Stdio MCP server that lets Claude ask the Google Gemini CLI for large-file, codebase, brainstorming, and sandboxed analysis while preserving MCP tool and prompt workflows inside Claude Code or compatible MCP clients.
Gemini MCP Tool runs locally but invokes the Gemini CLI, so prompts, file references, and command output can leave the local machine through the configured Google Gemini account or API path., The `ask-gemini` tool can pass `@` file or directory references to Gemini CLI; current source checks that references stay under the working directory, but users should still scope prompts carefully., Sandbox mode is exposed as an option on `ask-gemini` and forwards the Gemini CLI sandbox flag; review generated scripts, network calls, package installs, and filesystem changes before relying on sandboxed output., Change mode can generate structured edit suggestions for Claude to apply; inspect proposed OLD/NEW replacements before applying them to source files., Treat the project as an unofficial third-party bridge, not an official Google MCP server.
Privacy notes
Prompts, selected source files, directory context, code snippets, local paths, command output, change-mode chunks, and brainstorming context may be sent to Gemini CLI and the configured Gemini service., Avoid referencing `.env` files, credentials, private keys, customer data, unreleased product plans, or regulated datasets in `@` references., The MCP server and Gemini CLI may log execution details locally; protect terminal history, MCP client logs, and Gemini CLI configuration files., Google account, project, retention, and telemetry behavior depends on the user's Gemini CLI configuration and Google service terms.
Author
jamubc
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
4 prerequisites to line up before setup. Includes a review or approval gate.
0/4 ready
Install & runtime3Review & approval110 minutes
Safety & privacy surface
Safety & privacy surface
5 safety and 4 privacy notes across 6 risk areas. Review closely: credentials & tokens, permissions & scopes, network access, third-party handling.
6 areas
SafetyLocal filesGemini MCP Tool runs locally but invokes the Gemini CLI, so prompts, file references, and command output can leave the local machine through the configured Google Gemini account or API path.
SafetyPermissions & scopesThe `ask-gemini` tool can pass `@` file or directory references to Gemini CLI; current source checks that references stay under the working directory, but users should still scope prompts carefully.
SafetyNetwork accessSandbox mode is exposed as an option on `ask-gemini` and forwards the Gemini CLI sandbox flag; review generated scripts, network calls, package installs, and filesystem changes before relying on sandboxed output.
SafetyLocal filesChange mode can generate structured edit suggestions for Claude to apply; inspect proposed OLD/NEW replacements before applying them to source files.
SafetyThird-party handlingTreat the project as an unofficial third-party bridge, not an official Google MCP server.
PrivacyThird-party handlingPrompts, selected source files, directory context, code snippets, local paths, command output, change-mode chunks, and brainstorming context may be sent to Gemini CLI and the configured Gemini service.
PrivacyCredentials & tokensAvoid referencing `.env` files, credentials, private keys, customer data, unreleased product plans, or regulated datasets in `@` references.
PrivacyLocal filesThe MCP server and Gemini CLI may log execution details locally; protect terminal history, MCP client logs, and Gemini CLI configuration files.
PrivacyData retentionGoogle account, project, retention, and telemetry behavior depends on the user's Gemini CLI configuration and Google service terms.
Disclosure: Gemini MCP Tool is an unofficial third-party project and is not affiliated with, endorsed by, or sponsored by Google. The npm package metadata reports MIT, but the repository LICENSE file is titled "MIT License (Non-Commercial)" and prohibits commercial use without written permission.
Safety notes
Gemini MCP Tool runs locally but invokes the Gemini CLI, so prompts, file references, and command output can leave the local machine through the configured Google Gemini account or API path.
The `ask-gemini` tool can pass `@` file or directory references to Gemini CLI; current source checks that references stay under the working directory, but users should still scope prompts carefully.
Sandbox mode is exposed as an option on `ask-gemini` and forwards the Gemini CLI sandbox flag; review generated scripts, network calls, package installs, and filesystem changes before relying on sandboxed output.
Change mode can generate structured edit suggestions for Claude to apply; inspect proposed OLD/NEW replacements before applying them to source files.
Treat the project as an unofficial third-party bridge, not an official Google MCP server.
Privacy notes
Prompts, selected source files, directory context, code snippets, local paths, command output, change-mode chunks, and brainstorming context may be sent to Gemini CLI and the configured Gemini service.
Avoid referencing `.env` files, credentials, private keys, customer data, unreleased product plans, or regulated datasets in `@` references.
The MCP server and Gemini CLI may log execution details locally; protect terminal history, MCP client logs, and Gemini CLI configuration files.
Google account, project, retention, and telemetry behavior depends on the user's Gemini CLI configuration and Google service terms.
Prerequisites
Node.js 16 or newer.
Google Gemini CLI installed, authenticated, and configured before starting the MCP server.
A Claude Code, Claude Desktop, or compatible MCP client configuration that can run stdio servers.
Review of any `@file` or `@directory` references before sending prompts through Gemini CLI.
