{"slug": "io-github-lykhoyda-ask-llm-io-github-lykhoyda-ask-llm-0-9-3", "title": "io.github.Lykhoyda/ask-llm (io.github.Lykhoyda/ask-llm@0.9.3)", "summary": "The MCP server io.github.Lykhoyda/ask-llm reached version 0.9.3, published to the official MCP registry on 2026-09-13 and distributed as @ask-llm/mcp on npm, according to the mcpindex registry listing. The server unifies Gemini, Codex, Claude, Grok, Ollama, and Antigravity, declares 16 environment variables, and received a PARTIAL semantic-screen verdict from mcpindex that found no malicious instructions in its description via static_description, though the deterministic conformance probe has not yet run. mcpindex notes the registry listing changed after the screen ran, so the assessed description no longer matches the current listing.", "body_md": "[← Index](/leaderboard)\n\n# io.github.Lykhoyda/ask-llm\n\nUnified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity\n\nThe current version, v0.9.3, was published to the official MCP registry on 2026-09-13. It is distributed as @ask-llm/mcp on npm, filed under AI & LLMs by this index, and declares 16 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; [the index's current counts](/stats) put this record in context.\n\n## Using io.github.Lykhoyda/ask-llm in Claude, Cursor, Gemini CLI, Cline, or Zed?\n\nMCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and **HOLDs the call** when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use **Install this server** for that).\n\nRewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less\n\n```\nuv tool install mcpindex-gate && mcpindex-config-wire\n```\n\n[method](/methodology)\n\nSemantic screen found no manipulation pattern in the description. Conformance probe not yet run.\n\n`mcpindex.integrity.description` passINFO\nevidence“No malicious instructions”via static_description\n\n- - Semantic screen only - the deterministic conformance probe has not run on this server\n- - Confidence is reported but not yet calibrated (v1)\n- - Screen reads the tool description, not the live behavior\n- - advisory\n- - registry description only no input schema\n- - screen model 8b\n- - The registry listing (version, packages, links) changed after this screen ran - the description we assessed did not\n\nSemantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.\n\nOwn this server? [Screen its description →](/screen)\n\n## That verdict was true at screening time (snapshot 2026-09-13).\n\nContracts can change after screening, with no version bump. The gate pins io.github.Lykhoyda/ask-llm’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.\n\n[See your first HOLD in 2 minutes →](/guides/install-the-gate-first-hold)\n\nRelated: [how to trust an MCP server](/guides/how-to-trust-an-mcp-server) · [screen before install](/guides/screen-mcp-server-before-install) · [silent contract drift](/guides/mcp-silent-contract-drift)\n\nPeople vet a server before wiring it in. One line on your project site or docs answers that with an independent record: screening verdict, registry provenance, contract drift history. It stays current as new screens and drift events land.\n\n```\n[Independent trust record for io.github.Lykhoyda/ask-llm](https://mcpindex.ai/server/io-github-lykhoyda-ask-llm) - screening verdict, registry provenance, and contract drift monitoring.\n<a href=\"https://mcpindex.ai/server/io-github-lykhoyda-ask-llm\">Independent trust record for io.github.Lykhoyda/ask-llm</a> - screening verdict, registry provenance, and contract drift monitoring.