"Ways to Improve Thinking Skills" matching MCP tools:

• ateam_redeploy

  ateam-mcp

  Re-deploy skills WITHOUT changing any definitions. ⚠️ HEAVY OPERATION: regenerates MCP servers (Python code) for every skill, pushes each to A-Team Core, restarts connectors, and verifies tool discovery. Takes 30-120s depending on skill count. Use after connector restarts, Core hiccups, or stale state. For incremental changes, prefer ateam_patch (which updates + redeploys in one step).

  Connector

• ateam_build_and_run

  ateam-mcp

  Build and deploy a governed AI Team solution in one step. ⚠️ HEAVIEST OPERATION (60-180s): validates solution+skills → deploys all connectors+skills to A-Team Core (regenerates MCP servers) → health-checks → optionally runs a warm test → auto-pushes to GitHub. AUTO-DETECTS GitHub repo: if you omit mcp_store and a repo exists, connector code is pulled from GitHub automatically. First deploy requires mcp_store. After that, write files via ateam_github_write, then just call build_and_run without mcp_store. For small changes to an already-deployed solution, prefer ateam_patch (faster, incremental). Requires authentication.

  Connector

• aws___retrieve_skill

  AWS Knowledge

  Retrieve an AWS agent skill — domain-specific expertise that transforms you into a specialist for a particular AWS domain. Skills provide workflows, context, best practices, decision frameworks and step-by-step procedures. A skill may include reference files (architecture docs, schemas, examples) and deterministic workflows for sub-tasks that require exact execution. ## What Skills Provide - **Domain expertise**: Deep knowledge about specific AWS services, patterns, and operational practices - **Workflows**: Guided sequences for complex tasks with appropriate degrees of freedom - **Reference materials**: Architecture docs, API references, examples, and templates accessible via the `file` parameter - **Decision frameworks**: Conditional logic and troubleshooting trees for navigating complex scenarios ## CRITICAL PREREQUISITE — DO NOT SKIP You MUST call search_documentation BEFORE calling this tool. NEVER call this tool first. You do NOT know skill names — they are unpredictable identifiers that can only be discovered through search_documentation results. Guessing or fabricating a skill_name WILL fail. ## REQUIRED WORKFLOW (no exceptions) 1. FIRST: Call search_documentation with the user's requirements 2. THEN: Find the result entry that has a skill_name field 3. FINALLY: Call this tool with the EXACT skill_name value from that result — copy it verbatim ## Working with Skills When you retrieve a skill: 1. Read the SKILL.md overview to understand the domain and scope 2. Follow the workflows and guidance in the skill body 3. When the skill references additional files (e.g., `[architecture](references/architecture.md)`), retrieve them using this same tool with the `file` parameter 4. Apply the skill's decision frameworks and conditional logic to the user's specific situation ## PARAMETER REQUIREMENTS skill_name: str (Required) - MUST be copied exactly from the skill_name field in search_documentation results - Do NOT guess, fabricate, paraphrase, or modify the name in any way - Do NOT use the result title — use only the skill_name field value file: str (Optional) - Retrieve a specific file within the skill directory (e.g., "references/architecture.md") - Use this when the SKILL.md body links to reference files - If omitted, returns the main SKILL.md file ## IF SKILL NOT FOUND If you get an error, you likely guessed the name. Call search_documentation first to discover it. The error response will include a list of available files for the skill. ## Returns The skill content — either the main SKILL.md with domain expertise, workflows, and guidance, or a specific reference file when the `file` parameter is provided.

  Connector

• getJobDetails

  qubitsok — Quantum Computing Jobs, Papers & Researchers

  Get full details for a specific quantum computing job by its numeric ID. Use after searchJobs when the user wants more information about a specific position. Returns: job summary, required skills, nice-to-have skills, responsibilities, visa sponsorship, salary, location, and apply URL. Requires a valid job_id from searchJobs results. Returns error if ID not found.

