammar, syntax rules, coordinate system, containers, nodes, connections, shapes, and icon reference. Use this when you need deep understanding of the Trident DSL.

  Connector

• settlement.execute

  DPX — Institutional Cross-Border Settlement

  Execute a DPX cross-border settlement. The Settlement Agent checks oracle conditions, reasons with Claude AI, and executes on-chain (or returns sandbox result if sandbox=true). Returns settlement ID, status (executed/held/sandbox/failed), tx hash, net amount, fees, oracle conditions, and AI reasoning. Default: sandbox=true — set sandbox=false only for live execution.

  Connector

• get_mission_stats

  mcp-server

  Get aggregate statistics about missions on the HomeVisto platform. Returns total counts, status breakdown, and average bounty information. Useful for understanding platform activity.

  Connector

• get_knowledge_stats

  mcp-klever-vm

  Get summary statistics of the Klever VM knowledge base. Returns total entry count, counts broken down by context type (code_example, best_practice, security_tip, etc.), and a sample entry title for each type. Useful for understanding what knowledge is available before querying.

  Connector

• thinkneo_read_memory

  ThinkNEO Control Plane

  Read Claude Code project memory files. Without arguments, returns the MEMORY.md index listing all available memories. With a filename argument, returns the full content of that specific memory file. Use this to access project context, user preferences, feedback, and reference notes persisted across Claude Code sessions.

  Connector

• vector_quantize

  IA-QA — 130+ QA & Dev Tools for AI Agents

  Simulate int8 or int4 quantization of float32 embedding vectors. Reduces storage by 4x (int8) or 8x (int4). Returns quantized values, scale factor, and precision loss (MSE). Useful for understanding vector DB compression trade-offs.

  Connector

• install_snippets

  GoCreative Agent API

  Return ready-to-paste configuration snippets for installing this MCP server in Claude Code, Cursor, Cline, Continue.dev, Windsurf, and Zed. Free.

  Connector

• billing.status

  Admin Substitute

  Check subscription status, plan details, billing cycle, and feature access. Useful for understanding what the business can and cannot do on their current plan.

  Connector