\n```\n\nA live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.\n\n```\n[![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-lykhoyda-ask-llm)](https://mcpindex.ai/server/io-github-lykhoyda-ask-llm)\n<a href=\"https://mcpindex.ai/server/io-github-lykhoyda-ask-llm\"><img src=\"https://mcpindex.ai/api/v1/badge/io-github-lykhoyda-ask-llm\" alt=\"mcpindex verdict\" height=\"20\" /></a>\n```\n\n`XAI_API_KEY`\nxAI API key for metered Grok requests; Ask LLM never enables billing or credits\n\n`ASK_GROK_HARNESS`\nExplicit Grok harness: xai-api (default) or grok-cli; no failover\n\n`ASK_GROK_MODEL`\nExact selected-harness model override (API default grok-4.6; CLI default grok-build; no fallback)\n\n`ASK_GROK_REASONING_EFFORT`\nGrok reasoning effort: low, medium, high, or xhigh (default: high)\n\n`ASK_GROK_MAX_OUTPUT_TOKENS`\nxAI API output-token ceiling to bound accidental spend (default: 16384)\n\n`ASK_GROK_TIMEOUT_MS`\nTimeout for xAI API requests in milliseconds (default: 600000)\n\n`CURSOR_API_KEY`\nOptional Cursor CLI credential for ask-cursor-agent; alternative to agent login\n\n`ASK_CURSOR_TIMEOUT_MS`\nTimeout for model-neutral Cursor Agent harness calls (default: 600000)\n\n`ASK_CLAUDE_MODEL`\nDefault Claude model alias or full model name (default: opus)\n\n`ASK_CLAUDE_FALLBACK_MODEL`\nClaude CLI fallback when Opus is overloaded or unavailable (default: sonnet)\n\n`ASK_CLAUDE_TIMEOUT_MS`\nTimeout for Claude CLI execution in milliseconds (default: 600000 = 10 minutes)\n\n`OLLAMA_HOST`\nOllama server address (default: http://localhost:11434)\n\n`ASK_ANTIGRAVITY_TIMEOUT_MS`\nTimeout for Antigravity (agy) execution in milliseconds (default: 300000 = 5 minutes)\n\n`ASK_ANTIGRAVITY_SANDBOX`\nSet to '0' to drop agy's --sandbox flag if it blocks --add-dir context reads (default: sandbox on)\n\n`GMCPT_TIMEOUT_MS`\nTimeout for CLI execution in milliseconds (default: 300000 = 5 minutes)\n\n`GMCPT_LOG_LEVEL`\nLog verbosity: debug, info, warn, error (default: warn)\n\n[methodology](/methodology)\n\n[Codex Delegateio.github.andreilungeanu/codex-delegate-mcp](/server/io-github-andreilungeanu-codex-delegate-mcp)\n\nBridge AI coding hosts to the OpenAI Codex CLI for delegated implementation.\n\n[BridgeNode MCPio.github.bridgenode-ai/bridgenode-mcp](/server/io-github-bridgenode-ai-bridgenode-mcp)\n\nBridgeNode — x402 pay-per-request AI inference. OpenAI-compatible API + MCP, Solana USDC, gas-free.\n\n[io.github.MGM-FALCON/quelllm-mcpio.github.MGM-FALCON/quelllm-mcp](/server/io-github-mgm-falcon-quelllm-mcp)\n\nMCP server for quelllm.fr: 190+ open-weights LLM catalog - list, compare, VRAM and cost estimates", "url": "https://wpnews.pro/news/io-github-lykhoyda-ask-llm-io-github-lykhoyda-ask-llm-0-9-3", "canonical_source": "https://mcpindex.ai/server/io-github-lykhoyda-ask-llm", "published_at": "2026-09-13 14:15:23+00:00", "updated_at": "2026-09-13 14:40:05.437692+00:00", "lang": "en", "topics": ["ai-tools", "ai-products", "developer-tools", "ai-agents"], "entities": ["io.github.Lykhoyda/ask-llm", "@ask-llm/mcp", "mcpindex", "Gemini", "Codex", "Claude", "Grok", "Ollama"], "alternates": {"html": "https://wpnews.pro/news/io-github-lykhoyda-ask-llm-io-github-lykhoyda-ask-llm-0-9-3", "markdown": "https://wpnews.pro/news/io-github-lykhoyda-ask-llm-io-github-lykhoyda-ask-llm-0-9-3.md", "text": "https://wpnews.pro/news/io-github-lykhoyda-ask-llm-io-github-lykhoyda-ask-llm-0-9-3.txt", "jsonld": "https://wpnews.pro/news/io-github-lykhoyda-ask-llm-io-github-lykhoyda-ask-llm-0-9-3.jsonld"}}