SPM - Structured Project Memory

Name: SPM - Structured Project Memory
Author: getspm

@getspm

SPM - Structured Project Memory について

Structured project memory for AI agents, delivered through a project-scoped remote MCP connector.

#mcp #agents #project-memory #agent-memory #context-packs #temporal-memory #context-graph #provenance #verification #access-control #agent-governance #developer-tools

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

公開者

getspm

投稿者

Marcos Oliva

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "spm": {
      "url": "https://getspm.com/v1/mcp",
      "headers": {
        "Authorization": "Bearer <SPM_PROJECT_TOKEN>"
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is SPM - Structured Project Memory?

SPM - Structured Project Memory turns project knowledge into scoped, temporal, verifiable and injectable context for AI agents. It provides an authenticated remote MCP endpoint for agents to query temporal memory, request context packs, verify provenance, and report post-action evidence.

How to use SPM - Structured Project Memory?

Use the remote MCP endpoint at https://getspm.com/v1/mcp. Authentication is required via a project-scoped SPM token passed as a Bearer token. The connector is available in the public repository; no explicit installation steps are needed beyond configuring your MCP client to point to this endpoint.

Key features of SPM - Structured Project Memory

Query temporal project memory
Request scoped context packs
Verify provenance and hashes
Navigate context graphs
Run preflight checks before actions
Report post-action evidence back to memory

Use cases of SPM - Structured Project Memory

An AI agent queries past decisions and context before proposing a change.
A developer requests a scoped context pack for a specific module.
An agent verifies the provenance of a piece of project knowledge.
A system runs a preflight check to avoid destructive actions.
Post-action evidence is automatically logged to project memory.

FAQ from SPM - Structured Project Memory

How do I authenticate with SPM - Structured Project Memory?

Use a project-scoped SPM token as a Bearer token in the HTTP Authorization header when connecting to the MCP endpoint.

What protocol does SPM - Structured Project Memory use?

It uses the Model Context Protocol (MCP) via a remote endpoint at https://getspm.com/v1/mcp.

What operations are not supported by the connector?

The connector does not expose billing, checkout, invoice payments, customer portal creation, destructive tenant administration, or raw secrets.

Where can I find the agent integration guide and the connector source?

The agent integration guide is at https://getspm.com/agents, and the public connector repository is at https://github.com/getspm/spm-agent-connectors.

「AI とエージェント」の他のコンテンツ

Gemini MCP Server

aliargun

MCP server implementation for Google's Gemini API

259

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768

1Panel

1Panel-dev

🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.

36.1K