"Comparison or information about VS Code and Claude AI coding assistant" matching MCP tools:

• list_topicsA

  Umesh Malik Blog & ProfileA

  List the curated topic hubs (Claude Code, MCP, AI Search, LLM Engineering, AI Coding Agents) with their URLs.

  ConnectorNo auth

• compare_toolsA

  Vibe ShippedA

  Use when the user asks to compare AI coding tools, app builders or agents ('X vs Y'). Returns sourced pricing, licence and features side by side. Example: {"tools":["cursor","claude-code"]}

  ConnectorNo auth

• get_toolA

  Vibe ShippedA

  Use when you need current pricing or facts for one AI coding tool or agent harness by slug (cursor, claude-code, lovable, cline...). Example: {"slug":"cursor"}

  ConnectorNo auth

• map_agent_oversightA

  7IT SolutionsA

  Use this when someone asks which actions their AI agent or its connected tools may take on their own, which need a person's approval, and which a person must do; or how to set up human oversight, permissions or AI governance for an agent (for example under the EU AI Act). Give either the address of a public MCP server, or the list of tools the agent has (name, description and annotations). Sorts every tool into green (runs alone: reads and prepares), yellow (a person approves: sending, updating, scheduling) or red (a person does it: money, permissions, deletion, code execution, commitments), flags tools with no risk annotations, and returns a ready policy, Claude Code permission rules (allow, ask, deny) and an oversight checklist. Reads tool lists only and never calls a tool. A working checklist, not legal advice.

  ConnectorNo auth

• dante.remediate_hallucinationA

  Dante IX — Brand & GEO IntelligenceA

  Synthesize structured semantic counterweight artifacts to correct an inaccurate or outdated claim (hallucination) made by an AI assistant (ChatGPT, Perplexity, or Google Gemini) about a brand. Returns a JSON package (`markdown_counterweight_block`, `html_claim_review_snippet`, `faq_json_ld_script`, `verification_prompts`, and `domain_seal_sha256`). Side effects & latency: Purely deterministic, read-only synthesis (<300ms) with zero external LLM calls and zero destructive behavior. Security & parameter constraints: `brand_name` must match the stem of `domain_url`, and `verified_fact` must not contain third-party foreign URLs. Auth & quota: Consumes 0 live audit credits. Runs in 30% preview mode at $0 cost when `DANTE_API_KEY` is omitted; returns 100% unredacted `ClaimReview` and `FAQPage` artifacts when called with a paid `dnt_live_` license key. When to use: Use `dante.remediate_hallucination` when an AI assistant is actively stating false pricing, wrong features, or outdated ownership about a brand and you need an authoritative `Schema.org ClaimReview` + `FAQPage` correction block. Use `dante.forge_geo_shield` instead for general site-wide `/llms.txt` and `Organization` schema generation, or `dante.probe_geo_share` to check current AI citations.

  ConnectorNo auth

• assets.listA

  AI Design BlueprintA

  Public: list downloadable doctrine and agent asset artifacts (skill packs, rule packs, MCP setup snippets) the user can drop into their AI coding tool to import the Blueprint as native skill/rule files. Returns a list of assets with name, format (one of: zip / md / markdown / mdc / json / toml / text, the full vocabulary), pack_version, download_url, and platform target (Claude Code, Cursor, Codex, Gemini, Qwen). The response also carries `count` (length of `assets`) for symmetry with principles.list / clusters.list / guides.list. WHEN TO CALL: the user asks how to bring the Blueprint into their coding agent, or wants to install it as a local skill/rule file. WHEN NOT TO CALL: for the live MCP tools themselves, those are already available through this server. For doctrine content, prefer principles.list/get and guides.list/get. BEHAVIOR: read-only, idempotent, no auth required. Asset artefacts are regenerated on every deploy from the canonical doctrine.

