MCP server
Engraphy
io.github.devon-clarkk/engraphy
Checked 25 Oct 2026, 21:10 UTC · Checked against OSV.dev for malware and vulnerabilities; never run by us
Self-hosted MCP memory server: a typed knowledge graph on Postgres 16 and pgvector.
Runs on your computer
At a glance
- Type
- MCP server
- Publisher
- Not verified
- Status
- Runs on your computer
- Sets up in
- Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code
- Last checked
- 25 Oct 2026, 21:10 UTC
Connect it to your agent
Opens the app, which shows the server and asks you to confirm. It then runs the package on your computer with your permissions. For other apps, copy the setup below.
Claude Code
claude mcp add engraphy --env ENGRAPHY_DATABASE_URL=YOUR_VALUE -- docker run -i --rm -e ENGRAPHY_DATABASE_URL ghcr.io/devon-clarkk/engraphy:0.3.0
Claude Desktop
{"mcpServers":{"engraphy":{"command":"docker","args":["run","-i","--rm","-e","ENGRAPHY_DATABASE_URL","ghcr.io/devon-clarkk/engraphy:0.3.0"],"env":{"ENGRAPHY_DATABASE_URL":"YOUR_VALUE"}}}}
Codex (config.toml)
[mcp_servers.engraphy]
command = "docker"
args = ["run","-i","--rm","-e","ENGRAPHY_DATABASE_URL","ghcr.io/devon-clarkk/engraphy:0.3.0"]
env = { ENGRAPHY_DATABASE_URL = "YOUR_VALUE" }
Gemini CLI
{"mcpServers":{"engraphy":{"command":"docker","args":["run","-i","--rm","-e","ENGRAPHY_DATABASE_URL","ghcr.io/devon-clarkk/engraphy:0.3.0"],"env":{"ENGRAPHY_DATABASE_URL":"YOUR_VALUE"}}}}
Cursor
{"mcpServers":{"engraphy":{"command":"docker","args":["run","-i","--rm","-e","ENGRAPHY_DATABASE_URL","ghcr.io/devon-clarkk/engraphy:0.3.0"],"env":{"ENGRAPHY_DATABASE_URL":"YOUR_VALUE"}}}}
VS Code
{"servers":{"engraphy":{"type":"stdio","command":"docker","args":["run","-i","--rm","-e","ENGRAPHY_DATABASE_URL","ghcr.io/devon-clarkk/engraphy:0.3.0"],"env":{"ENGRAPHY_DATABASE_URL":"YOUR_VALUE"}}}}
Runs on your computer with your permissions: check the package and its source before installing. Replace YOUR_VALUE with your own ENGRAPHY_DATABASE_URL.
Browse
Related MCP servers
- ctxstore — memory that follows you across models
Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model. - StudioMeyer Memory
Bi-temporal AI memory. 56 tools, knowledge graph, semantic search. EU-hosted, free tier. - Echo Memory
Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM. - Memory Vault
Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT. - amu-pgvector
Lineage-gated agent memory tools on Postgres + pgvector, enforced by row-level security. - Tribal
Self-hosted semantic memory over MCP for an engineering team's tacit knowledge. Needs Postgres. - RemembrallMCP
Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector. - MaxGraph
Self-hosted persistent memory for AI agents: knowledge graph and hybrid search.
Badge for your README
[](https://aptlynx.net/servers/io.github.devon-clarkk/engraphy)
Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents