Claude MarketplacesSubmit

Gemini Code Context Mcp

qmediat/gemini-code-context-mcp

Connects Claude to Gemini's 2M-token context cache, turning your codebase into persistent memory for repeat queries. Three patterns: `ask` eagerly uploads the whole workspace and caches it (measured 8× faster, 4× cheaper on subsequent calls), `ask_agentic` lets Gemini lazily explore via sandboxed file tools for arbitrarily large repos, and `code` delegates implementation tasks with native thinking budget and optional execution. First run takes 45 seconds to 2 minutes to build the cache; follow-ups hit in 13 to 16 seconds. Backed by a Polish tech company (qmediat.io) running this in production, so it ships updates every week or two instead of going stale. Beats the unmaintained `gemini-mcp-tool` with direct SDK integration and actual caching.

tools: 6
auth: Secret needed
transport: STDIO
env vars: 9
last updated: Oct 6, 2026

Tools

6 tools

Public tool metadata for what this MCP can expose to an agent.

askQ&A and long-context analysis against your workspace. Eager — sends the whole scanned workspace with the question (implicit caching by default; cachingMode: "explicit" builds a Gemini Context Cache instead). Best for repeat queries on a repo ≤ ~900 k tokens.

Q&A and long-context analysis against your workspace. Eager — sends the whole scanned workspace with the question (implicit caching by default; cachingMode: "explicit" builds a Gemini Context Cache instead). Best for repeat queries on a repo ≤ ~900 k tokens.

No parameter schema in public metadata yet.

ask_agenticSame question shape as ask, but agentic — Gemini uses sandboxed list_directory / find_files / read_file / grep tools to read only what each question needs. Scales to arbitrarily large repos; no eager upload.

Same question shape as ask, but agentic — Gemini uses sandboxed list_directory / find_files / read_file / grep tools to read only what each question needs. Scales to arbitrarily large repos; no eager upload.

No parameter schema in public metadata yet.

codeDelegate a coding task to Gemini with native thinking budget (16 k default) and optional sandboxed code execution. Returns structured OLD/NEW diffs Claude Code can apply directly.

Delegate a coding task to Gemini with native thinking budget (16 k default) and optional sandboxed code execution. Returns structured OLD/NEW diffs Claude Code can apply directly.

No parameter schema in public metadata yet.

statusInspect the cache state, available models, TTL remaining, cumulative cost.

Inspect the cache state, available models, TTL remaining, cumulative cost.

No parameter schema in public metadata yet.

reindexForce a fresh cache rebuild for this workspace.

Force a fresh cache rebuild for this workspace.

No parameter schema in public metadata yet.

clearDelete the cache and manifest for this workspace.

Delete the cache and manifest for this workspace.

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly

Agent CaffeineSponsoredClose your lid, come back to finished work

SnugSponsoredThe clipboard manager for the AI era Promote your product hereReach 125k+ visitors monthly

WaxSponsoredBlock anything with supervision, without erasing your iPhone Promote your product hereReach 125k+ visitors monthly

knobsSponsoredSee your site on any phone, any day, in any language

Configuration

GEMINI_CREDENTIALS_PROFILE

Profile name in ~/.config/qmediat/credentials (chmod 0600). Created by `npx @qmediat.io/gemini-code-context-mcp init`. Recommended; keeps your API key out of ~/.claude.json.

GEMINI_API_KEYsecret

Fallback Tier 3 auth. Your Gemini API key. Emits a warning at startup recommending you move it to the credentials profile via the init command.

GEMINI_USE_VERTEX

Set to `true` to use Vertex AI backend via Application Default Credentials. Requires GOOGLE_CLOUD_PROJECT.

GOOGLE_CLOUD_PROJECT

GCP project ID when using Vertex AI backend. Only read when GEMINI_USE_VERTEX=true.

GEMINI_DAILY_BUDGET_USD

Hard daily USD cap enforced locally. Server refuses calls after the cap until UTC midnight. Unlimited if unset. Honoured by `ask`, `code`, and per-iteration by `ask_agentic`.

GEMINI_CODE_CONTEXT_DEFAULT_MODEL

Model alias (`latest-pro-thinking`, `latest-pro`, `latest-flash`, `latest-lite`, `latest-vision`) or literal model ID, read by ask, ask_agentic and code. Default: `latest-pro-thinking` (the thinking tier). code replaces a configured default that resolves but cannot reason or thin

GEMINI_CODE_CONTEXT_CACHING_MODE

`implicit` (default since v1.14.0: the workspace text is sent inline, Gemini's automatic prefix cache decides any discount) or `explicit` (Files API upload + Context Cache with Google's cached-input price). Per-call `cachingMode` wins.

GEMINI_CODE_CONTEXT_CACHE_TTL_SECONDS

Context Cache TTL in seconds in explicit caching mode. Default: 3600 (1 hour). Hot workspaces (<10 min since last use) auto-refresh via background watcher.

GEMINI_CODE_CONTEXT_LOG_LEVEL

`debug` | `info` | `warn` | `error`. Default: `info`.

Readme

`@qmediat.io/gemini-code-context-mcp`

Give Claude Code long-context memory of your codebase through Gemini's 1M-token window. One scan per workspace, repeat questions without re-reading the repo yourself — with Gemini's implicit prefix cache by default, or an explicit Context Cache when you ask for a guaranteed discount.

View the full README on GitHub

Details

Repository: github.com/qmediat/gemini-code-context-mcp
Category: AI & LLM Tools
Package: @qmediat.io/gemini-code-context-mcp
Transport: STDIO
Auth: Required
Registry: MCP registry, active

More from qmediat

Ideogram Mcp

Related AI & LLM Tools MCP servers

1

Sequential Thinking Working Notesarben-adm/mcp-sequential-thinkingLocal working notes, decisions, evidence and resumable sessions with SQLite persistence.960stars

2

Shodh Memoryvarun29ankus/shodh-memoryCognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.217stars

3

Gemini Cloud Assist Mcpgooglecloudplatform/gemini-cloud-assist-mcpMCP Server for understanding, managing & troubleshooting your GCP environment.63stars

4

Geminihoutini-ai/gemini-mcpModel Context Protocol server for Google Gemini AI with chat, research, and grounding34stars

5

Neverinfamous Memory Journal Mcpneverinfamous/memory-journal-mcpA MCP server built for developers enabling Git based project management with project and personal…17stars

6

Pmll Memory Mcpdrqedwards/ppmPMLL Memory MCP — persistent KV context memory and Q-promise deduplication.14stars