  Connector

• get_job

  JobGPT

  Get detailed information about a specific job listing/posting by its job listing ID (not application ID). Use this to view the full job posting details including description, salary, skills, and company info. For job application details, use get_application instead.

  Connector

• search_humans

  Human Pages

  Search for humans available for hire. Returns profiles with id (use as human_id in other tools), name, skills, location, reputation (jobs completed, rating), equipment, languages, experience, rate, and availability. All filters are optional — combine any or use none to browse. Key filters: skill (e.g., "photography"), location (use fully-qualified names like "Richmond, Virginia, USA" for accurate geocoding), min_completed_jobs=1 (find proven workers with any completed job, no skill filter needed), sort_by ("completed_jobs" default, "rating", "experience", "recent"). Default search radius is 30km. Response includes total count and resolvedLocation. Contact info requires get_human_profile (registered agent needed). Typical workflow: search_humans → get_human_profile → create_job_offer.

  Connector

• get_human_state

  Nefesh — Real-Time Human State Awareness for AI

  Get current unified human state for a session. Call this before generating important responses. Returns: - state: calm | relaxed | focused | stressed | acute_stress - stress_score: 0-100 (lower = calmer) - confidence: 0.0-1.0 (based on signal quality and device type) - suggested_action: maintain_engagement | simplify_and_focus | de-escalate_and_shorten | pause_and_ground - action_reason: human-readable explanation of why this action was suggested - adaptation_effectiveness (on 2nd+ call): shows whether your previous suggested_action actually reduced stress — contains previous_action, stress_delta, and effective boolean. Use this to self-improve. Use suggested_action to adapt your response: calm/relaxed = full complexity, focused = shorter and structured, stressed = max 2 sentences, acute_stress = one grounding sentence only. Requires a prior ingest call to have data. Not a medical device.

  Connector

• search_skills

  AiPayGen — 65+ AI Tools as an MCP Server

  Search 646+ skills using TF-IDF semantic search. Returns ranked skills with scores. Use this to discover capabilities before calling execute_skill.

  Connector

• sieve_screen

  Sieve

  Run a Sieve IMPACT-X Quick Screen on a startup. Analyzes the company across 7 dimensions (Innovators, Market, Product, Advantage, Commerce, Traction, X-Factor) and returns an analysis ID. Takes 2-5 minutes to complete. Upserts -- if the company was previously screened, returns the existing deal (set confirm=true to re-screen). Two ways to use: - v3 (recommended): First add documents with sieve_dataroom_add, then call sieve_screen(deal_id=...) to analyze everything in the data room. - v2 (legacy): Call sieve_screen(company_name=..., website_url=...) directly. At least one of website_url or pitch_deck_text is required in this mode. Args: company_name: Name of the startup to screen (v2 flow, or to create new deal). deal_id: Screen an existing deal by ID (v3 flow -- use after sieve_dataroom_add). website_url: Company website URL (v2 flow). pitch_deck_text: Extracted pitch deck text (v2 flow). description: Brief company description (optional). confirm: Set to true to re-screen an existing deal.

  Connector

• get_human

  Human Pages

  Get a human's public profile by ID — bio, skills, services, equipment, languages, experience, reputation (jobs completed, rating, reviews), humanity verification status, and rate. Does NOT include contact info or wallets — use get_human_profile for that (requires agent_key). The id can be found in search_humans results.

  Connector

• collect_feedback

  mcp-server

  Collects user feedback on the provided response. **When to use this tool:** - After providing an analysis, a SQL query, or an important response - When you want to know if the response was helpful - Naturally suggest: "Was this response helpful? 👍 👎" **Ratings:** - 'positive': The response was helpful and accurate - 'negative': The response was not satisfactory - 'neutral': Neither satisfied nor dissatisfied **Categories (optional):** - 'accuracy': Was the response accurate? - 'relevance': Did the response address the question? - 'completeness': Was the response complete? - 'speed': Was the response time acceptable? - 'other': Other feedback **Feedback usage:** Feedback is used to improve future responses (RAG, analytics).

