Algenta MCP Server

Algenta SDK

Python and TypeScript client libraries and the official MCP server for [Algenta](https://algenta.ai) — self-hosted building blocks for AI applications.

📖 Full documentation: [GitHub Wiki](https://github.com/thyn-ai/algenta-sdk/wiki)

Docs · Python SDK · TypeScript SDK · MCP server · Integrations · Examples · Contributing

Custom Mojo kernels give Algenta its speed. Your team never writes a line of Mojo — the blocks speak Python and TypeScript. On your infrastructure, not ours. These SDKs are how Python and TypeScript call the engine: typed access to governed data queries, Monte Carlo simulations and recommendations, decision memory with execution receipts that pin the policy and schema snapshots each execution ran under, agent runs with human-in-the-loop approvals, managed connectors, and a full audit trail — enforced by the engine, never by client-side convention.

MCP server

MCP server (`algenta-mcp`) — the official MCP server for Algenta lives in THIS repository at packages/mcp/ (implementation: packages/mcp/algenta_mcp; stdio transport by default, Streamable HTTP optional). Install it with pip install algenta-mcp and run it as the algenta-mcp command; it is also on the official MCP Registry as io.github.thyn-ai/algenta. The framework integrations (LangChain, LlamaIndex, Vercel AI SDK, …) are what live in the companion repository thyn-ai/algenta-integrations — not the MCP server.

Introspection (initialize/tools/list) needs no credentials. Executing tools requires a free community login — device registration at algenta.ai (free): run algenta login, or create a key at https://app.algenta.ai/dashboard/api-keys, then set ALGENTA_API_KEY.

Installation

pip install algenta-sdk       # Python 3.12+

npm install algenta-sdk # TypeScript / JavaScript, Node.js 18+

Quickstart

Both clients read ALGENTA_API_KEY from the environment and default to Algenta's hosted API at https://api.algenta.ai.

Python — note the import name is decision_engine (see Legacy names):

from decision_engine import AlgentaClient

client = AlgentaClient() # reads ALGENTA_API_KEY; defaults to https://api.algenta.ai

datasets = client.list_datasets(search="orders", compact=True) summary = client.get_dataset_summary(datasets.datasets[0].dataset_id) result = client.query_with_metadata( { "dataset_id": summary.dataset_id, "metric": {"hint": "gross_revenue"}, "aggregation": "sum", } ) print(result.data.result)

TypeScript:

import { AlgentaClient } from "algenta-sdk";

const client = new AlgentaClient(); // reads ALGENTA_API_KEY; defaults to https://api.algenta.ai

const datasets = await client.listDatasets({ search: "orders", compact: true }); const summary = await client.getDatasetSummary(datasets.datasets[0].dataset_id); const result = await client.queryWithMetadata({ dataset_id: summary.dataset_id, metric: { hint: "gross_revenue" }, aggregation: "sum", }); console.log(result.data.result);

Self-hosted engine? Point the client at your own deployment — AlgentaClient(base_url="http://localhost:8000") in Python, new AlgentaClient({ baseUrl: "http://localhost:8000" }) in TypeScript — and use the API key provisioned by your operator. The self_hosted and air_gapped deployment profiles fail closed: they never silently fall back to Algenta's cloud. Framework integrations in thyn-ai/algenta-integrations take the opposite default on purpose: they are self-hosted-first, resolve their endpoint from ALGENTA_BASE_URL or an explicit base_url, and never default or fall back to the hosted API.

The full API surface — governed queries, connectors, simulations, jobs, triggers, agent runs, decisions, repository intelligence, and the TypeScript local Runtime facade — is documented in packages/python-sdk/README.md and packages/ts-sdk/README.md, with runnable projects in examples/. The MCP server lives in this repository (see MCP server above); framework integrations (LangChain, LlamaIndex, Vercel AI SDK, and more) live in the companion repository thyn-ai/algenta-integrations.

Errors, retries, and timeouts

Both SDKs raise the same exception taxonomy. Every error carries the HTTP status, the engine's machine-readable error_code, and — in Python — the engine-assigned request_id; validation failures additionally expose per-field details via field_errors (Python) / fieldErrors (TypeScript).

