Mie MCP Server

Stop re-explaining yourself to every AI agent. MIE gives all your agents — Claude, ChatGPT, Cursor, Gemini — a shared, persistent knowledge graph

Local serverstdioPython

What is the Mie MCP server?

Stop re-explaining yourself to every AI agent. MIE gives all your agents — Claude, ChatGPT, Cursor, Gemini — a shared, persistent knowledge graph they can read and write. Decisions, context, facts, and relationships survive across. The mie mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 12 defined tools rather than through you.

Its toolset

Everything the assistant can do here goes through one of these:

  • mie_analyze — Surfaces related context before storing — the agent decides what's worth remembering
  • mie_store — Writes facts, decisions, entities, events, and relationships to the graph
  • mie_bulk_store — Batch store up to 50 nodes with cross-references — ideal for importing knowledge from files or git history
  • mie_get — Retrieve a single memory node by ID with full details
  • mie_query — Semantic search, exact lookup, or graph traversal across all node types
  • mie_list — List and filter nodes with pagination
  • mie_update — Invalidate outdated facts, update statuses — with full history preserved
  • mie_delete — Remove nodes with cascade (embedding + edges) or remove individual relationships
  • mie_conflicts — Detect contradictions in stored knowledge
  • mie_export — Export the full graph as JSON or Datalog
  • mie_repair — Rebuild HNSW indexes and clean orphaned embeddings
  • mie_status — Graph health, node counts, usage metrics

Adding it to your client

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Configuration

  • Go 1.24+ (building from source) - Ollama (optional, for semantic search) — ollama pull nomic-embed-text MIE works without Ollama. You get exact-match search and graph traversal. Add Ollama for semantic search ("find things related to deployment" instead of exact keywords).

When to reach for it

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Mie's toolset — mie_analyze, mie_store, mie_bulk_store and 9 more — is a fair guide to whether it matches your workflow. It is maintained by kraklabs; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Mie.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mie mcp server does with a few real requests.

Available tools

ToolWhat it does
mie_analyzeSurfaces related context before storing — the agent decides what's worth remembering
mie_storeWrites facts, decisions, entities, events, and relationships to the graph
mie_bulk_storeBatch store up to 50 nodes with cross-references — ideal for importing knowledge from files or git history
mie_getRetrieve a single memory node by ID with full details
mie_querySemantic search, exact lookup, or graph traversal across all node types
mie_listList and filter nodes with pagination
mie_updateInvalidate outdated facts, update statuses — with full history preserved
mie_deleteRemove nodes with cascade (embedding + edges) or remove individual relationships
mie_conflictsDetect contradictions in stored knowledge
mie_exportExport the full graph as JSON or Datalog
mie_repairRebuild HNSW indexes and clean orphaned embeddings
mie_statusGraph health, node counts, usage metrics

How to install the Mie MCP server

{
  "mcpServers": {
    "mie": {
      "command": "mie",
      "args": ["--mcp"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Go 1.24+ (building from source) - Ollama (optional, for semantic search) — ollama pull nomic-embed-text MIE works without Ollama. You get exact-match search and graph traversal. Add Ollama for semantic search ("find things related to deployment" instead of exact keywords).

Example prompts to try

  • Use Mie to mie analyze.
  • Use Mie to mie store.
  • Use Mie to mie bulk store.

Frequently asked questions

It connects Mie to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (mie_analyze, mie_store, mie_bulk_store, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Mie directly.