← Back to search

io.github.Lykhoyda/ask-gemini

Lykhoyda Scanned 5h ago

Bridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions

MCP Registry ↗
C
73.2 / 100

Versions

1.2.1latest
first seen Jun 5, 2026
1.4.5
first seen May 19, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 4

ask-llm
annotations: verified low

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.

readOnlyHint false openWorldHint true idempotentHint false destructiveHint false
ask-cursor-agent
annotations: verified low

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.

readOnlyHint true openWorldHint true idempotentHint false destructiveHint false
ping
annotations: verified low

Test connectivity with the MCP server

readOnlyHint true openWorldHint false idempotentHint true destructiveHint false
multi-llm
annotations: verified low

readOnlyHint false openWorldHint true idempotentHint false destructiveHint false

Permissions 4

network medium
Server uses network capabilities via: fetch(), net
filesystem low
Server uses filesystem capabilities via: fs, fs sync ops, path
shell high
Server uses shell capabilities via: child_process, spawn(), spawnSync()
env_vars low
Server uses env_vars capabilities via: process.env

Scan Findings 21

info
Tool 'ask-llm' annotations are consistent annotation_checker · 80%
info
Tool 'ask-cursor-agent' annotations are consistent annotation_checker · 80%
info
Tool 'ping' annotations are consistent annotation_checker · 80%
info
Tool 'multi-llm' annotations are consistent annotation_checker · 80%
medium
OAuth implementation without PKCE auth_checker · 75%
info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
medium
Vulnerable dependency: @modelcontextprotocol/sdk@1.30.0 (GHSA-6qxp-vccf-f47h) dependency_analyzer · 95%
info
package.json metadata manifest_parser · 100%
info
Tool: ask-llm manifest_parser · 85%
info
Tool: ask-cursor-agent manifest_parser · 85%
info
Tool: ping manifest_parser · 85%
info
Tool: multi-llm manifest_parser · 85%
info
Transport: stdio manifest_parser · 90%
info
Required env vars (89) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
medium
Permission: network access detected permission_analyzer · 90%
low
Permission: filesystem access detected permission_analyzer · 90%
high
Permission: shell access detected permission_analyzer · 95%
low
Permission: env_vars access detected permission_analyzer · 90%
info
SBOM generated: 29 components sbom_generator · 100%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%