Engram MCP server
Commit Nov 13, 2026Stores every AI conversation verbatim and lets an AI client search past sessions by meaning across MCP clients.
Also known as get-engram/engram
- Stars
- 22
- Tools
- 8
- Downloads, 30 days
- —
- Latest version
- 0.1.1
- Last commit
- Nov 13, 2026
- License
- —
What is Engram MCP?
Engram stores every AI conversation verbatim and lets an AI client search past sessions by meaning across MCP clients. It exposes 8 tools, such as create_conversation, append_messages, search.
Summary generated from the project's README
About Engram MCP server
Providing long-term memory for AI agents across different platforms is what Engram achieves by storing every conversation verbatim. Developers using Claude Desktop, Claude Code, Cursor, Windsurf, or Zed can connect their clients to this remote server to ensure their agents remember past sessions through semantic search. Instead of relying on summaries, it keeps uncompressed transcripts that are searchable by meaning using bge-base-en-v1.5 embeddings.
Setup is handled via an OAuth flow that requires no manual API key copying or configuration file editing. When using Claude Code, you can add the plugin directly via the marketplace. For other clients, you can connect to the remote HTTP server or use mcp-remote to bridge stdio-only clients. The system supports various tiers, starting with a free plan that holds 10,000 messages, while paid plans offer up to 1,000,000 messages or unlimited capacity for enterprise users. It provides eight core tools including search, append_messages, and create_conversation to manage the memory infrastructure.
What you can do with it
- 1Retrieve past context by meaningAsk your AI agent to find information from a previous chat session without needing to remember the exact keywords used.
- 2Maintain continuity across different IDEsEnsure your AI assistant retains knowledge of your project history when switching between Cursor, Windsurf, or Zed.
- 3Automate memory management in Claude CodeLet the AI decide which parts of a conversation are important enough to save for future reference automatically.
- 4Manage organizational AI knowledgeOrganize and isolate conversation data for different teams or companies using specific seats and API keys.
Written from the project's README. Every use case is checked against a quote from it.
How to install Engram MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Engram MCP in Claude Code
$ claude mcp add --transport http engram https://mcp.getengram.app/mcpInstall Engram MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"engram": {
"url": "https://mcp.getengram.app/mcp"
}
}
}Install Engram MCP in VS Code
.vscode/mcp.json
{
"servers": {
"engram": {
"type": "http",
"url": "https://mcp.getengram.app/mcp"
}
}
}Install Engram MCP in VS Code CLI
$ code --add-mcp '{"name":"engram","type":"http","url":"https://mcp.getengram.app/mcp"}'Install Engram MCP in Codex
$ codex mcp add engram --url https://mcp.getengram.app/mcpInstall Engram MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.engram] url = "https://mcp.getengram.app/mcp"
Install Engram MCP in Gemini CLI
$ gemini mcp add -s user --transport http engram https://mcp.getengram.app/mcpInstall Engram MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"engram": {
"url": "https://mcp.getengram.app/mcp",
"type": "http"
}
}
}Engram MCP tools 8
Detected from the READMEcreate_conversationappend_messagessearchget_conversationlist_conversationsdelete_conversationmemory_statuswhoami
Automated checks
Ran Nov 13, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableget-engram/engram is public and reachablegithub.com/get-engram/engram ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-11-13github.com/get-engram/engram ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model8 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubEngram
Memory infrastructure for AI agents. Store every conversation verbatim. Search by meaning.
Engram is an MCP-native memory server that stores complete, uncompressed conversation transcripts and makes them searchable via semantic search. Connect any MCP-compatible client — Claude Desktop, Claude Code, Cursor, Windsurf, Zed — and your agent remembers everything across sessions.
Quick start
Claude Code
/plugin marketplace add get-engram/engram
/plugin install engram@engram
Restart Claude Code and approve access in the browser. There is no API key to copy and no config file to edit — the server implements the MCP authorization flow (RFC 9728 / 8414 / 7591, PKCE), so the client discovers it, registers itself, and signs you in. A free account is created as part of signing in.
