Skip to main content

​
What is MCP?

Model Context Protocol (MCP) lets AI clients like Claude Desktop, Cursor, and Windsurf connect to external tools. Mengram’s MCP server gives these clients persistent memory — semantic, episodic, and procedural.

​
Setup with Claude Desktop

Add to your Claude Desktop config (claude_desktop_config.json): 
{
  "mcpServers": {
    "mengram": {
      "command": "uvx",
      "args": ["mengram-ai"],
      "env": {
        "MENGRAM_API_KEY": "om-your-key"
      }
    }
  }
}

​
Setup with Cursor

Add to Cursor’s MCP settings (.cursor/mcp.json): 
{
  "mcpServers": {
    "mengram": {
      "command": "uvx",
      "args": ["mengram-ai"],
      "env": {
        "MENGRAM_API_KEY": "om-your-key"
      }
    }
  }
}

​
Setup with Windsurf

Add to Windsurf’s MCP settings: 
{
  "mcpServers": {
    "mengram": {
      "command": "uvx",
      "args": ["mengram-ai"],
      "env": {
        "MENGRAM_API_KEY": "om-your-key"
      }
    }
  }
}

​
Available Tools

The cloud MCP server exposes 29 tools:

​
Memory Operations

ToolDescription
rememberSave knowledge from a conversation to memory — pass message pairs and the AI extracts entities, facts, relations, episodes, and procedures.
remember_textSave plain text to memory — the AI extracts entities, facts, and relations automatically.
recallSemantic search through cloud memory. Use specific keywords: person names, project names, technologies.
searchAdvanced structured search — returns entities with relevance scores, facts, and knowledge snippets.
search_allUnified search across ALL memory types — semantic, episodic, and procedural.
timelineSearch memory by time. Use when user asks “what did I do last week”, “when did I…”, etc. Returns facts with timestamps.
list_memoriesList all stored memory entities with their types and fact counts.

​
Entity Management

ToolDescription
get_entityGet details of a specific entity — facts, relations, knowledge.
delete_entityDelete an entity and all its data (facts, relations, knowledge).
fix_entity_typeFix an entity’s type classification (e.g. a technology labeled as “person”). Valid types: person, project, technology, company, concept, unknown.
merge_entitiesMerge two entities into one — combines facts, relations, and knowledge.
archive_factArchive a specific fact on an entity — soft-delete without removing the entity.
dedupFind and automatically merge duplicate entities. Scans all entities and merges near-duplicates.

​
Episodic Memory

ToolDescription
list_episodesList or search episodic memories (events, interactions, experiences).

​
Procedural Memory

ToolDescription
list_proceduresList learned workflows/procedures from memory. Returns procedures with steps, success/fail counts, and version info.
procedure_feedbackRecord success or failure for a procedure. On failure with context, the system automatically evolves the procedure.
procedure_historyShow how a procedure evolved over time — all versions and what changed.

​
Insights & Reflection

ToolDescription
reflectTrigger AI reflection on memories — analyzes facts to find patterns, insights, and connections.
get_reflectionsGet AI-generated reflections (insights and patterns found across memories). Optional scope filter: “entity”, “cross”, “temporal”.
get_insightsAI-generated insights about the user — patterns, connections, reflections from memory analysis.

​
Agents

ToolDescription
run_agentsRun memory agents that analyze, clean, and find patterns. Use “curator”, “connector”, “digest”, or “all”.
vault_statsGet memory vault statistics — total entities, facts, relations, knowledge items, and storage usage.

​
Triggers & Graph

ToolDescription
get_triggersList smart triggers — reminders, contradictions detected, and patterns.
dismiss_triggerDismiss a smart trigger without firing its webhook.
get_graphGet the knowledge graph — all entities and their relationships.
get_feedActivity feed — recent memory changes and events.

​
Context & Rules

ToolDescription
checkpointSave a session checkpoint — summarize key decisions, learnings, and outcomes. Lighter than “remember”: takes a structured summary instead of raw messages.
context_forGet relevant memory context for a specific task. Returns a compact context pack: related entities, procedures, and past events.
generate_rules_fileGenerate a CLAUDE.md, .cursorrules, or .windsurfrules file from memory. Creates structured project rules, conventions, tech stack, workflows.

​
HTTP Transport

For remote/cloud MCP clients, Mengram also supports SSE transport: 
SSE endpoint: https://mengram.io/mcp/sse
Messages:     https://mengram.io/mcp/messages/
The MCP server uses cloud mode by default with MENGRAM_API_KEY. For local mode (your own LLM keys), run mengram server without the --cloud flag.