io.github.Lykhoyda/ask-llm
NPM · @ASK-LLM/MCP
Unified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity
Available components
Last scanned (11 hours ago)
Scores higher than 76% of npm servers
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 30 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 22 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability82
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1181 tokens (~168/item across 7 items; 6 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (83% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 −3
- Stability: pass → 0.80 functional
- 20 Oct 26 +1
- Stability: 0.97 → pass security
- 19 Oct 26 −1
- Stability: pass → 0.97 functional
- 17 Oct 26 +2
- Stability: 0.87 → pass security
- 16 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Oct 26 +44
- Injection markers: unverified → pass ▲ security
- Tool coverage: unverified → 100 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Stability: unverified → 0.80 ▲ functional
- Package version: 1.2.0 → 1.2.1 functional
- 13 Oct 26 −46
- Stability: 0.97 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Stability: 0.97 → pass security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Package version: 1.2.0 → 1.2.1 functional
- 12 Oct 26 −1
- Stability: pass → 0.97 functional
- Package version: 1.1.0 → 1.2.0 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/@ask-llm/mcp@1.2.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
ask-cursor-agent ~238
Use Cursor Agent as a model-neutral, read-only consultation harness. The provider and exact Cursor catalog model ID are separate required fields. Runs `agent --print --mode ask` without --force/--trust, never changes spend settings, and never falls back to another model or provider.
| Name | Type | Req | Description |
|---|---|---|---|
| includeDirs | array | – | Relative additional workspace directories passed to Cursor Agent with repeatable --add-dir. |
| model | string | yes | Exact Cursor catalog model ID from `agent --list-models`; Ask LLM does not rewrite it, echoes it back as `model`, and refuses Auto or other noncanonical IDs. The CLI's display label is returned separ… |
| prompt | string | yes | Question, review, or analysis task for Cursor Agent ask mode. |
| provider | string | yes | Canonical provider family of the selected Cursor model (claude, codex, gemini, grok); kept separate from the cursor-agent harness and verified against the requested and CLI-reported model ID. |
| sessionId | string | – | Prior Cursor conversation ID to resume. Omit on the first call and reuse the returned sessionId. |
| Name | Type | Req | Description |
|---|---|---|---|
| harness | string | – | – |
| model | string | yes | – |
| provider | string | yes | – |
| reportedModel | string | – | – |
| response | string | yes | – |
| sessionId | string | – | – |
| usage | object | – | – |
No examples provided.
ask-llm ~581
Send a prompt to an LLM provider (Codex, Claude, Grok, Antigravity, Ollama, Gemini). Specify which provider to use. Provider-specific fallback behavior is reported truthfully; Grok never substitutes or falls back from the requested model. Returns both human-readable text and a structured response (provider, model, sessionId, usage) via outputSchema.
| Name | Type | Req | Description |
|---|---|---|---|
| harness | string | – | Execution harness, separate from provider/model. xai-api and grok-cli require provider=grok. Use ask-cursor-agent for Cursor's model-neutral harness. No harness fallback is attempted. |
| includeDirs | array | – | Relative workspace directories exposed to providers that support additional read roots (Codex, Claude, and Antigravity). Unsupported providers are rejected instead of silently dropping this option; C… |
| model | string | – | Exact model ID for the selected provider/harness. Usually not needed. |
| preferred | boolean | – | Codex-only: opt into ASK_CODEX_PREFERRED_MODEL when it differs from the default. Unsupported on other providers; never silently stripped. Leave unset for normal review calls. |
| prompt | string | yes | The question, code review request, or analysis task to send |
| provider | string | yes | Which LLM provider to use. Available: "gemini" (Gemini, default model: gemini-3.1-pro-preview), "codex" (Codex, default model: gpt-6-astra), "claude" (Claude, default model: opus), "grok" (Grok, defa… |
| reasoningEffort | string | – | Provider-native reasoning effort. Codex accepts low/medium/high/xhigh/max/ultra; Grok accepts low/medium/high/xhigh. Unsupported provider/effort combinations are rejected, never stripped. |
| sandbox | string | – | Codex-only sandbox. Defaults to the executor's read-only review contract when omitted. Set workspace-write only for explicit write flows such as image generation. Unsupported on other providers; neve… |
| sessionId | string | – | Optional session ID. For Codex, pass "" on the first call to create a persisted thread, then pass its returned Thread ID to resume; omitting it makes the call ephemeral. For other session-capable pro… |
| Name | Type | Req | Description |
|---|---|---|---|
| harness | string | – | – |
| model | string | yes | – |
| provider | string | yes | – |
| reportedModel | string | – | – |
| response | string | yes | – |
| sessionId | string | – | – |
| usage | object | – | – |
No examples provided.
