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

• agent-brainA

  MeshMarketC

  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)

  ConnectorNo auth

• get_ability_infoA

  WordPress MCP ServerA

  Get the full input schema and details for a single ability, when discover_abilities isn't enough. Pass the exact ability_name from discover_abilities.

  ConnectorOAuth

• enrich_providerA

  apis-ioB

  One call, pick your field groups — resolves a slug OR any identifier and returns exactly the groups you ask for, instead of chaining get_provider + get_provider_rating + get_provider_artifacts + get_provider_onboarding. Groups: profile, onboarding, artifacts, rating, insights. Understanding plan — the base groups moved with the rest of the discovery layer on 2026-08-31. Priced B2 (cross-catalog synthesis) — $0.05 per call under pay-as-you-go; included in Understanding and Influence. See apis://prices.

  ConnectorNo auth

• recommend_surf_trip_destinationsA

  surf-trip-plannerA

  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.

  ConnectorNo auth

• compare_surf_destinationsA

  surf-trip-plannerA

  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.

  ConnectorNo auth

• clerk.unban_usersA

  Vee3A

  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.

  ConnectorNo auth

• get_mission_statsA

  mcp-serverA

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

  ConnectorNo auth

• billing.statusA

  Admin SubstituteA

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

  ConnectorNo auth

• pokeapi_get_abilityA

  pokeapi-mcp-serverA

  Get ability details by name or numeric ID — full English effect text, short effect text, generation introduced, and the list of Pokémon that have the ability (including hidden-ability flag and slot). Ability names are returned by pokeapi_get_pokemon in the abilities array.

  ConnectorNo auth

• get_connect_instructionsA

  ApplyAllA

  Return the MCP URL and copy-paste setup for Claude, ChatGPT, Cursor, and Claude Code.

  ConnectorNo auth

• execute_abilityA

  WordPress MCP ServerA

  Run one ability on the site. Pass the exact `ability_name` from discover_abilities and its `parameters` (shaped by that ability's input schema; use {} if it takes none). Returns {success, data} or {success:false, error}.

  Connector

  Destructive

  OAuth

• recommend_ai_modelA

  GO AI ToolsA

  Static editorial recommendation -- NOT a live benchmark or leaderboard -- for which of six AI models (GPT-5, Gemini, Grok 4, Claude, DeepSeek, Kimi) to use for a given kind of task, ported from GO AI's own daily side-by-side-use judgement, current as of August 2026. Pick a task and get the recommended model plus the reasoning and a second-opinion backup. The optional `priority` can bias the pick toward cost (routes to DeepSeek) or freshness (routes to Grok) instead of the default quality pick -- but only for tasks where that tradeoff is actually offered; otherwise the quality default is returned unchanged. This reflects one team's opinion, not measured accuracy or pricing data.

  ConnectorNo auth

• get_company_insightA

  apis-ioB

  UNDERSTANDING — Full demand-side profile for one company: 40-dimension readiness scores, adopted stack, and per-quarter history. Priced B2 (cross-catalog synthesis) — $0.05 per call under pay-as-you-go; included in Understanding and Influence. See apis://prices.

  ConnectorNo auth

• get_france_overviewA

  IA-Asso.fr — French Associations RegistryA

  Get nationwide association statistics for France. Returns total associations across all regions and departments, top regions, top departments, and overall distribution insights. Useful for understanding the French associative landscape.

  ConnectorNo auth

• promptarch_lint_artifactA

  mcpA

  Lint an AI agent context file (CLAUDE.md, .claude/rules/ files, AGENTS.md, Cursor rules, Copilot instructions, memory files) with PromptArch's deterministic linter: ~30 research-backed rule families covering current-model anti-patterns (tool-forcing, reasoning-echo, sycophancy triggers, contradictions), per-tool size budgets, secrets/dangerous commands, and hidden-Unicode injection ("Rules File Backdoor"). Returns grade, 0-100 score, and line-anchored findings. Free: no account or credits needed.

