Gemini Code Context MCP
by qmediat
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | No | Fallback API key (Tier 3; emits a warning) | |
| GEMINI_USE_VERTEX | No | Enable Vertex AI backend (set to 'true' or '1') | |
| GOOGLE_CLOUD_PROJECT | No | Google Cloud project ID for Vertex AI (required if GEMINI_USE_VERTEX is set) | |
| GEMINI_DAILY_BUDGET_USD | No | Hard cap on daily spend in USD | unlimited |
| GEMINI_CREDENTIALS_PROFILE | No | Profile name in the credentials file | default |
| GEMINI_CODE_CONTEXT_LOG_LEVEL | No | Log level: debug, info, warn, error | info |
| GEMINI_CODE_CONTEXT_DEFAULT_MODEL | No | Default model alias or literal ID | latest-pro |
| GEMINI_CODE_CONTEXT_ASK_TIMEOUT_MS | No | Wall-clock timeout in ms for ask (1s–30min) | |
| GEMINI_CODE_CONTEXT_CODE_TIMEOUT_MS | No | Wall-clock timeout in ms for code | |
| GEMINI_CODE_CONTEXT_FORCE_MAX_OUTPUT | No | Force every call to send maxOutputTokens = model.outputTokenLimit | false |
| GEMINI_CODE_CONTEXT_CACHE_TTL_SECONDS | No | Cache TTL in seconds | 3600 |
| GEMINI_CODE_CONTEXT_TPM_THROTTLE_LIMIT | No | Client-side tokens-per-minute ceiling per resolved model (0 disables) | 80000 |
| GEMINI_CODE_CONTEXT_WORKSPACE_GUARD_RATIO | No | Fraction of model.inputTokenLimit that workspace may fill before fail-fast | 0.9 |
| GEMINI_CODE_CONTEXT_AGENTIC_ITERATION_TIMEOUT_MS | No | Per-iteration wall-clock cap for ask_agentic |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/qmediat/gemini-code-context-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server