predictalot
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
predictalot
One HTTP service, two model families, zero ceremony.
Foundation time-series — 5 zero-shot forecasters (chronos-2, timesfm-2.5, moirai-2, toto-1, sundial-base-128m). Hand them a context window, get quantile or sample-path forecasts. No training step. Six modality-specific endpoints under
/v1/timeseries/<type>/.Model lifecycle —
POST /v1/models/unloadreleases all resident foundation-model weights and runtime caches. A forecast body with"unload": trueschedules its model for teardown after concurrent forecasts using that model finish.Tabular ML — 9 supervised learners (lightgbm, xgboost, hist-gbt, random-forest, logistic, mlp, svm-rbf, knn, naive-bayes) + 3 meta-learners (calibrated, stacking, diversified). Train on YOUR engineered features, persist server-side by
modelId, forecast on the latest snapshot. Under/v1/tabular/.MCP — streamable-HTTP tools at
/mcp. One named tool per (FM type, model) cell plus per-type ensemble + listing. Tabular endpoints are HTTP-only for now.
Quick start
docker run -d --name predictalot \
-v $HOME/predictalot-models:/models \
-e PREDICTALOT_AUTH_TOKENS=changeme \
-p 8080:8080 \
psyb0t/predictalot:latest
# Zero-shot FM forecast
curl -s http://localhost:8080/v1/timeseries/univariate/forecast \
-H "Authorization: Bearer changeme" -H "Content-Type: application/json" \
-d '{"model":"chronos-2","context":[[10,11,12,13,14,15,16,17,18,19,20]],"config":{"horizon":5}}' | jq
# Train + persist a tabular model on your own features
curl -s http://localhost:8080/v1/tabular/train \
-H "Authorization: Bearer changeme" -H "Content-Type: application/json" \
-d '{"modelId":"my-model","backend":"lightgbm","target":[[100,101,99,...]],
"features":[{"rsi":[55,58,...],"macd":[0.3,0.4,...]}],
"config":{"mode":"direction","horizon":3,"nEstimators":400}}' | jq
# Then forecast on the latest snapshot
curl -s http://localhost:8080/v1/tabular/forecast \
-H "Authorization: Bearer changeme" -H "Content-Type: application/json" \
-d '{"modelId":"my-model","features":[{"rsi":[58],"macd":[0.4]}]}' | jq
# Release all resident foundation-model memory when it is no longer needed
curl -s -X POST http://localhost:8080/v1/models/unload \
-H "Authorization: Bearer changeme" | jqRelated MCP server: OpenAI-Compatible MCP Gateway
Documentation
Doc | What it covers |
Foundation time-series API. All 5 models (capabilities + per-model quirks + what each is recommended for), all 6 forecast types, per-type ensemble with | |
Tabular ML API. All 9 backends (what each is recommended for), 3 modes (direction / value / quantile), tier-1/2/3 config knobs, the 3 meta-learners (calibrated / stacking / diversified), storage layout. | |
MCP streamable-HTTP server: tool naming, args, current scope (FM only). | |
Every | |
Multi-venv sidecar pattern for sundial, CPU vs CUDA images, multi-stage build. | |
Benchmark sMAPE + latency on academic + real-world datasets. Honest takeaways including which models lose. | |
Error contract: 400 / 401 / 404 / 413 / 422 / 503 shapes. |
CHANGELOG.md tracks per-version changes.
Agent integrations
The skill works in any agent that reads .agents/skills/ (such as peen), and
installs natively in the clients below.
Claude Code
claude plugin marketplace add psyb0t/agents
claude plugin install predictalot@psyb0tClaude Code prompts for the predictalot URL and, if auth is enabled, the token — the token is stored in your OS keychain.
Codex
codex plugin marketplace add psyb0t/agents
codex plugin add predictalot@psyb0tInstalled via the marketplace, the skill invokes as $predictalot:predictalot. Codex also picks
the skill up automatically, with no install, in any repo containing .agents/skills/ — there it
invokes as plain $predictalot.
OpenClaw
The skill is published to ClawHub on every release:
openclaw skills install @psyb0t/predictalotFor MCP clients that speak local stdio, the @psyb0t/predictalot
plugin bridges to predictalot's /mcp endpoint:
openclaw plugins install clawhub:@psyb0t/predictalotThen set PREDICTALOT_URL (and PREDICTALOT_AUTH_TOKENS if the server requires one).
License
Code: WTFPL (see LICENSE). The MCP plugin under .agents/plugins/predictalot/ is MIT (its own LICENSE).
Foundation models retain their upstream licenses — chronos-2 / timesfm-2.5 / toto-1 / sundial-base-128m: Apache 2.0; moirai-2: CC-BY-NC-4.0 (non-commercial). Tabular backends use their upstream licenses — lightgbm / xgboost / scikit-learn: permissive. Review each before commercial use.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for progressive tool usage at any scale (see https://klavis.ai)
MCP server for the Seline Analytics API
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA standalone MCP server that exposes API endpoints as tools for AI assistants, using SSE transport.-
- FlicenseNot gradedqualityDmaintenanceLocal MCP server that exposes fixed tools for GPT, Claude, and Gemini while routing to any OpenAI-compatible chat completions backend with independent configuration per target.1-
- AlicenseNot gradedqualityNot gradedmaintenanceLocal MCP server for GPU-backed TimesFM 2.5 forecasting, enabling zero-shot time-series forecasting, covariate forecasting, anomaly detection, and CSV forecasting via MCP tools.2Apache 2.0
- AlicenseNot gradedqualityBmaintenanceAn MCP server wrapping AutoGluon's AutoML capabilities, enabling data loading, model training, prediction, evaluation, and model management.Apache 2.0