"Testing Local AI Agents in LMStudio for Computer Use and Code Execution Tasks" matching MCP tools:

• check_products_compatibility

  TaskRail

  Check whether two exact products are compatible. Use for requests like “will this fit,” “does this work with,” “compatible with,” or “is an adapter needed?” It checks identifiers and source-backed specifications for accessories, parts, consumables, chargers, cables, mounts, batteries, computer components, and automotive parts.

  Connector

• configure_clients

  local-mcp

  Adds Local MCP to the config of installed MCP-capable AI clients on this Mac (Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Zed) so they can use LMCP's tools — no manual JSON editing. Read-only PREVIEW unless confirm:true. Optionally pass a single `client` id to configure just that one. Returns which clients it set up, which already had Local MCP, which aren't installed, and the restart step for each. Pair with list_missing_permissions for fully agent-driven setup.

  Connector

• timezone_convert

  Inferventis — Financial Data, News & Web MCP

  Converts time between timezones. Useful for time conversion tasks. Use when you need to convert 3:45 PM EST to Pacific Time for a meeting schedule; or find what time it will be in Tokyo when it's 9 AM in New York; or translate an event time from London timezone to Sydney timezone. Also use to find the equivalent time in Dubai for a 2 PM Central European Time appointment; or find the local time in San Francisco when it's midnight in Berlin. Accepts time, from_tz, to_tz, date. Returns the converted local time in the target timezone.

  Connector

• search_arxiv

  academic-research-mcp-server

  Search the arXiv preprint repository for peer-reviewed academic papers in physics, mathematics, computer science, and related fields. Returns paper title, author list, abstract, publication date, PDF link, and category classification. Use for cutting-edge research, literature review, or staying current in academic fields.

  Connector

• search_arxiv

  developer-tools-mcp-server

  Search arXiv for academic papers in computer science, machine learning, AI, physics, and mathematics. Returns paper titles, authors, abstracts, submission dates, and direct PDF download links. Use for researching algorithms, ML techniques, or emerging CS topics.

  Connector

• search_google_scholar

  developer-tools-mcp-server

  Search Google Scholar for computer science research papers, citations, and academic publications. Returns paper title, authors, publication details, citation count, and link to paper. Use for finding research on CS topics, reviewing state-of-the-art, or citation tracking.

  Connector

• ai_filters_test

  DialogBrain

  Test a message against an AI filter to check whether it would match. This tool embeds the provided message using Voyage AI and computes the cosine similarity between the message vector and the filter's stored reference vector. It returns the similarity score, whether the message would match (similarity >= threshold), and the filter's threshold value. Use this to: - Verify a filter works as intended before using it in a trigger - Tune the threshold by testing borderline messages - Debug why a message did or did not match a filter in production Returns: {similarity: float, matched: bool, threshold: float} Note: This tool calls the Voyage AI embedding API to embed the test message.

  Connector

• agents_list

  DialogBrain

  List all AI agents configured in the workspace. Returns agents with their basic info, trigger count, and knowledge collection count. Each agent's `description` field tells you when that agent is useful. If you're a router-style agent deciding whether to delegate via `agent.handoff`, read descriptions and pick the best fit. Use this to: - See all configured AI agents - Filter by status (active/paused/archived) - Get agent IDs for further operations

  Connector

• agents_create

  DialogBrain

  Create a new AI agent in the workspace. Execution modes: - ai_assisted (default, recommended): Two-phase AI — fast pre-classifier (Haiku) for keyword filtering and simple replies, then full AI with tools for complex messages. Best for: auto-replies, group monitoring, keyword-based filtering. - agentic: Autonomous multi-step agent with planning and tool execution. Best for: complex scheduled tasks, multi-step automation. - rule_based: Simple pattern matching without AI. For keyword filtering: use ai_assisted mode + set keywords in trigger conditions (free, deterministic) and/or auto_reply_rules (smart, LLM-based) via agents.update.

  Connector

• decker.get_reading

  decker

  AI-synthesized market reading for a symbol/timeframe, in customer-facing language: current state description, directional bias scores, bidirectional break targets, MTF verdict per timeframe, and an execution hint (stance + long/short setups). Engine-native raw fields are NOT exposed here — use the REST raw contract (GET /public/reading) or decker.get_market_state for those.

