# Dataverse Harvard

> Harvard Dataverse MCP.

- name: io.github.pipeworx-io/dataverse-harvard
- version: 0.1.2
- connection class: R0 (autonomous)
- trust: 96/100
- quality: –/100 (not scored)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.pipeworx-io%2Fdataverse-harvard
- tools: https://api.protogrid.dev/v1/servers/io.github.pipeworx-io%2Fdataverse-harvard/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "dataverse-harvard": {
      "type": "http",
      "url": "https://gateway.pipeworx.io/dataverse-harvard/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 85
- drivers: +repository +namespace-matches-repo +website -thin-description +reachable +uptime-99% +updated-25d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality –/100 (not scored)

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-03-26; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: n/a (weight 30)

- n/a `tools.descriptions`, `tools.description_length`, `tools.schemas`, `tools.annotations`, `tools.directory_hints`, `tools.token_cost`, `tools.api_dump`: tool list unknown (behind auth, not probed, or empty)

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool list unknown

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: unknown
- tools last changed: 2026-10-18T07:13:19.135Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.pipeworx-io/dataverse-harvard.svg)](https://protogrid.dev/servers/io.github.pipeworx-io/dataverse-harvard)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-18 `dataverse` removed
  - Dataverse (collection) metadata by alias or id.
- 2026-10-18 `dataset_files` removed
  - List all files in the latest version of a Harvard Dataverse dataset identified by its DOI persistent ID (e.g. "doi:10.7910/DVN/..."), returning file names, content types, sizes, and download URLs. For files Dataverse has TABULAR-INGESTED (CSV/DTA/SAV/POR under its ingest size limit), also returns exact COLUMN / VARIABLE NAMES and labels from Dataverse's DDI metadata (variables_by_file). If a dataset has no tabular-ingested files (common for very large files, or non-tabular formats), column names are not available from Dataverse at all — the response says so explicitly rather than silently omitting them.
- 2026-10-18 `dataset` removed
  - Full metadata for one Harvard Dataverse dataset by its DOI persistent id: title, authors, abstract, subject, keywords, version and publication date. The id must come from search — DOIs cannot be guessed.
- 2026-10-18 `search` removed
  - Keyword search across Harvard Dataverse — the ~200k-dataset open research repository. Returns dataset titles, DOIs, authors, publication dates and descriptions; pass a returned DOI to dataset or dataset_files. Use to find research data behind a paper or topic (e.g. "climate", "survey experiment", "replication data").
- 2026-10-18 `forget` removed
  - Delete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall.
- 2026-10-18 `remember` removed
  - Save data the agent will need to reuse later — across this conversation or across sessions. Use when you discover something worth carrying forward (a resolved ticker, a target address, a user preference, a research subject) so you don't have to look it up again. Stored as a key-value pair scoped by your identifier. Authenticated users get persistent memory; anonymous sessions retain memory for 24 hours. Pair with recall to retrieve later, forget to delete.
- 2026-10-18 `scan_competitor_ai_presence` removed
  - Compare AI visibility across multiple entities side-by-side. Probes each entity (your brand + N competitors) with ai_visibility_check, ranks by score, surfaces which is most/least recognized. Useful for competitive AI-marketing audits: "does Claude know about us as well as our competitors?". Returns ranked list with score, confidence, signal density per entity.
- 2026-10-18 `ai_visibility_check` removed
  - Probe one or more LLMs for what they know about a business / brand / product / topic and score visibility (0-100) per model. Default model is Workers AI Llama-3.3-70b (free); pass `_apiKey` to also probe Anthropic (BYO key — you pay Anthropic directly for those calls). Returns per-model {score, confidence, signals, raw_response} + a combined view. Useful for AI-marketing audits, pre-launch brand checks, competitive monitoring.
- 2026-10-18 `generate_llms_txt` removed
  - Generate a production-ready llms.txt file for any URL so AI crawlers (ChatGPT, Claude, Perplexity) can index the site cleanly. Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format. Output is a single text blob ready to drop at site-root/llms.txt. Useful for: getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor.
- 2026-10-18 `classify_row` removed
  - Cheap categorization: given a company and a list of candidate labels, decide which labels apply — the most common GTM/AI usage shape (tagging a list by industry, ICP fit, etc.), one small model call. Same evidence contract as research_row: each label comes back {label, applies, evidence_url, quote, status: found|inferred|not_established} — "found" only when the model's quote is independently verified as a verbatim substring of the text used. Pass text directly (cheapest — no fetch) or entity.domain to fetch the homepage once as a fallback. No text and no domain means every label is not_established with no model call made.

Full history: https://api.protogrid.dev/v1/servers/io.github.pipeworx-io%2Fdataverse-harvard/changes

## Remotes

- https://gateway.pipeworx.io/dataverse-harvard/mcp (streamable-http, auth none, reachable true, uptime30d 0.99159664)

## Packages

_none_

## Tools (0)

_none observed_