菜单
Workflow guide for GoodMem MCP server tools. Use when an agent needs to understand what GoodMem MCP tools are available and how to use them. Parameter signatures are provided by the MCP protocol itself — do not hardcode them here.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when the user wants to write Python code that interacts with GoodMem — creating embedders, spaces, memories, retrieval, managing API keys, etc. Provides the complete SDK reference for the goodmem Python package.
Overview of all available GoodMem skills and what a user needs to get started. Invoke when a user asks what GoodMem skills are available, how to get started, or what they need to set up.
Use when the user wants to write Java code that interacts with GoodMem - creating embedders, spaces, memories, retrieval, pagination, streaming, or async workflows with the goodmem-java SDK.
| name | goodmem:mcp |
| description | Workflow guide for GoodMem MCP server tools. Use when an agent needs to understand what GoodMem MCP tools are available and how to use them. Parameter signatures are provided by the MCP protocol itself — do not hardcode them here. |
| allowed-tools | Read |
The GoodMem MCP server exposes tools across multiple API namespaces plus local utilities. Most tools map to a GoodMem REST API endpoint; the utilities (goodmem_configure, goodmem_lookup_model, goodmem_client_info) run locally without contacting the server. Use tools/list to discover exact parameter schemas — this document covers workflow and patterns only.
Setup: The MCP server needs GOODMEM_BASE_URL and GOODMEM_API_KEY. These can be set as environment variables before launch, or configured from chat via goodmem_configure.
TLS: If the server uses self-signed or private CA certificates, set NODE_EXTRA_CA_CERTS=/path/to/rootCA.pem or NODE_TLS_REJECT_UNAUTHORIZED=0 (local dev only) as an environment variable before launch.
goodmem_configure if credentials weren't set via env vars.goodmem_lookup_model to check the model registry before creating — it auto-infers provider, endpoint, and dimensionality for known models.goodmem_memories_create (single) or goodmem_memories_batch_create (bulk). Supports text, base64-encoded files, or URL references.goodmem_memories_get until processingStatus is COMPLETED.goodmem_memories_retrieve performs semantic search. Returns NDJSON with ranked results.goodmem_embedders_*)Register and manage embedding models. The four SaaS provider types (OpenAI, Cohere, Voyage, Jina) require credentials. OpenAI-compatible endpoints (Anthropic, Google, Mistral) also require credentials when used under the OPENAI provider type. Omitting credentials for a known SaaS endpoint throws an error before the request is sent.
CRUD: create, list, get, update, delete.
goodmem_llms_*)Register and manage LLM configurations. Same credential pattern as embedders.
CRUD: create, list, get, update, delete.
goodmem_rerankers_*)Register and manage reranker models for result re-ranking.
CRUD: create, list, get, update, delete.
goodmem_spaces_*)Memory spaces — containers that bind an embedder and chunking config.
CRUD: create, list, get, update, delete.
goodmem_memories_*)Store, retrieve, and manage memories within spaces.
create / batch_create — ingest content (text, base64, or URL reference)retrieve — semantic search across one or more spaces (returns NDJSON)get / batch_get — fetch by IDlist — list memories in a spacedelete / batch_delete — remove memoriespages — list memory page images with optional filters and paginationNot available via MCP (binary response): content, pages_image.
goodmem_ocr_*)document — extract text from a document using OCRgoodmem_ping_*)Connectivity probes for embedders, LLMs, rerankers, and other GoodMem endpoints.
once — run one probe and return a PingResultstream — run streaming probes and return NDJSON ping eventsgoodmem_users_*)me — get the current authenticated userget — get a user by ID or emailgoodmem_apikeys_*)Manage API keys for authentication.
CRUD: create, list, update, delete.
goodmem_system_*)info — server version and configurationinit — first-time server initializationgoodmem_admin_*)drain — request the server to enter drain modebackground_jobs_purge — purge completed background jobslicense_reload — reload the server licensegoodmem_configure — set base URL and API key from chatgoodmem_lookup_model — look up model registry entries before creating embedders/LLMs/rerankersgoodmem_client_info — return MCP client version and the goodmem server commit it was built against