diagnose ~56
Run a self-diagnosis of the MCP server's environment: Node version, resolved PATH, provider CLI presence and versions, key env vars. Returns a structured report and a human-readable summary. Read-only; never spawns LLM calls.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| checks | array | yes | – |
| environment | object | yes | – |
| generatedAt | string | yes | – |
| providers | array | yes | – |
| status | string | yes | – |
No examples provided.
get-usage-stats ~81
Get the current MCP server's session usage stats: total LLM calls, token totals (input/output/thinking/cached), wall time, and breakdowns per provider and per model. No data leaves your machine — counts are tracked in-memory for the lifetime of the server process. Returns both human-readable markdown and a structured JSON snapshot via outputSchema.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| byModel | object | yes | – |
| byProvider | object | yes | – |
| fallbackCount | number | yes | – |
| totalCachedTokens | number | yes | – |
| totalCalls | number | yes | – |
| totalDurationMs | number | yes | – |
| totalInputTokens | number | yes | – |
| totalOutputTokens | number | yes | – |
| totalThinkingTokens | number | yes | – |
No examples provided.
multi-llm ~164
Dispatch the same prompt to multiple LLM providers in parallel and return all responses in one structured payload. Use when you want to compare answers across Codex, Claude, Grok, Antigravity, Ollama, and Gemini, or when you want a multi-provider sanity check on a question. Returns per-provider success/failure, response text, model, sessionId, and token usage. Each call is fresh — no session continuity (use ask-llm for individual session-bearing calls).
| Name | Type | Req | Description |
|---|---|---|---|
| prompt | string | yes | The prompt to send to all selected providers in parallel. |
| providers | array | – | Which providers to dispatch to. Available: gemini, codex, claude, grok, ollama, antigravity. Defaults to all available providers. |
| Name | Type | Req | Description |
|---|---|---|---|
| dispatchedAt | string | yes | – |
| failureCount | number | yes | – |
| results | array | yes | – |
| successCount | number | yes | – |
| totalDurationMs | number | yes | – |
No examples provided.
ping ~30
Test connectivity with the MCP server
| Name | Type | Req | Description |
|---|---|---|---|
| message | string | – | A message to echo back to test the connection |
No output schema declared.
No examples provided.
How do I install the io.github.Lykhoyda/ask-llm MCP server?
io.github.Lykhoyda/ask-llm runs locally as an npm package, launched with npx -y @ask-llm/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @ask-llm/mcp
claude mcp add lykhoyda-ask-llm -- npx -y @ask-llm/mcp
What is the io.github.Lykhoyda/ask-llm MCP server?
io.github.Lykhoyda/ask-llm is an MCP server listed in the public MCP registry as io.github.Lykhoyda/ask-llm. Unified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity. This page covers its npm package (@ask-llm/mcp).
Is the io.github.Lykhoyda/ask-llm MCP server safe to use?
io.github.Lykhoyda/ask-llm scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.Lykhoyda/ask-llm MCP server expose?
io.github.Lykhoyda/ask-llm exposes 6 tools: ask-llm, ask-cursor-agent, ping, get-usage-stats, multi-llm, diagnose. Their descriptions and schemas cost roughly 1,150 tokens of context every time the server is loaded.
Is the io.github.Lykhoyda/ask-llm MCP server still maintained?
io.github.Lykhoyda/ask-llm is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.Lykhoyda/ask-llm MCP server under?
io.github.Lykhoyda/ask-llm declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the io.github.Lykhoyda/ask-llm MCP server?
VerifyMCP ran 16 checks on io.github.Lykhoyda/ask-llm, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.