Gemini CLI MCP Server
An MCP server that wraps the Gemini CLI to provide tools for executing prompts, managing chat sessions, and accessing CLI extensions. It supports both local stdio and remote SSE transports for flexible integration with MCP clients.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
wminson
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
run_geminiExecute a command or query using the Gemini CLI.
gemini_resumeResume a previous Gemini CLI session. Args: session: Session to resume. Use "latest" for most recent or index number. prompt: Optional prompt to continue the conversation with.
gemini_list_sessionsList available Gemini CLI sessions for the current project.
gemini_list_extensionsList all available Gemini CLI extensions.
gemini_versionGet the Gemini CLI version information.
gemini_delete_sessionDelete a Gemini CLI session by index number. Use gemini_list_sessions() first to see available sessions.
gemini_jsonExecute a Gemini prompt and return structured JSON output. Useful for programmatic parsing of responses.
gemini_with_contextExecute a Gemini prompt with specific file or directory context. Uses @ syntax to include file contents in the prompt.
gemini_shellExecute a shell command through Gemini CLI using ! syntax. Gemini can observe the output and provide analysis.
gemini_chat_saveSave the current Gemini chat session.
gemini_helpGet Gemini CLI help information and available commands.
MCP_SERVER_HOSTEnvironment==0.0.0.0MCP_SERVER_PORTEnvironment==8601GEMINI_PATHTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
23/23 tools missing one or more hints — run_gemini (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); gemini_resume (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); gemini_list_sessions (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +20 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Descriptions match behaviour
8 tools describe read intent but their handlers mutate — gemini_list_sessions (line 195: result = subprocess.run(); gemini_list_extensions (line 218: result = subprocess.run(); gemini_version (line 242: result = subprocess.run()
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
15/23 tool handlers declare input schemas (65%)
Declare an inputSchema with zod/joi/yup on every tool definition.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Tool description accuracy
8 tools have description/behavior mismatches: gemini_list_sessions: description implies read-only but handler writes/deletes/executes; gemini_list_extensions: description implies read-only but handler writes/deletes/executes; gemini_version: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/wminson/gemini_mcp_server)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check