gemini-web-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| XDG_CONFIG_HOME | No | Base directory for config files (sessions.json and cookies). | ~/.config |
| GEMINI_COOKIE_PATH | No | Directory where gemini-webapi stores cookie cache. | ~/.config/gemini-web-mcp/cookies |
| GEMINI__SECURE_1PSID | No | Google session cookie __Secure-1PSID, used for authentication when browser cookie extraction is not possible. | |
| GEMINI__SECURE_1PSIDTS | No | Google session cookie __Secure-1PSIDTS, must be used together with GEMINI__SECURE_1PSID. | |
| GEMINI_WEB_MCP_TEMPORARY | No | Set to '0' to have MCP conversations appear in Gemini Web history; default '1' keeps them temporary. | 1 |
| GEMINI_WEB_MCP_DEFAULT_MODEL | No | Default model to use when `gemini_chat_new` omits `model`. | Pro |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| gemini_chat_newB | 新規 conversation を作って prompt を投げ、応答を返す。 |
| gemini_chat_continueA | 既存 conversation に prompt を投げ、応答を返す。 モデルは会話開始時のものを引き継ぐ。Gemini は会話途中のモデル変更を
|
| gemini_models_listA | このアカウントで実際に使えるモデルの一覧。
|
| gemini_chat_listB | 保存中の conversation 一覧。 |
| gemini_chat_historyA | 指定 session の会話履歴を全件返す。 |
| gemini_chat_deleteB | 指定 session を local から削除する。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: starting a new conversation, continuing an existing one, listing models, listing conversations, viewing history, and deleting. The overlap between new and continue is resolved by explicit descriptions of creating vs. continuing.
All tools share the gemini_ prefix and mostly follow a resource_verb pattern (chat_new, chat_continue, chat_list, chat_delete, models_list). The exception is gemini_chat_history, where 'history' is a noun rather than a verb, creating a minor inconsistency.
With 6 tools, the server is well-scoped for chat conversation management. Each tool serves a distinct function in the lifecycle (create, continue, list, read history, delete) plus model discovery, without unnecessary bloat.
The tool set covers the complete workflow: create a conversation, continue it, list all conversations, retrieve full history, and delete. Model listing supports selecting the right model upfront. No obvious gaps remain for the stated purpose of interacting with Gemini conversations.