Gemini MCP Tool is an unofficial third-party project and is not affiliated with, endorsed by, or sponsored by Google. The npm package metadata reports MIT, but the repository LICENSE file is titled "MIT License (Non-Commercial)" and prohibits commercial use without written permission.
Gemini MCP Tool connects Claude to the Google Gemini CLI through a local stdio
MCP server. It is designed for workflows where Claude should ask Gemini for a
second-pass analysis, use Gemini's larger context window on selected files or
directories, brainstorm alternatives, or request structured edit suggestions
without leaving the MCP client.
The server exposes MCP tools and prompts from a unified registry. Current
source registers ask-gemini, brainstorm, fetch-chunk, Ping, and Help
tools, with test-only tools gated behind an environment variable. The
ask-gemini implementation supports optional model selection, sandbox mode,
change mode, and chunk continuation. The Gemini executor validates @ file
references against the current working directory before passing prompts to the
Gemini CLI.
These sources were reviewed on 2026-06-06. Prefer the live repository,
README, docs site, npm registry metadata, package manifest, stdio server
implementation, tool registry, ask-gemini implementation, Gemini CLI
executor, chunk helper, and license file for current install paths, tool
registration, sandbox behavior, file-reference handling, package metadata, and
licensing.
Features
Local stdio MCP server distributed as the gemini-mcp-tool npm package.
Claude Code one-line setup through claude mcp add gemini-cli -- npx -y gemini-mcp-tool.
Claude Desktop configuration through npx -y gemini-mcp-tool, or global
gemini-mcp after package installation.
MCP tools and prompts for asking Gemini, brainstorming, fetching chunked
change-mode output, pinging the server, and showing help.
Optional Gemini model selection, with the README documenting
gemini-2.5-pro as the default.
Optional Gemini CLI sandbox flag from the verified ask-gemini tool path.
Change mode for structured OLD/NEW edit suggestions, including chunk cache
retrieval for large responses.
Working-directory checks for @ file references before prompts reach Gemini
CLI's file-inlining parser.
Unofficial third-party project with a non-commercial repository license text.
Installation
Install and configure the Google Gemini CLI first. Then add the MCP server to
Claude Code:
claude mcp add gemini-cli -- npx -y gemini-mcp-tool
For Claude Desktop or another compatible MCP client, use the npm package through
npx:
Restart the MCP client after editing configuration, then use the client's MCP
status view to confirm the gemini-cli server is active.
Use Cases
Ask Gemini to summarize a large file, dependency manifest, or directory using
the Gemini CLI @ reference syntax.
Get a second-model review of code architecture, bug hypotheses, or refactor
options while keeping Claude as the primary coding assistant.
Use brainstorming prompts to compare approaches before changing a complex
codebase.
Request sandboxed Gemini CLI analysis for risky scripts, generated commands,
package installs, or code experiments.
Generate structured change-mode suggestions that Claude can inspect and apply
in smaller chunks.
Keep a local MCP workflow while using the separately installed Gemini CLI for
authentication and provider access.
Safety and Privacy
Gemini MCP Tool is a bridge from Claude to another model provider path. Anything
included in a prompt, selected through an @ reference, shown in terminal
output, or summarized in a change-mode response can be sent through Gemini CLI
under the user's configured Google account or API context.
Use the smallest useful file references, keep prompts inside the intended
repository, and avoid secrets or regulated data. The source currently validates
that @ references stay inside the working directory, but that does not make
the selected project files safe to disclose. Review proposed OLD/NEW changes
before applying them, and treat sandboxed runs as risk-reducing rather than
risk-free.
The project is not affiliated with Google. Its package metadata and README
describe MIT licensing, while the repository license text is non-commercial, so
commercial users should review licensing with the project owner before adopting
it.
Duplicate Check
Existing MCP content includes Google, search, code-analysis, and local CLI
servers, but no dedicated gemini-mcp-tool, gemini-cli MCP bridge, or
jamubc/gemini-mcp-tool entry was found in content/mcp. Gemini MCP Tool is
distinct because it documents the npm-distributed stdio server that calls the
Google Gemini CLI from Claude and exposes verified Gemini analysis, brainstorm,
change-mode, and chunk-retrieval workflows.
Show that Gemini MCP Tool is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/gemini-mcp-tool)
How it compares
Gemini MCP Tool side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
Stdio MCP server that lets Claude ask the Google Gemini CLI for large-file, codebase, brainstorming, and sandboxed analysis while preserving MCP tool and prompt workflows inside Claude Code or compatible MCP clients.
High-performance MCP server that indexes codebases into a persistent knowledge graph for structural search, call tracing, architecture summaries, dead-code detection, and cross-repo analysis.
Local-first context-engineering MCP server and CLI that gives Claude token-efficient file reads, shell-output compression, code search, graph queries, persistent session memory, context packaging, verification tools, and dashboard-style token accounting through a single Rust binary.
✓Gemini MCP Tool runs locally but invokes the Gemini CLI, so prompts, file references, and command output can leave the local machine through the configured Google Gemini account or API path.
The `ask-gemini` tool can pass `@` file or directory references to Gemini CLI; current source checks that references stay under the working directory, but users should still scope prompts carefully.
