SPM - Structured Project Memory
@getspm
About SPM - Structured Project Memory
Structured project memory for AI agents, delivered through a project-scoped remote MCP connector.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"spm": {
"url": "https://getspm.com/v1/mcp",
"headers": {
"Authorization": "Bearer <SPM_PROJECT_TOKEN>"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
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.
Frequently asked questions
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`.
Basic information
More AI & Agents MCP servers
21st.dev Magic AI Agent
21st-devIt's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
Unreal Engine Generative AI Support Plugin
prajwalshettydevUnreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agenti
MCP Client for Ollama (ollmcp)
joniglHarness 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
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.
欢迎来到 智言平台
Shy2593666979AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。
Comments