Transient network errors are retried on the same policy as 5xx responses. The Python SDK additionally never retries one rate-limit code, inline_preview_rate_limited.

Legacy names

The SDK was renamed to Algenta partway through its history. For backward compatibility, the legacy names below still work — existing code and deployment configurations do not need to change:

• Python import name — the PyPI package is algenta-sdk, but the importable module remains decision_engine: from decision_engine import AlgentaClient.
• Client aliases — CodnaClient (and AsyncCodnaClient in Python) remain exported as aliases of AlgentaClient in both SDKs.
• Environment variables — DE_API_KEY, DE_BASE_URL, and ALGENTA_API_URL are still accepted alongside the canonical ALGENTA_API_KEY and ALGENTA_BASE_URL.

The published API contract guarantees a 90-day deprecation window (DEPRECATION_WINDOW_DAYS) before any legacy name is removed.

Powered by Mojo

The engine's compute kernels — simulation, scoring, and local query execution — are written in Mojo and are proprietary. They are distributed as signed algenta-runtime-native wheels and are not part of this repository.

What is open, here and under Apache-2.0: both SDKs, the published API contract they are generated from, the client/runtime wire protocol they speak, and runnable examples — including examples/mojo-quickstart/, a minimal end-to-end walkthrough of calling the native runtime through the SDK.

What is open source?

This repository contains Algenta's Python and TypeScript client SDKs and the official MCP server (packages/mcp/), licensed under Apache-2.0 (see LICENSE and NOTICE).

The Algenta engine itself is closed source and is not contained in this repository. Engine licensing, device entitlements, worker limits, concurrency limits, and Server Compute Units are enforced independently by the engine, subject to the separate Algenta Engine license.

The SDK is a plain HTTP client. It holds no license-signing keys, no entitlement-enforcement logic, and no secret shared with the engine — every entitlement claim is independently verified and enforced by the closed engine, never by this SDK. Fork it, delete every check in it, or replace it with your own HTTP client entirely — modifying or replacing this SDK does not change the execution capacity licensed to an Algenta engine. See SECURITY.md for what that means for vulnerability reports.

Algenta does not require hosted inference or telemetry for execution. Paid licenses expand local execution and governance capacity rather than charging per SDK call.

Verify a release

Every release built by release.yml is tied to:

• a protected sdk-vX.Y.Z source tag in this repository;
• the exact commit that tag points to;
• a release-authorization record, signed by the internal release pipeline after the engine's test suite has validated the commit, binding that commit and a contract-file digest to the version being released (see releases/).

release.yml refuses to build or publish anything unless all of the above independently agree — see scripts/verify_release_authorization.py.

Each GitHub Release cut since signing was added (September 2026) carries, next to the wheel, the sdist and release-manifest.json:

• a keyless Sigstore signature bundle per asset ( .sigstore.json), signed by the release.yml run itself;
• SLSA build provenance covering all three assets (multiple.intoto.jsonl), from the SLSA generic generator.

To check an asset against both, with VERSION set to the release version (VERSION=1.0.15 for tag sdk-v1.0.15):

pipx run sigstore verify identity "algenta_sdk-${VERSION}-py3-none-any.whl" \

--bundle "algenta_sdk-${VERSION}-py3-none-any.whl.sigstore.json" \ --cert-oidc-issuer https://token.actions.githubusercontent.com \ --cert-identity "https://github.com/thyn-ai/algenta-sdk/.github/workflows/release.yml@refs/tags/sdk-v${VERSION}"

slsa-verifier verify-artifact "algenta_sdk-${VERSION}-py3-none-any.whl" \ --provenance-path multiple.intoto.jsonl \ --source-uri github.com/thyn-ai/algenta-sdk \ --source-tag "sdk-v${VERSION}"

A release published through release.yml's workflow_dispatch path was signed from the dispatched branch, so its certificate identity ends in @refs/heads/main instead of the tag; the bundle records which.

Versioning

Both packages share one version number, since they wrap one API contract, and follow Semantic Versioning:

• Patch — bug fixes and documentation; no API surface change.
• Minor — backward-compatible additions (new methods, new optional fields).
• Major — breaking changes to exported symbols, required fields, or behavior, announced in advance through the deprecation window above.

Release history lives in CHANGELOG.md.

#