Skip to main content
Glama
tribe-mcp

tribe-mcp

by spxrtiat111

tribe-mcp

Standalone MCP server that exposes TRIBE brand data — neural fingerprints, organic posts, and brands — from a Turso (libsql) database to MCP clients like Claude. Lets you do brand-grounded analysis over real data. No app or dashboard required; it only needs a Turso DB with the expected tables.

Tools

Tool

What it does

list_brands

Discover brand IDs to use with the other tools.

list_fingerprints

List TRIBE fingerprints (filter by brand / label).

get_fingerprint

Pull a full fingerprint with channels + timeline by ID.

compare_fingerprints

Pull two fingerprints side-by-side for A/B analysis.

list_organic_posts

List Instagram + TikTok posts logged for a brand.

get_organic_post

Pull a single organic post with its retention curve.

write_insight

Persist an analysis back to the DB so other tools/UIs can read it.

Related MCP server: mcp-turso-cloud

Setup

Requires Node 18+ and a Turso database (the tables are defined in src/db.ts).

git clone https://github.com/<you>/tribe-mcp.git
cd tribe-mcp
npm install
cp .env.example .env          # fill in TURSO_DATABASE_URL + TURSO_AUTH_TOKEN
npm run build

Smoke-test:

TURSO_DATABASE_URL=... TURSO_AUTH_TOKEN=... npm start
# prints "tribe-mcp ready (stdio)" then waits for MCP messages; Ctrl-C to exit.

Connect to Claude

Claude Code (available in every project):

claude mcp add tribe -s user \
  -e TURSO_DATABASE_URL="libsql://<your-db>.turso.io" \
  -e TURSO_AUTH_TOKEN="<your-token>" \
  -- node /ABSOLUTE/PATH/TO/tribe-mcp/dist/index.js

Claude Desktop — add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "tribe": {
      "command": "node",
      "args": ["/ABSOLUTE/PATH/TO/tribe-mcp/dist/index.js"],
      "env": {
        "TURSO_DATABASE_URL": "libsql://<your-db>.turso.io",
        "TURSO_AUTH_TOKEN": "<your-token>"
      }
    }
  }
}

Restart the client; the tribe tools appear in conversation.

The model (Modal) — modal_app.py

modal_app.py is the inference backend that produces the fingerprints this MCP reads. It runs Meta FAIR's TRIBE v2 brain-encoding pipeline on a Modal GPU:

video URL / upload
  → yt-dlp + ffmpeg
  → V-JEPA2 (video) + Wav2Vec2 (audio) + LLaMA (transcript text)  features per fMRI TR
  → TRIBE v2 brain encoder → Schaefer-400 / 7-network parcel time-series (T × 400)
  → reduce to 9 channels + global stats + nilearn 3D brain + Whisper transcript
  → Fingerprint JSON  (stored in Turso → served by this MCP)

Endpoints (deployed at https://<workspace>--api.modal.run): POST /start → job_id, GET /poll?job_id=… → running|complete|error, GET /health, plus /serve_brain, /serve_video, /predictions.

Deploy

pip install modal && modal token new          # one-time
# optional Bearer auth (recommended for a public endpoint):
modal secret create tribe-api-key TRIBE_API_KEY="$(openssl rand -base64 32)"
modal deploy modal_app.py
curl https://<workspace>--api.modal.run/health   # {"status":"ok","atlas":"schaefer_400_7networks_v1",...}

TRIBE weights

Set TRIBE_CKPT (a path baked into the image or on the mounted Volume) to Meta's trained TRIBE v2 brain-encoder checkpoint. Without it, a deterministic placeholder encoder runs so the whole app is end-to-end testable — its numbers are structurally valid but not real brain predictions.

⚠️ Reconstruction + license. The original tribev2-by-meta/modal_app.py was lost; this file is reconstructed from the dashboard's exact API contract + design doc — the serving contract and feature pipeline are faithful; supply the checkpoint for real predictions. TRIBE v2 is CC BY-NC (research only) — this wrapper is MIT, but the model weights are not; don't ship client-facing deliverables from its outputs without a commercial license from Meta.

License

MIT — see LICENSE. (Applies to this wrapper code, not the TRIBE v2 weights.)

Available Tools

7 tools
compare_fingerprintsA

Pull two neural fingerprints side-by-side. Returns both full payloads — diffing happens in the analysis layer (Cowork-Claude).

Inputs: id_a (required), id_b (required).

get_fingerprintA

Pull a single neural fingerprint by ID with the full channels + timeline data. Heavy — only call when you need the full payload.

Inputs: id (required).

get_organic_postB

Pull a single organic post by ID with retention curve.

Inputs: id (required).

list_brandsA

List all brands in the database. Use to discover brand_id values for the other tools.

Inputs: no named parameters.

list_fingerprintsA

List TRIBE neural fingerprints. Filter by brand_id and/or label. Returns metadata only — call get_fingerprint for the full channel/timeline data.

Inputs: label, limit, brand_id.

list_organic_postsA

List Instagram + TikTok organic posts that the brand has logged. Filter by brand_id and/or platform.

Inputs: limit, brand_id, platform.

write_insightA

Persist an analysis insight back to the database so other tools or UIs can read it. Use after producing a substantive analysis you want to keep. The markdown content is stored as-is.

Inputs: type (required), content (required), brand_id (required), model, +3 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 7 tools

    Disambiguation5/5

    Every tool has a clearly distinct purpose: compare_fingerprints compares two fingerprints, get_fingerprint retrieves full fingerprint data, get_organic_post retrieves a single post, list_brands returns all brands, list_fingerprints lists fingerprint metadata, list_organic_posts lists posts, and write_insight stores analysis. No overlap.

    Naming Consistency4/5

    Most tools follow a verb_noun pattern (list_brands, list_fingerprints, list_organic_posts, write_insight). However, there is minor inconsistency: compare_fingerprints uses plural, while get_fingerprint uses singular; get_organic_post is singular, but list_organic_posts is plural. Overall consistent but not perfect.

    Tool Count5/5

    7 tools is well-suited for the domain of brand fingerprint analysis and organic post management. Each tool covers a necessary operation without bloat, and the count is within the ideal 3-15 range.

    Completeness4/5

    The tool set covers listing, retrieval, and comparison of fingerprints, listing and retrieval of posts, listing brands, and writing insights. Missing update/delete operations for most entities, but the stated purpose (analysis and insight persistence) is reasonably covered. Minor gaps exist.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      C
      maintenance
      🗂️ A Model Context Protocol (MCP) server that provides integration with Turso databases for LLMs. This server implements a two-level authentication system to handle both organization-level and database-level operations, making it easy to manage and query Turso databases directly from LLMs.
      9
      18
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that integrates Turso databases with LLMs, supporting organization and database-level operations with two-level authentication.
      MIT