DONVI108 Free Research Beta

io.github.ho11-bitPublished by GitHub account ho11-bitv1.0.0Updated Oct 24, 2026

Free scholarly paper and DOI discovery via Crossref. Self-service registration; no invitation.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Remote MCP server that lets an assistant search Crossref for candidate scholarly papers and DOI references, with optional feedback on results.

What you can do
Search scholarly literature: run a public research query and get up to five candidate paper and DOI references from Crossref metadata, optionally filtered by source label. Report feedback: attach a usefulness rating and optional comment to a specific returned search call ID, updating the same report if repeated. Register a free agent credential through the REST helper before the MCP endpoint can initialize or list tools.
When to use it
Useful when an assistant needs quick candidate scholarly references or DOI lookups for a public research topic and the user will verify sources themselves. Not suitable when full text, private retrieval, or verified scientific evidence is required.
Requirements
Remote streamable HTTP endpoint; no local package. A free self-service DONVI108 agent credential registered first through the website or the Node.js 22+ helper script, sent as an Authorization bearer header via the client's secret store. Network access to the endpoint and Crossref.
Before you install
The Authorization header carries a secret agent credential; keep it private and out of source control. Registration profile fields are public, and a lost registration response is not retried. Results are candidate references, not full text or verified evidence, so check primary sources before citing. Do not send confidential queries. Daily and per-IP search quotas apply, and upstream failures can consume quota.

Installation

In SourceWeft

  1. Open DONVI108 Free Research Beta in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.ho11-bit%2Fdonvi108-research/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "donvi108-free-research-beta": {
      "type": "http",
      "url": "https://donvi108-agent-hub-live-preview.donvi108.workers.dev/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

DONVI108: free research tools for AI agents

Find candidate scholarly papers and DOI references from a REST or MCP workflow. Public free beta: no invitation, no card, no wallet. Register a self-service agent credential and start searching.

Source: Crossref public bibliographic metadata. Results are candidate references, not full text, private EIO retrieval, or verified scientific evidence. Check relevance and primary sources before citing. Do not send confidential queries.

Install the skill

Review the skill and script first. From an Agent Skills compatible client:

sh
npx skills add ho11-bit/donvi108-agent-skills --skill donvi108-research

Alternatively, copy skills/donvi108-research into your client's skill directory. Installing a skill does not itself authorize network calls, disclose data, or spend money. Use it when it fits the user's research task.

Try without an agent runtime

Node.js 22 or newer, no npm dependencies for this helper:

sh
node skills/donvi108-research/scripts/client.mjs register your-unique-agent-slugnode skills/donvi108-research/scripts/client.mjs search "shape memory alloy fiber pullout concrete" --limit 3 --source github

The helper saves credentials privately under your home directory and does not print them. Re-running registration stops if the credential file exists. Keep that file out of source control. Set DONVI108_BETA_CREDENTIAL_DIR to use another private directory for a dedicated client. Registration profile fields are public. A lost registration response is not automatically retried.

MCP

Streamable HTTP endpoint: https://donvi108-agent-hub-live-preview.donvi108.workers.dev/mcp. Authentication: Authorization: Bearer <your self-service agent credential>. Configure that header through your client's secret store. Register first through REST/the helper; the MCP endpoint requires authentication for initialization and tool listing.

  • research_papers: { "query": "your public research topic", "limit": 3, "source": "mcp-registry" }.
  • submit_beta_feedback: { "call_id": "returned UUID", "useful": false, "category": "irrelevant", "comment": "Optional concrete feedback" }.

Other existing network tools have their own scopes and availability. Private EIO is operator-controlled and is not part of this free research beta.

Limits and feedback

20 search attempts/agent/UTC day; 60/shared IP/day; 500/day and 10/minute across the beta. Up to 5 references/request. Upstream failures can consume quota. Wait after 429 or 503; do not create identities to evade limits. No automatic paid upgrade.

After checking a result for your actual task, optionally report its usefulness:

sh
node skills/donvi108-research/scripts/client.mjs feedback RETURNED_CALL_ID --useful false --category irrelevant --comment "Explain the mismatch without private data"

Feedback is tied to your own completed search; repeating the call ID updates one report. Comments are private to the operator. Do not automatically send positive feedback, rate our internal tests as adoption, or post confidential data in issues.

Usage metrics distinguish internal validation from unverified external agent identities. Identity counts are not independent customers, and self-reported useful results are not purchases. Queries and result content are not persisted in beta analytics. Usage/feedback are cleaned up daily after 90 days; encrypted backups expire separately after seven days.

What makes the beta useful?

One documented registration, a bounded common REST/MCP interface, DOI-based references, explicit failure behavior, and feedback tied to actual results. Crossref is the underlying metadata provider and can also be used directly. This beta does not claim a proprietary corpus or superior search relevance.

Integration problems or suggestions: open an issue. Never include credentials or private queries. This repository contains only the public skill, client and documentation; the operational system is maintained separately.

Source: README.md at commit 19a4e94

Tools

0
This server asks for a credential such as an API key, so SourceWeft could not read its tools without one and has not indexed them.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

85% 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 daysRequired25 pts
  • Auth declaredRequired10 pts
  • 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