Skip to main content
Glama

flyconn-mcp

An MCP server that lets Claude, Cursor or any MCP client query public Drosophila connectomes and run in-silico experiments on them through flyconn. It runs locally. Every answer carries flyconn's controls, uncertainty and provenance.

Status: pre-alpha (M0 scaffold). Only list_datasets exists so far; see PLAN.md.

Install (from source, for now)

git clone https://github.com/moiz-lakkadkutta/flyconn-mcp && cd flyconn-mcp
uv sync
claude mcp add flyconn -- uv --directory "$PWD" run flyconn-mcp

Once released on PyPI: claude mcp add flyconn -- uvx flyconn-mcp.

Data lives in flyconn's cache ($FLYCONN_CACHE, default ~/.cache/flyconn). Pull a dataset with flyconn data pull malecns@1.0 --level weights (about 1.1 GB).

Related MCP server: neurograph

Tools

Tool

Does

list_datasets

Registered datasets with licence, citation, download size per level, and the locally cached level

Honesty

Wiring is measured; neurotransmitter signs are predicted; simulation outputs are model predictions. Experiments run with rewire / sign-shuffle controls on by default.

Development

scripts/check.sh runs ruff, format check, pyright (strict) and the offline tests.

Licence: Apache-2.0.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      A
      quality
      C
      maintenance
      An MCP server that gives Claude access to NCBI Datasets v2 — search genome assembly metadata, retrieve taxonomy records, and download data packages without leaving your conversation.
      10
      -
    • F
      license
      A
      quality
      B
      maintenance
      Exposes NeuroGraph's scientific API to AI models as MCP tools, enabling them to query, analyze, and visualize brain networks — regions, tracts, connectivity, literature, and cross-species homologies — drawn from a portable SSD-based neuroimaging data library. Lets models read real atlas data, load datasets, compute graph metrics, and produce visualization scene descriptors without acting as the scientific engine itself.
      12
      3
      -
    • F
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables AI agents to analyze and link citations across multiple research sources, building cross-citation graphs and resolving consensus from conflicting findings. It exposes this capability as a deterministic, zero-dependency MCP server that plugs into Claude Desktop, Cursor, and other MCP-compliant clients.
      -
    • A
      license
      B
      quality
      B
      maintenance
      Exposes a local-first personal brain to any MCP client, letting agents perform identity-grounded memory recall, simulate stances and value conflicts, propose or approve audited guardrail changes, take snapshots with drift comparison, and run a neural validation harness. Everything runs against a local SQLite neuron/synapse memory graph with consent-gated, append-only auditing.
      6
      CC BY-4.0