  Connector

• ateam_upload_connector

  ateam-mcp

  Upload connector code to Core and restart — WITHOUT redeploying skills. Use this to update connector source code (server.js, UI assets, plugins) quickly. Set github=true to pull files from the solution's GitHub repo, or pass files directly. Much faster than ateam_build_and_run for connector-only changes.

  Connector

• match_jobs

  AI Dev Jobs

  Rank active AI/ML jobs against a candidate profile (skills, salary range, workplace, level). Scoring combines tag overlap (+2 per match), salary overlap (+3), workplace/level/type/location matches, and description keyword hits. Use this when an agent is choosing which role to surface to its user — it returns pre-ranked matches with scoring explanations.

  Connector

• interpret_result

  QueueSim

  Given an M/M/c configuration (arrivalRate, serviceRate, servers) and optionally an observed average wait, returns a queueing-theory framed interpretation: where you sit on the utilization curve, what ρ means in plain language, what one more or fewer server would qualitatively do, and which complexity factors (priority, abandonment, skills routing) might be hiding in real data the M/M/c model can't see. Use this to TEACH while answering — when the user wants context around a number, not just the number itself. Pure text computation, no simulation, no RNG — deterministic output.

  Connector

• analyze_work_image

  connect

  Return the primary image URL and current metadata for a work, so you can visually analyze the image yourself and propose structured catalogue fields. Use this when the artist asks you to read a work you uploaded, or when beat 2 of the add-work flow surfaced thin hints. The image URL is publicly accessible (Supabase Storage public bucket); fetch it and inspect the image directly with your vision capabilities. Fields you can honestly improve from a visual read: medium (paint vs. print vs. sculpture material vs. digital), classification (painting / sculpture / drawing / photography / time-based / software / installation / performance), visible signature or inscription (transcribe verbatim, note position), date visible in the work itself (distinct from EXIF), description (brief factual read of subject matter), dimensions if a scale reference is in frame. Fields to leave alone unless visible: dimensions without scale (cannot be honestly estimated from a flat photo), attribution, provenance, exhibition history — those come from records, not the image. Flow: (1) call this tool; (2) fetch + read the image; (3) present your proposals to the artist with per-field reasoning; (4) on confirmation, call update_work with the accepted patches. Do not write without confirmation. Resolve the work by workId (UUID) or uwi (e.g. "RAI-2026-00417"). Use search_natural_language to find workId — never ask the user.

  Connector

• skincare_report_issue

  La Luer — AI Skincare Commerce

  Report when a tool result was unhelpful, incomplete, or wrong. Call this whenever you override a recommendation, skip a cart result, or notice the engine output doesn't match what the user needs. Do not use proactively — only when you observe an actual issue. This helps improve the engine.

  Connector

• list-models

  Roundtable

  List available AI models grouped by thinking level (low/medium/high). Shows default models, credit costs, capabilities for each tier. Use this before consult to understand model options.

  Connector

• skincare_report_issue

  SearchShop AI

  Report when a tool result was unhelpful, incomplete, or wrong. Call this whenever you override a recommendation, skip a cart result, or notice the engine output doesn't match what the user needs. Do not use proactively — only when you observe an actual issue. This helps improve the engine.

  Connector

• submit_feedback

  Partle

  Send freeform feedback about your experience using Partle. Use when you encounter a confusing tool description, a broken response, missing data, or anything you'd want the maintainers to know. Especially valuable for AI agents — your feedback is a tuning signal we use to improve the API. Don't loop (each call adds a record). Not idempotent. No PII required. Args: feedback: Freeform text up to 5000 characters. Be specific — name the tool, the input that was confusing, and what you expected. Returns: ``{"id": int, "message": "Thanks for the feedback!"}`` on success, or ``{"error": ...}`` if the input is empty or too long.

  Connector

• ateam_get_workflows

  ateam-mcp

  Get the builder workflows — step-by-step state machines for building skills and solutions. Use this to guide users through the entire build process conversationally. Returns phases, what to ask, what to build, exit criteria, and tips for each stage.

  Connector