Ext Ops Panel
Open dashboard
Comparison

ask-llm vs Perplexity API Platform

ask-llm is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑30.

ask-llm is a plugin bundle for AI coding tools published by Anton Lykhoyda. No marketplace we read lists it any more. Perplexity API Platform is an MCP server published by perplexity.ai. Marketplaces we read that list it: 4 (Official MCP Registry, Docker MCP Catalog, npm registry (MCP servers), Community GitHub marketplaces). As of our marketplace pass on 2026-11-08. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplaceask-llmPerplexity API Platform
Community marketplace lykhoyda/ask-llm Removed on 2026-10-30
Version: 1.2.1
Forks (GitHub): 5
Stars (GitHub): 18
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 1.2.1
Downloads/month (npm): 87 686
Downloads/week (npm): 18 636
Not marked · First seen
Docker MCP Catalog Not listed Listed
Version: sha256:7816f45a6f26
Forks (GitHub): 392
Pulls (Docker Hub): 81 744
Stars (Docker Hub): 17
Stars (GitHub): 2 612
Not marked · First seen
npm registry (MCP servers) Not listed Listed
Version: 1.3.0
Downloads/month (npm): 87 686
Downloads/week (npm): 18 636
Forks (GitHub): 392
Stars (GitHub): 2 613
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

ask-llm vs Perplexity API Platform
Factask-llmno longer listed · Perplexity API Platform
Marketplaces that list it (differs)04
Stars (GitHub) (differs)182 613
Pulls (Docker Hub) (differs)No figure on Docker Hub81 744
Forks (GitHub) (differs)5392
Last release (differs)Not published2026-10-17
Where it runs (differs)On your machine (@ask-llm/codex-mcp)On your machine (@perplexity-ai/mcp-server)
Transport (differs)Not statedstdio
Tools it declares (differs)Not published3
Environment variables it asks for (differs)Not published2, secrets among them: 1
Hooks it runs (differs)51
Parts of the bundle (differs)542
LicenceMITMIT
Repository (differs)github.com/lykhoyda/ask-llmgithub.com/ppl-ai/modelcontextprotocol
Changes in the last 7 days (differs)04
First seen (differs)2026-10-132026-10-11

Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.

What to use instead of ask-llm

Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.

  • multi-ai-consultant

    Consult external AIs (Gemini 2.5 Pro, OpenAI Codex, Claude) for second opinions. Use for debugging failures, architectural decisions, security validation, or need fresh…

    by Claude Skills Maintainers · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • codex

    Launch OpenAI Codex for software architecture analysis and research

    by paddo · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • codex-advisor

    Get a second opinion from GPT-6 Astra via Codex CLI before big decisions.

    by Fatih C. Akyon · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • tunaLlama

    Delegate heavy code generation to a local LLM (Ollama / Ollama Cloud / LM Studio). Search + memory layer + Codex CLI compatibility.

    by d9ng (hang-in) · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • thread-keeper

    Multi-agent shared brain across Claude, Codex, Antigravity, Gemini, Copilot, and VS Code.

    by po4erk91 · MCP server

    Listed on: Official MCP Registry · Describes nearly the same job

  • second-opinion

    Get a second opinion from the OpenAI (Codex), Google (Antigravity CLI, agy) or Anthropic (Claude Code) CLIs. Single provider, multi-round consultation, diff review, or multi-model…

    by Petr Simecek · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

Its card, with similar plugins by marketplace

What each says it does

ask-llm

In its own words, on Community GitHub marketplaces:

AI-to-AI collaboration — review code and debate plans across Codex, Grok, Antigravity, Ollama, and Gemini providers

Perplexity API Platform

In its own words, on Official MCP Registry:

Real-time web search, reasoning, and research through Perplexity's API

How to run each

ask-llm

No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.

Perplexity API Platform As a local MCP server: npm package

Claude Code
claude mcp add --transport stdio perplexity-api-platform -- npx -y @perplexity-ai/mcp-server

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

The marketplaces of ask-llm publish no list of tools, so we do not compare tools.

Settings each asks for

The marketplaces of ask-llm publish no settings it asks for, so we do not compare settings.

What it can do: ask-llm · What it can do: Perplexity API Platform · Compare two other plugins

Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Package data comes from the public npm registry (registry.npmjs.org). Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built