
Suma Memory
A persistent knowledge graph for AI coding sessions that solves the cold start problem. Exposes six MCP tools: suma_ingest writes architectural decisions and bug fixes to a weighted graph, suma_search retrieves context by natural language query, suma_talk combines search and learning in one call, and suma_correct supersedes wrong information without deletion. Runs as a hosted service on Cloud Run, so no local server setup. The K-WIL gravity algorithm ranks facts by recency, density, semantic similarity, and emotional weight rather than flat chunking. Reach for this when you're tired of re-explaining your auth flow or database schema every time you open a new Claude chat, or when multiple agents need to share context across sessions without explicit handoffs.
- tools
- 6
- auth
- Secret needed
- transport
- STDIO, HTTP
- env var
- 1
- last updated
- Apr 12, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
suma_pingHealth check — verify connection and API key
Health check — verify connection and API key
No parameter schema in public metadata yet.
suma_ingestAdd knowledge to the graph (architecture decisions, bug fixes, rules)
Add knowledge to the graph (architecture decisions, bug fixes, rules)
No parameter schema in public metadata yet.
suma_searchRetrieve relevant context by natural language query
Retrieve relevant context by natural language query
No parameter schema in public metadata yet.
suma_talkSearch + learn in one call — retrieves context and updates graph
Search + learn in one call — retrieves context and updates graph
No parameter schema in public metadata yet.
suma_correctFix wrong information — supersedes original, queues replacement
Fix wrong information — supersedes original, queues replacement
No parameter schema in public metadata yet.
suma_cleanRemove noise nodes that pollute search results
Remove noise nodes that pollute search results
No parameter schema in public metadata yet.
Sponsors
Configuration
SUMA_API_KEY*secretYour SUMA Pro API key — get one free at sumapro.quadframe.work
Readme
SUMA Memory MCP
Stop re-explaining your project to Claude every time you start a new chat.
Your repos now have permanent memory. SUMA gives any MCP-compatible AI client (Claude Code, Cursor, Devin) a persistent knowledge graph that remembers architectural decisions, bug root causes, and project rules — across sessions, across machines, across your entire team.
Install (30 seconds)
Get an API key at sumapro.quadframe.work — free tier available.
Add to your .mcp.json:
{
"mcpServers": {
"suma-memory": {
"url": "https://sumapro.quadframe.work/mcp",
"headers": {
"Authorization": "Bearer sk_live_your_key_here"
}
}
}
}
That's it. No local server. No Docker. No npm install. SUMA runs on Cloud Run — stateless, auto-scaled, always available.
Onboard Your Project (2 minutes)
After installing, run this once per repo to seed your permanent context:
Details
- Repository
- github.com/sumanaddanki/suma-mcp
- Category
- AI & LLM Tools
- Package
suma-mcp-proxy- Transport
- STDIO, HTTP
- Auth
- Required
- Registry
- MCP registry, active