Antigravity GLM MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GLM_MODEL | No | 사용할 모델 (Model to use) | glm-4-plus |
| PYTHONPATH | No | Path to the antigravity_glm_mcp directory | |
| GLM_TIMEOUT | No | 요청 타임아웃 (초) (Request timeout in seconds) | 120 |
| GLM_BASE_URL | No | API 엔드포인트 (API endpoint) | https://open.bigmodel.cn/api/paas/v4 |
| PROJECT_ROOT | Yes | 작업 대상 디렉토리 (Target directory for work) | 현재 디렉토리 (Current directory) |
| ZHIPU_API_KEY | Yes | GLM API 인증 키 (GLM API authentication key) |
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": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| glm_cmdC | GLM-4-plus에 질문을 위임합니다. (지능) |
| glm_bypassC | GLM에 원시 프롬프트를 직접 보냅니다. (Raw Mode) |
| glm_file_readC | 파일 내용을 읽습니다. |
| glm_file_createB | 새 파일을 생성합니다. |
| glm_file_editB | 파일을 수정합니다 (문자열 교체). |
| glm_file_deleteB | 파일을 삭제합니다 (백업 보관). |
| glm_file_rollbackC | 파일을 복원합니다. |
| glm_memory_saveC | 메모리 저장. |
| glm_memory_getD | 메모리 조회. |
| glm_memory_listD | 메모리 목록. |
| glm_memory_deleteD | 메모리 삭제. |
| glm_action_logC | 작업 로그 조회. |
| glm_dir_listC | 디렉토리 목록 조회. |
| glm_code_runB | Python 코드 실행 (샌드박스). |
| glm_web_searchC | 웹 검색 (DuckDuckGo). |
| glm_git_statusB | Git 상태 조회. |
| glm_git_commitD | Git 커밋. |
| glm_http_requestD | HTTP 요청. |
| glm_db_queryD | DB 쿼리 (SQLite). |
| glm_image_analyzeC | 이미지 분석 (Vision). |
| glm_schedule_taskC | 작업 예약 관리. |
| glm_grepC | 파일 내용 검색 (grep). |
| glm_git_logC | Git 커밋 이력 조회. |
| glm_git_diffB | Git 변경 사항 비교. |
| glm_shell_execB | 제한적 쉘 명령 실행 (화이트리스트 기반). |
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 25 tools
Most tools have distinct purposes, but 'glm_cmd' (delegating to GLM) and 'glm_bypass' (raw prompt) could confuse an agent. Also, multiple log-related tools (glm_action_log, glm_git_log) are separate but might be misinterpreted without careful reading.
All tools follow a consistent 'glm_<domain>_<action>' pattern (e.g., glm_file_create, glm_git_commit). This makes the tool set predictable and easy to navigate.
With 25 tools, the server is on the heavy side for a general-purpose assistant. While each tool serves a purpose, the count is borderline and could be streamlined by merging some functions (e.g., memory operations).
The tool surface covers a wide range: file operations, git, memory, code execution, web search, HTTP, image analysis, shell, scheduling, and DB queries. Minor gaps exist (e.g., no file rename or explicit memory update), but overall it's quite comprehensive for an AI assistant.