Cortex vs Engram
A side-by-side look at the Cortex and Engram MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
E
EngramKnowledge & Memory · Local subprocess (stdio)Persistent memory for AI agents — verbatim conversations, searchable by meaning.57GoodAuth: not declaredVerdict: choose Cortex for knowledge & memory work over a hosted endpoint; choose Engram for knowledge & memory as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Cortex when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a remote HTTP/SSE transport.
- You have the keys it needs:
CORTEX_ACCESS_TOKEN, CORTEX_MCP_URL.
EChoose Engram when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- You want tools like
create_conversation, append_messages, search.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | E Engram | |
|---|---|---|
| Category | Knowledge & Memory | Knowledge & Memory |
| Quality signal | 40/100 · Fair | 57/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | CORTEX_ACCESS_TOKENCORTEX_MCP_URL | None listed |
| Verified owner | Community listing |
Tools & capabilities
Cortex tools
No tool names declared yet. Check the project README from the listing page.
Engram tools 6
create_conversationStart a new conversation with optional title, tags, metadataappend_messagesAdd messages to an existing conversationsearchSemantic search across all conversationsget_conversationRetrieve a conversation with its messageslist_conversationsList conversations with filtering and paginationdelete_conversationRemove a conversation and its data
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Cortex
{
"mcpServers": {
"cortex-5": {
"url": "https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp"
}
}
}
Engram
{
"mcpServers": {
"engram-2": {
"command": "npx",
"args": [
"-y",
"@getengram/cli"
]
}
}
}
Frequently asked questions
Cortex is categorized under Knowledge & Memory and uses a remote HTTP/SSE transport. Engram belongs to Knowledge & Memory and uses a local stdio subprocess. Pick Cortex for knowledge & memory work and Engram for knowledge & memory.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Cortex has no declared pricing — check the project's own site. Engram has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add cortex-5 and engram-2 as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Cortex has a quality signal of 40/100 (Fair) with 1 views, 0 installs and 1 GitHub stars. Engram has 57/100 (Good) with 1 views, 0 installs and 15 GitHub stars.