SPM - Structured Project Memory MCP server

SPM Agent Connectors

Public connector package for SPM - Structured Project Memory.

SPM turns project knowledge into durable, shareable, governed and internally smart project memory for AI agents. This repository contains only the public connector surface: the authenticated remote MCP configuration, installable bundles for Codex, Claude Code, Cursor and OpenClaw, browser authorization helpers, lifecycle adapters, examples and security guidance.

The SPM application, backend, billing system, private console, memory engine and infrastructure are not included in this repository.

Hosted MCP Endpoint

Human setup and inspection guide:

https://getspm.com/agents

https://getspm.com/v1/mcp

Official MCP Registry descriptor:

server.json

Registry name:

com.getspm/spm

The endpoint is public for discovery, but authenticated for use. A client needs:

projects the user may access in an organization.

• an SPM account;
• an organization and at least one project;
• a trial or paid plan;
• an SPM token authorized for one project, a selected project set or the

What Agents Can Do

Connector profiles expose the agent-facing SPM surface:

projects;

• use durable project memory across chats, runs and tools;
• resolve the active project without confusing it with other authorized

user explicitly requests it;

• list authorized projects and compose cross-project context only when the

completed work, source-backed context and temporal signals;

• work with smart memory packs that preserve requirements, current decisions,

provenance, when the client supports lifecycle hooks.

• query temporal project memory;
• request scoped context packs;
• verify context pack provenance and hashes;
• query context graphs and boundaries;
• run policy-aware preflight checks;
• report completed actions, tests, evidence and decisions;
• submit agent lifecycle turns to LLM-first memory triage with source

capture independently from the memory that triage promotes for future use;

• choose selective, complete redacted, summaries-only or metadata-only source

conversation bodies to agent tools.

• inspect and verify an append-ordered capture journal without exposing retained

matches, request only the specific authorized evidence still needed, then wait for the user to create, link or skip it in SPM;

• propose a source-grounded project-memory bootstrap when no authorized project

short-lived one-time handoff that carries references rather than memory bodies or credentials;

• continue an authorized project in another agent or device through a

revision and local-state hash; non-Git file or document snapshots; remote version references; or memory-only work;

• compare body-free workspace manifests before a handoff: Git identity,

turns and after completed work when the client supports lifecycle hooks, making stale observations and out-of-band changes visible without uploading local file bodies;

• refresh workspace manifests automatically at session start, before user

request an authorized source handoff when current content is required.

• distinguish metadata-only source observations from material evidence and

Typical Use Cases

changing code: requirements, current decisions, tests, constraints and completed work.

• Coding agents receive the project memory they should actually use before

engineers, clients, partners or support without exposing the whole project.

• Delivery teams turn scattered project knowledge into scoped packs for

expiry, revocation, provenance and audit evidence.

• Partners or external collaborators receive bounded memory with source,

and evidence back to SPM.

• Agent workflows preserve memory after the task by reporting decisions, tests

What Agents Cannot Do

The hosted MCP connector does not expose:

• billing or checkout;
• invoice payment;
• customer portal creation;
• destructive tenant administration;
• raw secrets;
• global operator tools.

Shortened. The full README is on GitHub.