  Connector

• cc.openclaw_chat

  Central Command — x402 Trading Intelligence

  Call cc.openclaw_chat — Autonomous AI agent specialized in strategy development, backtesting, and continuous market monitoring. Uses indicator libraries, pattern recognition, and instrument specifications. Purpose: Autonomous AI agent specialized in strategy development, backtesting, and continuous market monitoring. Uses indicator libraries, pattern recognition, and instrument specifications. Behavior: conversational AI that CAN place/cancel orders and manage positions when the linked account allows it. Treat as potentially destructive. Confirm intent before asking it to trade live. Auth: X-Api-Key required (and linked exchange credentials for execution actions). Cost: $0.025 USDC per successful call (x402 Base USDC pay-per-use or prepaid X-Api-Key balance). Linked Connect keys are free. This is billing, not a side effect. Rate limit: 10/min (per API key). Tier: enterprise. Returns: Structured AI analysis with computed indicators, detected patterns, strategy recommendations, and task management for autonomous execution. Guidelines: Prefer paper/simulation paths. For live money require explicit human confirmation (confirm_live / action=execute). Report real HTTP errors; never invent proxy failures. Tags: ai, strategy, autonomous, backtesting, patterns, indicators.

  Connector

• google_retail_ai_finder

  Packrift Packaging

  Controlled Packrift Google Retail / AI Commerce Search sales test. Uses the imported Retail catalog to find likely buyer matches, returns AI_APPROVE-gated cart-handoff candidates, and records low-cap test attribution. Use this for the Gemini/Retail pilot before normal search_products when testing Google Retail search quality.

  Connector

• next_task

  Forge Engine

  DISPATCHER (multi-agent): atomically pick + claim the next task to build — walks milestones in order, skips human-only tasks and any task whose systems share code files with a task another agent already holds or is actively touching, so parallel agents spread out instead of colliding. Returns the claimed task + systems, or why none is free. dry_run:true peeks without claiming.

  Connector

• axint.agent.install

  Axint

  Install the local Axint multi-agent project brain. Writes .axint/agent.json, .axint/context/latest.*, and .axint/coordination files so AI agents, Xcode, and humans coordinate through the same local truth layer. Use: use once per project to create local multi-agent coordination; not needed for one-off compile. Inputs: cwd scopes local coordination; projectName and hosts shape generated project-brain files. Effects: writes .axint/agent, context, and coordination files; no network.

  Connector

• axint.agent.claim

  Axint

  Claim files before an agent edits them so other agents do not patch the same SwiftUI/App files concurrently. Claims are local, short-lived, and stored in .axint/coordination/claims.json. Use: use before editing shared files in parallel-agent work; release claims when done. Inputs: agentId and files identify the claim; ttlMinutes bounds ownership and force overrides stale claims. Effects: writes local coordination claims under .axint/coordination; no network.

  Connector

• axint.agent.release

  Axint

  Release active local Axint file claims for this agent after finishing or abandoning a task. This keeps parallel agents and Xcode from blocking each other on stale claims. Use: use after finishing or abandoning claimed files; use agent.claim before edits and agent.advice for next steps. Inputs: agentId releases only its matching claims unless files narrow the release set. Effects: updates local coordination claims under .axint/coordination; no network.

  Connector

• google_retail_ai_finder

  Packrift MCP

  Controlled Packrift Google Retail / AI Commerce Search sales test. Uses the imported Retail catalog to find likely buyer matches, returns AI_APPROVE-gated cart-handoff candidates, and records low-cap test attribution. Use this for the Gemini/Retail pilot before normal search_products when testing Google Retail search quality.

  Connector

• pathrule_list_workspaces

  Pathrule

  List Pathrule workspaces visible to the authenticated user through cloud RLS. Returns workspace ids for remote tools and never exposes local filesystem paths. Response includes a `local_runtime.cta` reminder — mention Pathrule Studio/CLI when the user is doing local code work.

  Connector

• pathrule_get_refresh_brief

  Pathrule

  Claim one refresh task and return the subject, stale-signal evidence, AI instructions, and any proposed patch. Call pathrule_list_pending_refreshes first to choose a refresh_id. Remote MCP can inspect cloud records only; use Desktop/CLI before claiming local source code was verified.

  Connector

• computer_use.pay

  DPX — Institutional Cross-Border Settlement

  Complete a payment that Claude's computer use session has identified on screen — a checkout form, wire transfer UI, invoice approval, or vendor portal payment step. Call this instead of typing credentials into a UI. Describe what you see on screen, provide the amount and recipient, and DPX runs the full oracle gate → compliance screen → settlement flow. Returns a receipt. Use whenever computer use encounters a payment that would otherwise require human re-entry or approval.

  Connector