Sandbox mode is exposed as an option on `ask-gemini` and forwards the Gemini CLI sandbox flag; review generated scripts, network calls, package installs, and filesystem changes before relying on sandboxed output.
Change mode can generate structured edit suggestions for Claude to apply; inspect proposed OLD/NEW replacements before applying them to source files.
Treat the project as an unofficial third-party bridge, not an official Google MCP server.
✓Codebase Memory MCP reads source files across indexed repositories and writes MCP entries, instruction files, skills, hooks, and agent configuration files during install.
The background watcher and auto-index features can keep graph data updated as source files change.
The optional graph UI exposes a local visualization server on a localhost port.
Shared graph artifacts and SQLite databases can persist source metadata after an MCP session ends.
Verify downloaded release binaries, checksums, signatures, and provenance before running them in sensitive environments.
✓Context+ can inspect source files, build AST and embedding indexes, run static analysis, create memory graph nodes, and propose code changes.
The `propose_commit` tool is designed to write code after validation and creates shadow restore points before saving.
Static analysis tools may invoke local compilers, linters, or language tools depending on the repository.
Runtime caches and memory graph data can persist source-derived embeddings and relationships after the MCP session ends.
External embedding providers can receive source-derived text, identifiers, prompts, and cluster-labeling context.
✓LeanCTX can read local files, run shell commands invoked through its tools, cache outputs, install shell/editor hooks, and persist session state.
Review generated MCP and shell-hook changes before enabling them across all agents or shells.
Keep path jail enforcement enabled for normal use, and allow extra roots only when a project genuinely needs them.
Disable or restrict command-execution and unsafe I/O tools for regulated repositories, untrusted workspaces, or shared team environments.
Treat compressed shell output and cached reads as summaries; switch to full reads or raw command output when exact source text matters.
Privacy notes
✓Prompts, selected source files, directory context, code snippets, local paths, command output, change-mode chunks, and brainstorming context may be sent to Gemini CLI and the configured Gemini service.
Avoid referencing `.env` files, credentials, private keys, customer data, unreleased product plans, or regulated datasets in `@` references.
The MCP server and Gemini CLI may log execution details locally; protect terminal history, MCP client logs, and Gemini CLI configuration files.
Google account, project, retention, and telemetry behavior depends on the user's Gemini CLI configuration and Google service terms.
✓Source code, filenames, paths, symbols, comments, imports, routes, call graphs, architecture summaries, ADRs, graph queries, prompts, and tool outputs may be visible to the MCP client and model provider.
Persistent graph databases and shared artifacts can retain proprietary architecture, internal package names, route names, service boundaries, and accidentally committed secrets.
Auto-indexing broad workspace roots can include unrelated private repositories or generated files.
Avoid committing shared graph artifacts unless the repository owners explicitly approve storing derived code intelligence in version control.
✓Source code, file paths, symbol names, comments, identifiers, embeddings, memory nodes, relations, prompts, API keys, static-analysis output, proposed diffs, and tool results may be visible to the MCP client and model provider.
Proprietary codebases can expose internal architecture, feature maps, naming conventions, secrets accidentally present in code, and product plans.
Keep API keys and provider base URLs out of committed MCP configs, logs, screenshots, and shared prompts.
Review `.mcp_data` and generated restore-point data before sharing workspaces or artifacts.
✓Local code, file paths, command output, search terms, session notes, context packages, knowledge graph data, token metrics, and dashboard statistics can be sent to the MCP client and model.
LeanCTX stores local stats and session state under its own configuration/data directories; protect these files if they contain project decisions, findings, or sensitive paths.
Secret-like paths are blocked or role-gated by default according to upstream security docs, but users should still avoid prompting agents to read credentials, private keys, tokens, or ignored files.
The upstream security policy describes optional update checks and opt-in anonymous stats sharing; disable network checks when working in confidential or offline environments.
Prerequisites
Node.js 16 or newer.
Google Gemini CLI installed, authenticated, and configured before starting the MCP server.
A Claude Code, Claude Desktop, or compatible MCP client configuration that can run stdio servers.
Review of any `@file` or `@directory` references before sending prompts through Gemini CLI.
A local repository or workspace you are authorized to index.
Platform-compatible Codebase Memory MCP release binary verified before use.
Agent configuration write access reviewed before running the installer.
Sensitive paths, generated files, vendored code, secrets, and private repositories reviewed before indexing.
Node.js and npx available to the MCP client runtime.
A repository or workspace you are authorized to index and expose to an MCP client.
Ollama embedding model available, or an approved OpenAI-compatible embedding provider and API key.
Static analysis tools installed if you want Context+ to run native linters or compilers.
npm for the `lean-ctx-bin` package, or another upstream-supported install path such as release binaries, Homebrew, Cargo, or AUR.
A local repository workspace where LeanCTX is allowed to read files, run configured shell commands, and store session metadata.
Review of generated MCP client config, shell hooks, per-project `.lean-ctx.toml`, and global `~/.config/lean-ctx/config.toml`.
Explicit allow-listing for any paths outside the current project root that LeanCTX should be permitted to access.