Openexp MCP Server

<strong>How did this happen? — a hippocampus for AI agents.</strong>

Local serverstdioPython

What is the Openexp MCP server?

Openexp MCP server exists for a simple reason — assistants are far more useful when they can act on Openexp directly instead of describing what you should do. How did this happen? — a hippocampus for AI agents..

What the assistant can call

Once Openexp is connected, these are the calls the assistant has available:

  • search_memory — Hybrid search: semantic similarity + BM25 + recency
  • add_memory — Store a memory. Supports client_id for entity tagging
  • log_prediction — Log a pack-grounded prediction. Required when an installed experience pack cites a specific relative_day as the basis for an action recommendation
  • log_outcome — Resolve a prediction with the observed signal — interpretation-free record
  • memory_stats — Collection stats: point counts by source/type, session count

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Configuration and credentials

You will need 2 environment variables: QDRANT_HOST, ANTHROPIC_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Choosing this one

This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Openexp's toolset — search_memory, add_memory, log_prediction and 2 more — is a fair guide to whether it matches your workflow. It is maintained by anthroos; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Openexp's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Before you rely on it

  • 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.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the openexp mcp server does with a few real requests.

Available tools

ToolWhat it does
search_memoryHybrid search: semantic similarity + BM25 + recency
add_memoryStore a memory. Supports client_id for entity tagging
log_predictionLog a pack-grounded prediction. Required when an installed experience pack cites a specific relative_day as the basis for an action recommendation.
log_outcomeResolve a prediction with the observed signal — interpretation-free record.
memory_statsCollection stats: point counts by source/type, session count

Configuration

VariableDescriptionRequired
QDRANT_HOSTEndpoint or connection string the server talks to.Optional
ANTHROPIC_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Openexp to search memory.
  • Use Openexp to add memory.
  • Use Openexp to log prediction.

Frequently asked questions

It connects Openexp to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (search_memory, add_memory, log_prediction, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Openexp directly.