メニュー
Manage MCP (Model Context Protocol) servers in an Emergent project — register, inspect, sync tools, and delete servers. Use when the user wants to add, configure, or troubleshoot MCP servers connected to their Emergent project.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | memory-mcp-servers |
| description | Manage MCP (Model Context Protocol) servers in an Emergent project — register, inspect, sync tools, and delete servers. Use when the user wants to add, configure, or troubleshoot MCP servers connected to their Emergent project. |
| metadata | {"author":"emergent","version":"2.0"} |
Manage MCP servers connected to an Emergent project using memory agents mcp-servers.
memory browse — it launches a full interactive TUI that blocks on terminal input and will hang in an automated agent context.memory commands with NO_PROMPT=1 (e.g. NO_PROMPT=1 memory <cmd>). Without it, the CLI may show interactive pickers when no project, agent, MCP server, skill, or agent-definition ID is provided. Do not add this to .env.local — it must only apply to agent-driven invocations.--project <id> on project-scoped commands, or ensure MEMORY_PROJECT is set.memory agents mcp-servers list
memory agents mcp-servers list --output json
memory agents mcp-servers get <server-id>
SSE server:
memory agents mcp-servers create --name "my-server" --type sse --url "http://localhost:8080/sse"
HTTP server:
memory agents mcp-servers create --name "my-server" --type http --url "http://localhost:8080/mcp"
stdio server (spawned process):
memory agents mcp-servers create --name "github" --type stdio --command "npx" --args "-y,@modelcontextprotocol/server-github"
memory agents mcp-servers create --name "github" --type stdio --command "npx" --args "-y,@modelcontextprotocol/server-github" --env "GITHUB_TOKEN=ghp_xxx"
With env vars:
memory agents mcp-servers create --name "my-server" --type http --url "http://..." --env "API_KEY=abc123" --env "ENV=prod"
memory agents mcp-servers inspect <server-id>
Returns: connection status, latency, server info, list of tools/prompts/resources.
memory agents mcp-servers sync <server-id>
memory agents mcp-servers tools <server-id>
memory agents mcp-servers configure <tool-name> <key=value ...>
memory agents mcp-servers delete <server-id>
| Type | When to use | Required flags |
|---|---|---|
sse | Remote server with SSE transport | --url |
http | Remote server with HTTP transport | --url |
stdio | Local process (spawned by Emergent) | --command, optionally --args, --env |
create, then inspect to verify connectivity, then sync to populate toolsinspect to check connection status and see what capabilities it reportssync to refresh the cached tool list in Emergentlist --output json and look up by name--project global flag selects the project; falls back to config defaultlist to find them by name--args for stdio type is comma-separated: "arg1,arg2,arg3"Manage Emergent runtime agents and agent definitions — create, trigger, monitor runs, respond to questions, and manage agent configurations. Use when the user wants to run, inspect, or configure AI agents in an Emergent project.
Apply and export Emergent Blueprints — declarative directories of template packs, agent definitions, and seed data applied with `memory blueprints`. Use when setting up a project from a blueprint, seeding graph data, or exporting an existing project's graph as re-applyable seed files.
Full Memory CLI command reference with all subcommands and flags. Use when you need exact command syntax, flag names, or usage examples for any `memory` CLI command.
Onboard a project into Memory — understand what the project is, choose or create a Memory project, design and install a schema (template pack), then guide on creating objects and relationships. Use when setting up Memory for a new project or codebase for the first time.
Manage LLM provider credentials and browse available models in Emergent. Use when the user wants to configure API keys, set up Vertex AI, check which models are available, or review LLM usage and costs.
Query an Emergent project knowledge base using natural language or direct hybrid search. Use when the user wants to search, explore, or ask questions about content in an Emergent project.