The plugin also ships a skill that tells Claude when to search memory and what is worth saving, so context accumulates without being asked.
Any other MCP client
Point it at the remote server and let OAuth handle access:
{
"mcpServers": {
"engram": {
"type": "http",
"url": "https://mcp.getengram.app/mcp"
}
}
}
For a client that only speaks stdio, bridge to the remote server with mcp-remote — it drives the same browser OAuth flow, so there is still no key to copy:
{
"mcpServers": {
"engram": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.getengram.app/mcp"]
}
}
}
(An older version of this README suggested npx @getengram/cli mcp; the CLI
has no such command and that configuration never worked.)
How it works
- Verbatim storage — every message stored exactly as sent, no summarization or compression
- Semantic search — find relevant context by meaning using bge-base-en-v1.5 embeddings
- MCP-native — speaks the Model Context Protocol natively, works with any compatible client
- Multi-tenant — per-organization isolation, team seats, and API key management
Architecture
Runs entirely on Cloudflare's developer platform:
- Workers — Hono.js API and MCP server
- D1 — SQLite at the edge for messages and metadata
- Vectorize — semantic search index
- Workers AI — embedding generation
Read the full architecture deep-dive.
MCP tools
Engram exposes 8 core tools via MCP:
| Tool | Description |
|---|---|
create_conversation |
Start a new conversation with optional title, tags, metadata |
append_messages |
Add messages to an existing conversation |
search |
Semantic search across all conversations |
get_conversation |
Retrieve a conversation with its messages |
list_conversations |
List conversations with filtering and pagination |
delete_conversation |
Remove a conversation and its data |
memory_status |
Show how much of the plan's storage is used |
whoami |
Show which Engram account the connection is using |
Connections that use an API key also get the secrets vault tools (resolve_vault, vault_set, vault_get, vault_list, vault_delete) and manage_subscription. See the API reference for full parameters and examples.
Packages
| Package | Description |
|---|---|
apps/mcp-server |
Cloudflare Worker — MCP server and REST API |
apps/cli |
CLI and MCP bridge (@getengram/cli) |
packages/sdk |
TypeScript SDK (@getengram/sdk) |
packages/db |
Database queries and migrations |
packages/shared |
Shared constants, types, and utilities |
Integration guides
Pricing
Memory is permanent. The limits below are how many messages a plan can hold, not a monthly quota: nothing expires, and deleting conversations frees space.
| Plan | Price | Memory |
|---|---|---|
| Free | $0 | 10,000 messages |
| Pro | $9/mo | 1,000,000 messages |
| Team | $9/seat/mo, minimum 2 seats | 1,000,000 messages per seat, pooled |
| Education | $3/mo per student, $3/seat for academic teams | Pro or Team features with a verified university email |
| Enterprise | Custom | Unlimited |
Links
- Website: getengram.app
- Documentation: getengram.app/docs
- Blog: getengram.app/blog
- npm: @getengram/cli
License
Business Source License 1.1 — see LICENSE for details.
Engram MCP questions
How do I add Engram MCP to Claude Code?
Run claude mcp add --transport http engram https://mcp.getengram.app/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Engram MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Engram MCP provide?
It exposes 8 tools, including create_conversation, append_messages, search, get_conversation, list_conversations.
How do I connect Engram to Claude Code?
Add the Engram plugin from its marketplace and install it, then restart Claude Code and approve access in the browser. No API key or config file is needed.
Does Engram need an API key?
No, the server implements the MCP authorization flow with PKCE, so the client registers itself and signs you in through the browser. A free account is created during sign-in.
How does Engram search stored conversations?
It performs semantic search across all conversations using bge-base-en-v1.5 embeddings, so you find context by meaning rather than exact keywords.
Are conversations compressed or summarized when stored?
No, every message is stored exactly as sent with no summarization or compression, and memory is permanent within plan message limits.
Which tools does Engram expose over MCP?
It exposes 8 core tools including create_conversation, append_messages, search, get_conversation, list_conversations, delete_conversation, memory_status and whoami. API-key connections also get secrets vault tools.