# Engramic

> Engramic is a freemium MCP server for knowledge and memory. Team decisions, goals and constraints from Engramic for any MCP-capable agent. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, Web
- **Website:** https://www.engramic.ai/docs/mcp/
- **MCP Registry name:** ai.engramic/engramic
- **Categories:** knowledge and memory
- **Listing updated:** 2026-11-15

## About

Engramic keeps a knowledge graph that a team writes itself: topics such as concepts, goals, gaps, constraints and resources, plus a timeline of decisions, actions, events and discoveries. This connector lets agents in Claude, Cursor and similar clients query that graph and add to it, so a session begins from what the team has already settled.

Sign-in uses OAuth 2.1 with PKCE and dynamic client registration; each connection is bound to one workspace and acts as the user or as a named agent they manage. Roles apply on every request: owners and contributors can write, viewers get the read-only tools except Open Share. Every write shows on the workspace timeline with its author, and no tool deletes anything.

One tool, ask_alia, sends relevant workspace content and the question to Anthropic's API; the documentation says no other tool calls an AI model. Workspaces run in separate databases hosted on AWS in London.

## Features

- **Search and browse:** Find topics and timeline events by text, or walk the topic graph one level at a time.
- **Timeline queries:** Filter decisions, actions, events and discoveries by type, actor, topic or date.
- **Draft then publish:** Stage a record, see the topic's context, then publish it to the timeline.
- **Create and update topics:** Add or change concepts, goals, gaps, constraints and resources.
- **Role-based access:** A connection uses the signed-in user's own workspace role.
- **Admin controls:** Owners manage members; users can revoke connected apps at any time.

## Good for

- Ask what was decided about a plan's pricing and why
- Record a launch date change against a project topic
- Log an open question as a gap
- Check current constraints before starting a redesign

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http engramic https://api.engramic.ai/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://api.engramic.ai/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "engramic": {
      "url": "https://api.engramic.ai/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "engramic": {
      "type": "http",
      "url": "https://api.engramic.ai/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "engramic": {
      "serverUrl": "https://api.engramic.ai/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "engramic": {
      "type": "http",
      "url": "https://api.engramic.ai/mcp"
    }
  }
}
```

## Tools

- `engramic_search`: Find topics and timeline events by text.
- `ask_alia`: Ask one question and get one answer synthesised from the workspace.
- `engramic_summary`: The caller's identity and a workspace overview.
- `engramic_topic`: Browse the topic graph one level at a time.
- `engramic_timeline`: Query decisions, actions, events and discoveries.
- `engramic_event`: One timeline event in full.
- `engramic_open_share`: Open a shared topic snapshot by its ID.
- `engramic_record_draft`: Stage a record and get the topic's context first.
- `engramic_record_publish`: Publish a staged record to the timeline.
- `engramic_create_concept`: Create a concept topic.
- `engramic_create_goal`: Create a goal topic.
- `engramic_create_gap`: Create a gap topic.
- `engramic_create_constraint`: Create a constraint topic.
- `engramic_create_resource`: Create a resource topic.
- `engramic_update_concept`: Change a concept topic's fields.
- `engramic_update_goal`: Change a goal topic's fields.
- `engramic_update_gap`: Change a gap topic's fields.
- `engramic_update_constraint`: Change a constraint topic's fields.
- `engramic_update_resource`: Change a resource topic's fields.

## FAQ

### How does sign-in work?

OAuth 2.1 with PKCE; there are no API keys to paste.

### Can an agent delete data?

No tool deletes anything, though the update tools replace a field's previous value.

### Is a paid plan required?

The connector works on every plan, including Free.

### Where is data hosted?

On AWS in London (eu-west-2), with each workspace in its own database.

### Is Engramic free?

Engramic has a free plan, with paid plans for more usage or features.

### How do I add Engramic to Claude Code?

Run this command in your terminal: claude mcp add --transport http engramic https://api.engramic.ai/mcp

### What are the best alternatives to Engramic?

The closest alternatives to Engramic are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

## Alternatives

- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.
- [note1](https://ai-powered.com/mcp/note1): note1 is an MCP server for productivity.
- [MedXpert 图书馆连接器（通用版）](https://ai-powered.com/mcp/medxpert): MedXpert 图书馆连接器（通用版） is an open-source MCP server for knowledge and memory.
- [Context Nest](https://ai-powered.com/mcp/context-nest): Context Nest is a freemium MCP server for knowledge and memory.
- [Tulsa Ecosystem Map](https://ai-powered.com/mcp/tulsa-ecosystem-map): Tulsa Ecosystem Map is a free MCP server for knowledge and memory.

---
Source: https://ai-powered.com/mcp/engramic