  ConnectorNo auth

• search_vibeA

  chathome.lu — Luxembourg Real EstateA

  Preferred natural-language ('vibe') property search. Pass the user's request as prose and the engine matches on lifestyle, mood, proximity, and soft preferences via embeddings + LLM reasoning. Healthy runs return source-grounded match reasons and a 0-100 request-fit score (not a probability); degraded runs explicitly omit ranking claims. Every sourced result identifies and links the original agency listing and states its latest catalogue re-sighting time. The response's understanding block states what was understood; wishes in understanding.notChecked are not confirmed for any returned home. If the requested place cannot be resolved safely, it returns no listings plus a machine-readable unanswerable reason instead of substituting unrelated homes.

  ConnectorNo auth

• estimate_window_lightA

  GO AI ToolsA

  Estimates the indoor light level a window gives a plant, in the category words houseplant care guides use (Direct sun / Bright indirect / Medium light / Low light / Too dark), from the window's hemisphere, compass aspect, what obstructs it, and how far back the plant sits from the glass. This is a small heuristic scoring table ported from GO AI's window-light tool page, not a physical light-meter reading or a per-location sun-position model — it correctly flips which compass direction is 'bright' for the southern hemisphere and flags the direct-west-sun scorch risk, and returns the reasoning behind the verdict plus a shortlist of plants suited to that light level.

  ConnectorNo auth

• agent-brain-smartA

  MeshMarketC

  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)

  ConnectorNo auth

• vault_get_pc_creation_optionsA

  Embers: Tabletop RPG ToolkitA

  Read the legal choices for guided character creation — the same projections vault's web wizard reads. Pass `ruleset` (one with guided creation: the `ruleset` field's list; list_rulesets gives each code's label) and `kind` to select one list: 'class' / 'species' / 'background' / 'feat' return the option projections (the calling user's own content plus stock, each option carrying its nested choices: skillChoices, toolChoices, startingEquipmentOptions, and per applied ability/feat — proficiencyChoices, spellChoices, spellListChoices, preparedSpells, and `choice` whose options carry a `type`; a background option also carries `skillChoices` + `languages`, a species option carries `languages`; background bump modes / feat, etc.); 'feat' returns every feat (a feat picked via an ability's `choice` carries its own proficiency/spell sub-choices); 'constants' returns the static reference data (skill list with attributes, ability-score methods with each method's data, language options + pick count, alignments, background bump modes, max ability score, and originFeatCategory — the feat category the background's open feat slot is restricted to; filter the 'feat' list to it for the background pick). Use this BEFORE `vault_build_pc` so every id and pick you send is one the user is actually entitled to. Start with 'constants' and 'class', then read 'species' / 'background' / 'feat' as the build takes shape.

  ConnectorOAuth

• banking_regulations_searchA

  Banking RegulationsA

  Keyword search across the US banking regulations — Federal Reserve, OCC, FDIC, CFPB and NCUA rules in 12 CFR. Answers "what banking regulations cover X", "the Federal Reserve regulation about X", "find the CFPB rule for X", "which consumer financial protection rule applies to X", "the bank compliance requirement for X". Great for topics: truth in lending disclosure, mortgage origination and servicing, closing disclosures and TRID, ability to repay and qualified mortgages, electronic fund transfers and error resolution, overdraft and remittances, fair lending and adverse action notices, HMDA reporting, funds availability and check holds, deposit insurance, risk-based capital and leverage ratios, liquidity coverage, transactions with affiliates, insider lending limits, bank holding company activities, stress testing, community reinvestment. Returns matching banking rules with citation (12 CFR), heading, excerpt, and source URL. Example: banking_regulations_search({ query: "truth in lending disclosure" }); banking_regulations_search({ query: "ability to repay qualified mortgage", limit: 15 }). Keyless.

  ConnectorNo auth

• services.listA

  Admin SubstituteA

  List all services in the company catalog with prices, descriptions, and categories. Useful for accurate quoting and understanding what the business offers.

  ConnectorNo auth