Alembica MCP

io.github.open-and-sustainablePublished by GitHub account open-and-sustainablev0.3.5Updated Oct 24, 2026

MCP server for Alembica validation, extraction, cost estimation, and schema queries.

VerifiedSTDIODesktop onlyData & AnalyticsAI & ML

Overview

AI-generated overview

Alembica MCP lets an assistant validate extraction queries, estimate LLM token costs, and extract structured datasets from unstructured text.

What you can do
Validate input queries for correct formatting before model interaction, including schema version checks and optional provider fields such as base URL, region, project and location. Estimate token costs for a requested extraction against different model pricing. Extract structured datasets from unstructured text corpora using supported LLM providers. Query schema information to shape extraction requests.
When to use it
Use it when you want an assistant to turn unstructured text into structured datasets through LLM providers, and to check query formatting and token cost before running an extraction.
Requirements
Runs as a local process over stdio, from a locally built Go binary or the published container image. Extraction relies on an LLM provider such as OpenAI, Google AI, Anthropic, Cohere, DeepSeek, Perplexity, AWS Bedrock, Azure AI, Vertex AI or a self-hosted OpenAI-compatible endpoint, so provider credentials and network access are needed. No environment variables or authentication are declared in the manifest.
Before you install
Extraction sends your text to the chosen third-party LLM provider, so review what data leaves your machine. Provider credentials are required for extraction. Cost estimation returns zero for self-hosted, AWS Bedrock, Azure AI and Vertex AI providers, so do not rely on it for budgeting there.

Installation

In SourceWeft

  1. Open Alembica MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[logo] alembica

Open Science Software for Semantic Synthesis and Extraction of Information from Unstructured Sources.

[Go Reference] [Go Report Card] [DOI] [MCP Registry]

About

alembica simplifies the use of Large Language Models (LLMs) to extract structured datasets from unstructured corpora of text. It provides a flexible and scalable framework to process, synthesize, and transform textual information into structured formats suitable for analysis and further processing.

Supports OpenAI, Google AI, Anthropic, Cohere, DeepSeek, Perplexity, AWS Bedrock, Azure AI, Vertex AI, and Self-Hosted OpenAI-compatible providers.

Installation (Go)

To install alembica in Go, run:

sh
go get github.com/open-and-sustainable/alembica

If you want to use alembica in other programming languages, check out the C-Shared Library in the User Guide.

Documentation

User Guide – Learn how to use alembica in different programming languages. API Reference – Explore the Go package documentation.

MCP Server

alembica includes an optional MCP server for agent tool access.

The MCP server can be used from a locally built Go binary, the GHCR container image, or the MCP Registry.

Available in the official MCP Registry:

See the User Guide MCP page for installation options, run commands, and tool schemas.

MCP Registry publishing

The MCP server is published to the MCP Registry by GitHub Actions when a version tag such as v1.2.3 is pushed.

The workflow uses GitHub OIDC for authentication, and each new registry version is published explicitly by CI rather than implicitly from GitHub Releases.

Features

  • Validation of Input – Ensures that queries are correctly formatted to support proper interaction with models.
  • Cost Assessment – Calculates token costs based on the requested extraction and different model pricing.
  • Data Extraction – Processes unstructured text and transforms it into structured datasets for further analysis.

Note: Cost estimation is not supported for Self-Hosted, AWS Bedrock, Azure AI, or Vertex AI providers and will return zero.

Optional model fields for cloud/local providers:

  • base_url and api_version for Azure/OpenAI-compatible endpoints
  • region for AWS Bedrock
  • project_id and location for Vertex AI

Use schemaVersion: "v2" when you need these cloud/local provider fields or non-enumerated model IDs.

Authors & Contributions

Author: Riccardo Boero - [email protected]

Contributions are welcome!

License

alembica is licensed under the GNU AFFERO GENERAL PUBLIC LICENSE, Version 3.

[AGPL License]

Citation

Boero, R. (2025). alembica - Open Science Software for Semantic Synthesis and Extraction of Information from Unstructured Sources. Zenodo. https://doi.org/10.5281/zenodo.14899666

Source: README.md at commit 0967130

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.3.5LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts