How do I install Notanda (Beta)?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Notanda (Beta) need an API key?

The publisher lists these environment variables: HARVESTER_OPENALEX_API_KEY.

What transport does Notanda (Beta) use?

Notanda (Beta) runs locally over stdio.

When was Notanda (Beta) last checked?

Last checked 2026-11-09. Every OpenAlex search stores its request, response and checksums so sources can be checked later.

Notanda (Beta) MCP server

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

uvx notanda-mcp==0.1.0b3

Credentials from the publisher

HARVESTER_OPENALEX_API_KEY — OpenAlex API key used for literature searches.

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1HARVESTER_OPENALEX_API_KEY=<secret> claude mcp add io.github.rudiregenwurm-notanda -- uvx notanda-mcp==0.1.0b3

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "io.github.rudiregenwurm-notanda": {4      "command": "uvx",5      "args": [6        "notanda-mcp==0.1.0b3"7      ],8      "env": {9        "HARVESTER_OPENALEX_API_KEY": "<secret>"10      }11    }12  }13}

claude_desktop_config.json

Local · pypiPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
Version: 0.1.0-beta.3
API key

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

Notanda — Open-Access API Harvester

Notanda is the public product name and PyPI distribution name. The repository, Python import package and CLI keep their established technical names Open-Access-API-Harvester, harvester and harvester.

This repository publishes the reviewed 1.3.2 product-core source. It is not a hosted service and the recommended accompanied beta path remains [email protected].

A public Installer Preview is available under GitHub Releases solely as a technical pre-release: https://github.com/RudiRegenwurm/Open-Access-API-Harvester/releases/tag/v1.3.0-installer-preview.1 Those installers are unsigned on Windows/Linux and ad-hoc signed on macOS, may trigger SmartScreen/Gatekeeper warnings, and are not the recommended installation path for non-technical users.

A headless, resumable, idempotent CLI pipeline that discovers Open-Access scholarly works through OpenAlex Topics, cross-checks them against Europe PMC, falls back to Unpaywall for OA locations, validates every downloaded artifact, and stores the result as a deterministic flat corpus ready for a downstream pre-ingestion pipeline. Schema 4 additionally retains provider observations, merge decisions and acquisitions in an append-only Evidence Ledger while the established read model remains compatible.

DISCOVERY → NORMALIZATION → DEDUPLICATION → ACQUISITION → VALIDATION → INGESTION → PROVENANCE/REPORTING

It is not a web application, document-management system, search engine, OCR system or LLM application. It is a document harvesting pipeline with persistent state.

Quick start

With Python 3.10 or newer, install the PyPI distribution in a fresh virtual environment:

python -m venv .venv
# Linux/macOS:
source .venv/bin/activate
# Windows PowerShell:
# .venv\Scripts\Activate.ps1
python -m pip install notanda
harvester --version

For an isolated application install with pipx:

pipx install notanda

For development from a repository checkout:

python3 -m venv .venv && . .venv/bin/activate
pip install -e ".[dev]"

With the local control center (no command line needed after this)

harvester serve

Opens a local web UI at http://localhost:8765/ for harvesting, browsing the corpus, inspecting runs and provenance, verifying integrity, retrying failures and editing settings. Credentials can be entered in its Settings page on first run.

New Harvest offers two search modes. Conventional Search uses the query you type, exactly as typed. Assisted Search turns a plain-language research question into one compact retrieval query you can edit, previews up to ten real discovery results without downloading anything, and only then hands the approved query to the same harvest pipeline. Assisted Search needs a query-advisor credential; Conventional Search does not and is unaffected when the advisor is missing or unavailable.

Experimental local MCP server

The repository also contains an optional local MCP component under mcp/. It exposes two deliberately narrow tools — search_literature and get_evidence — and persists the request, provider observation, exact returned result and SHA-256 manifest under one stable evidence ID. It performs no full-text download or corpus write and opens no network server.

The separate notanda-mcp Beta package uses the reviewed notanda==1.3.2 PyPI release as its core. With Python 3.11 or 3.12, install it using python -m pip install "notanda-mcp==0.1.0b3". The MCP Registry entry describes the package, local stdio transport, required OpenAlex API key and writable evidence directory. The package is not included in the notanda 1.3.2 distribution. The technical live search and restart/receipt checks passed again on 2026-10-14 with core 1.3.2; Thomas's external unaccompanied test is still pending. Client configuration, evidence format and verification steps are in mcp/README.md.

From the command line

export HARVESTER_OPENALEX_API_KEY='…'          # free: openalex.org/settings/api
export HARVESTER_CONTACT_EMAIL='[email protected]'  # required by Unpaywall
export HARVESTER_ADVISOR_API_KEY='…'           # optional: Assisted Search in the UI only

harvester discover --topic-id T10159 --limit 25    # dry run, downloads nothing
harvester harvest  --topic-id T10159 --limit 25    # real harvest
harvester verify --deep                            # check the corpus against state

Both drive the same engine and the same state database: a run started in the browser can be resumed from the terminal.

Output

The downstream contract is a flat directory of deterministic sibling files:

<storage_root>/
├── doi_10_1371_journal_pone_0123456_5d41402abc4b.pdf     primary full text
├── doi_10_1371_journal_pone_0123456_5d41402abc4b.xml     when legitimately available
└── doi_10_1371_journal_pone_0123456_5d41402abc4b.json    mandatory sidecar

The sidecar keeps bibliographic metadata, artifact metadata, provenance and harvest state in separate blocks. Missing information is null; nothing is ever invented.

{
  "document_id": "doi_10_1371_journal_pone_0123456_5d41402abc4b",
  "doi": "10.1371/journal.pone.0123456",
  "title": "…",
  "abstract": "…",
  "oa_status": "gold",
  "oa_status_source": "openalex",
  "domain_tags": ["Social Sciences", "Psychology", "…"],
  "artifacts": { "pdf": { "sha256": "…", "size_bytes": 123456, "…": "…" } },
  "provenance": {
    "discovered_via": ["openalex"],
    "cross_checked_via": ["europe_pmc"],
    "acquired_via": "unpaywall",
    "resolved_url": "…",
    "http_status": 200
  },
  "harvest": { "run_id": "…", "status": "COMPLETED", "attempts": 1 }
}

What it guarantees

Guarantee	How
Nothing false succeeds	HTTP 200 is never enough: magic bytes, trailer, parser openability, size bounds and SHA-256 must all pass before an artifact exists under its final name.
Atomic artifacts	Every download goes to a unique `.part` file and is published with a single atomic rename after validation.
Resumable	Discovery cursors and document state are checkpointed continuously; `harvester resume` continues without repeating completed work.
Idempotent	Re-running the same harvest downloads nothing and produces a byte-identical corpus.
Deduplicated	One logical document per canonical DOI, however many providers report it.
No silent loss	Every failure is a structured row in the state database and appears in the run report.
Historical evidence	Re-observations, field-level merge decisions and acquisitions append immutable rows; current `documents`, `source_records` and `artifacts` remain compatible projections.
Budget-safe	Provider daily-budget exhaustion checkpoints and suspends cleanly (exit 4) instead of hammering the API.
Secret-safe	API keys and contact addresses are redacted from logs, provenance, reports and state.
Lawful	Only OA locations that a provider explicitly flags as open are fetched. Access controls are recorded, never circumvented.

Commands

Command	Purpose
`serve`	open the local web control center
`harvest`	discover + acquire
`discover`	discovery and normalization only (dry run)
`resume`	continue an interrupted or suspended run
`status`	run and corpus status (`--json`)
`inspect`	one document's canonical record (`--json`)
`verify`	check the corpus against state (`--deep`, `--json`)
`retry-failed`	re-queue failed documents
`evidence-export`	write a deterministic, independently readable ledger JSON bundle (`--output`)
`evidence-restore`	validate and restore a bundle into an empty ledger (`--input`)

The evidence bundle contains Ledger records and file references, not the PDF/XML artifacts or the complete corpus directory. A portable corpus export with files is still in development.

Exit codes: 0 success · 1 failure · 2 configuration error · 3 completed with document failures · 4 suspended (provider budget) · 130 interrupted.

Tests

pytest            # offline suite — no network, no credentials required
pytest -m live    # controlled real-provider smoke tests

The offline suite runs against deterministic in-process mock providers covering normal responses, pagination, throttling, budget exhaustion, timeouts, malformed payloads, missing full text, alternative locations and duplicates.

Documentation

File	Contents
`LICENSE`	MIT license for the product code and documentation, subject to the stated exceptions
`THIRD_PARTY_NOTICES.md`	bundled font licenses and separately licensed dependencies
`TRADEMARKS.md`	treatment of the Notanda name and visual identity assets
`CODE_SIGNING_POLICY.md`	Windows code signing policy for the SignPath Foundation application
`INSTALL-MACOS.md`	macOS Installer Preview and Gatekeeper exception procedure
`mcp/README.md`	experimental local MCP server, evidence contract and verification guide

Code signing policy

Windows installers are currently unsigned.

Dependencies

httpx (streaming HTTP with a pluggable transport), pypdf (PDF structural validation), defusedxml (safe XML parsing). Everything else is the standard library: configuration, SQLite persistence, CLI, logging, hashing, concurrency, retry — and the web UI, which uses http.server plus a front end with no build step, so harvester serve is the only command needed to run it.

License

The bundled IBM Plex and Source Serif 4 font files are not MIT-licensed; they remain under the SIL Open Font License 1.1 included beside the files. External Python dependencies are not vendored and retain their own licenses. The Notanda name, emblem, wordmark, lockup, favicons and avatar are excluded from the MIT grant. Details and exact file scopes are in THIRD_PARTY_NOTICES.md and TRADEMARKS.md.