  ConnectorNo auth

• assets.listA

  AI Design Blueprint DoctrineA

  Public: list downloadable doctrine and agent asset artifacts (skill packs, rule packs, MCP setup snippets) the user can drop into their AI coding tool to import the Blueprint as native skill/rule files. Returns a list of assets with name, format (one of: zip / md / markdown / mdc / json / toml / text, the full vocabulary), pack_version, download_url, and platform target (Claude Code, Cursor, Codex, Gemini, Qwen). The response also carries `count` (length of `assets`) for symmetry with principles.list / clusters.list / guides.list. WHEN TO CALL: the user asks how to bring the Blueprint into their coding agent, or wants to install it as a local skill/rule file. WHEN NOT TO CALL: for the live MCP tools themselves, those are already available through this server. For doctrine content, prefer principles.list/get and guides.list/get. BEHAVIOR: read-only, idempotent, no auth required. Asset artefacts are regenerated on every deploy from the canonical doctrine.

  ConnectorNo auth

• check_ai_visibilityA

  AIGROWA

  Scans how AI assistants see one business: reads its website, writes the buyer questions a customer would ask an assistant, puts them to the models behind ChatGPT, Claude, Gemini and Grok, and reports how often the business was named, a score out of 100, who was named instead and what holds it back. A scan takes about three minutes. This call waits up to forty seconds and returns the result when it is ready, or else how far the scan has got; get_visibility_scan reads it after that. Calling again with the same website, city and category joins the same scan instead of starting another. Scans are limited per user and per day, and a city or category makes it a new scan, even of a website scanned before.

  ConnectorNo auth

• send_messageA

  ISMS CopilotA

  Continue a conversation with the ISMS Copilot GRC specialist on the same deliverable: refine the same policy, extend the same gap analysis, or ask the next question. Use it with the conversation_id that create_conversation returned. Do not use it to start a new deliverable (create_conversation), or while the previous turn is still generating: wait for get_reply, since a send then is rejected. assistant (optional): switches the assistant from this turn on; omit to keep it, 'general' for the general specialist. Rule: a task to do takes the job id even when it names a framework; a question about one framework takes that framework's id; else omit assistant. - questionnaire-responder: use when answering or assessing a security questionnaire - audit-prep: use when preparing an internal or external audit - implementation-lead: use when asked for a plan or roadmap to implement or certify a framework - incident-lead: use when an incident or breach is under way or just happened (what now, notification duties) - iso27701: use when about ISO 27701 privacy management - iso42001: use when about ISO 42001 AI management - nis2: use when about NIS 2 - dora: use when about DORA - eu-ai-act: use when about the EU AI Act - cra: use when about the Cyber Resilience Act Options: mode and answer_format as on create_conversation. Returns conversation_id, message_id and status: 'complete' with response, or 'generating': then poll get_reply. Limit errors include reset_at and what to do; when one carries fallback_available: true, resend the same message with overflow_consent: true only on the user's explicit go-ahead (no duplicate message is saved). Relay docgen_notice to the user when present. Do not include passwords, API keys, payment card numbers, health records or government ID numbers. Answers are informational, not legal advice.

  ConnectorAPI key

• handoff-to-humanA

  Chatway Live ChatA

  Request human-agent handoff for a Chatway conversation that is currently handled by a Chatway AI assistant. Returns an error if no AI assistant is assigned to the conversation; in that case, assign a teammate with `assign-conversation` or add a private note instead. This records a handoff request but does not guarantee that a human has joined or replied. Use it when the customer asks for a person or the request cannot be handled with the available tools; after handoff, do not reply with `send-message`.

  ConnectorOAuth

• create_keyA

  Roar AIA

  Create a new roar_live_ API key for an app or script the person is building. The key itself is never returned here: the result carries a one-time `setupCode` (works once, expires in 15 minutes). A coding agent working on the project redeems it by sending POST `setupUrl` with JSON {"code": setupCode}, then saves the returned api_key as ROAR_API_KEY in the project's .env, never in source code. `baseUrl` is the OpenAI-compatible endpoint the key is used against. A key whose code is not redeemed in time stops working; create another. If no coding agent is involved, the person can create and copy a key in the Roar AI console under API keys. Any MANAGEMENT scope you grant must be one your own key already holds; `inference` may always be granted. To query or test a model yourself, do not mint a key: use send_message.

  ConnectorOAuth

• check_ai_readinessA

  PageCriticA

  Fetches a public page as a normal browser and as GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-User and PerplexityBot, then reports which AI bots are blocked or get a challenge page, the robots.txt rule for each AI bot, how much text is visible without JavaScript, JSON-LD types, sitemap, Markdown versions and llms.txt, with a 0-100 score and prioritized fixes. Use it when someone asks whether ChatGPT, Claude or Perplexity can see or cite their site, or why their site does not show up in AI answers. Do not use it to judge design or copy (use audit_landing_page). It uses plain HTTP fetches, takes about 5-15 seconds, and is free (15 checks per hour per client).

  ConnectorNo auth

• sign_inA

  UpForkA

  Only when the user wants something that needs their UpFork account: saying a lesson worked or didn't, their account, installing a product that isn't free, a product's AI prompt, support tickets, their profile and résumé, articles, lesson drafts or team lessons. Ask the user first. Their AI app then opens upfork.dev for them to sign in (in Claude Code: /mcp, choose upfork, Authenticate) and connects again with the tools for those. Everything else here works without it.

  ConnectorNo auth

• startModpackUploadA

  PixlyA

  Only for an assistant that can send the user's file with HTTP PUT, such as a coding agent with a shell. Begins uploading a Modrinth .mrpack or a CurseForge modpack .zip (up to 1 GiB). Returns uploadId, key, fileName and parts (url valid one hour): PUT each piece, keep each ETag, then completeModpackUpload. Installing is refused while a modpack is set unless completeModpackUpload is called with replace.

  ConnectorNo auth

• startModpackUploadA

  PixlyA

  Only for an assistant that can send the user's file with HTTP PUT, such as a coding agent with a shell. Begins uploading a Modrinth .mrpack or a CurseForge modpack .zip (up to 1 GiB). Returns uploadId, key, fileName and parts (url valid one hour): PUT each piece, keep each ETag, then completeModpackUpload. Installing is refused while a modpack is set unless completeModpackUpload is called with replace.

  ConnectorNo auth

• check-repoA

  Jeevesus — DugganUSA threat-intel MCPA

  Before you open or run a repository someone else sent you (a recruiter's coding test, a downloaded zip, a proof of concept), pass it the few files that matter and get a verdict. It looks for the places a lure hides that a dependency check never reads: npm install hooks that fetch or evaluate code, a VS Code task set to run when the folder opens, agent hooks and MCP servers in .claude, .cursor and .mcp.json, dev container lifecycle commands (initializeCommand runs on your own machine), yarnPath and foreign npm registries, git or URL dependencies, source that decodes and evaluates a payload, and setup.py that fetches or executes. Prompted by the 2026-10-29 Binance theft, where a compromised engineer's laptop is the first account and fake recruitment coding tests are the documented route of the group blamed. Static and local: nothing is fetched, run or stored. Pass { "files": { "<path>": "<file text>" } } with at most 40 files and 28000 characters in total (package.json, .vscode/tasks.json, .claude/settings.json, .mcp.json, .devcontainer/devcontainer.json, .yarnrc.yml, .npmrc, setup.py and any suspicious script). For a whole directory use the command line scanner or the DugganUSA Checks GitHub Action. Returns {verdict:"block"|"review"|"no-findings"|"unknown", findings:[{rule, severity, verdict, file, line, evidence, message, fix}], coverage, note}. "no-findings" means none of the listed patterns were seen in the files you sent; it does NOT mean the repository is safe. "unknown" means nothing was analyzed. Read the code on a machine that holds no credentials before you run it. One tool call, no auth.

  ConnectorNo auth

• tokendiet_count_tokensA

  Clawhard StudioA

  Use when the user asks how many tokens a text, prompt, log, document or code paste is, whether it fits a context window (128K, 200K, 1M), or how big something is before they send it to an AI. Returns the exact o200k token count (GPT-4o family and later; Claude and Gemini usually within about 15%), plus words, characters and how much of each window it uses. Counts are exact for that tokenizer. Example: {"text": "<the text to measure>"}. Not for shortening text.

  ConnectorNo auth

• tokendiet_count_tokensA

  Token DietA

  Use when the user asks how many tokens a text, prompt, log, document or code paste is, whether it fits a context window (128K, 200K, 1M), or how big something is before they send it to an AI. Returns the exact o200k token count (GPT-4o family and later; Claude and Gemini usually within about 15%), plus words, characters and how much of each window it uses. Counts are exact for that tokenizer. Example: {"text": "<the text to measure>"}. Not for shortening text.

  ConnectorNo auth

• ga4_ai_trafficA

  GSCPAP - Google Search Console, GA4, PageSpeed Insights & live SERPs MCPB

  Traffic from AI assistants (ChatGPT, Perplexity, Gemini, Claude, Copilot, ...): how much, which engines, which pages they send people to, and how it compares with Google organic on the same pages. Use for "do AI assistants recommend my site?", "how much traffic does ChatGPT send?", "which of my pages does ChatGPT link to?", GEO / AEO / LLM visibility questions. This measures visits, the outcome of being recommended. It cannot see answers that mention the site without a click. A session counts as AI traffic when GA4 put it in its "AI Assistant" channel OR its source is a known assistant. The channel alone misses about 10% (measured over 446 properties), filed as Referral; `ai_sessions_outside_ai_channel` says how many that was here. `property_id="all"` returns one summary row per GA4 property the user can see (first 25), for comparing a portfolio of sites in one call. Reading the result: - `ai_to_organic` is the comparable number across sites (AI sessions per Google organic session); `ai_share_of_total` depends on how much direct/paid/social traffic the site has. - Conversion numbers come from GA4 over exactly the AI sessions (`sessionKeyEventRate`, `transactions`, `purchaseRevenue`), never from dividing summed rows. Key events are whatever the property marked, so quote them next to `transactions`. Across 77 measured properties the AI key-event rate matched organic (median ratio 1.06): do not tell the user AI visitors convert better unless this property shows it. - `pages` lists where AI assistants land people, each with its organic sessions beside it. A page AI sends people to that Google barely does (or the reverse) is the finding to surface. - `weekly_ai_sessions` is by ISO week; the last week is usually partial. - `engines[].key_events` are summed key events, which exceed sessions wherever a session fires several. Take rates from `ai_totals`.

  ConnectorAPI key

• cem_answerA

  CEMA

  Use for any question about CEM (the Compounding Execution Method) or a term it defines, such as the Drift Tax, the Pendulum, the Governor, Sweeps, Cycles or operator levels, and for questions about building or operating with AI that CEM's research covers. Returns CEM's own definition with its code (cite it, e.g. F-003) and the best research documents, each with its code, one-line summary and page. Free and instant. Use it first; ask_cem writes a longer answer when someone wants to go deeper.

  ConnectorNo auth

• check-repoA

  Jeevesus — DugganUSA threat-intel MCPA

  Before you open or run a repository someone else sent you (a recruiter's coding test, a downloaded zip, a proof of concept), pass it the few files that matter and get a verdict. It looks for the places a lure hides that a dependency check never reads: npm install hooks that fetch or evaluate code, a VS Code task set to run when the folder opens, agent hooks and MCP servers in .claude, .cursor and .mcp.json, dev container lifecycle commands (initializeCommand runs on your own machine), yarnPath and foreign npm registries, git or URL dependencies, source that decodes and evaluates a payload, and setup.py that fetches or executes. Prompted by the 2026-10-29 Binance theft, where a compromised engineer's laptop is the first account and fake recruitment coding tests are the documented route of the group blamed. Static and local: nothing is fetched, run or stored. Pass { "files": { "<path>": "<file text>" } } with at most 40 files and 28000 characters in total (package.json, .vscode/tasks.json, .claude/settings.json, .mcp.json, .devcontainer/devcontainer.json, .yarnrc.yml, .npmrc, setup.py and any suspicious script). For a whole directory use the command line scanner or the DugganUSA Checks GitHub Action. Returns {verdict:"block"|"review"|"no-findings"|"unknown", findings:[{rule, severity, verdict, file, line, evidence, message, fix}], coverage, note}. "no-findings" means none of the listed patterns were seen in the files you sent; it does NOT mean the repository is safe. "unknown" means nothing was analyzed. Read the code on a machine that holds no credentials before you run it. One tool call, no auth.

  ConnectorNo auth