Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Free scholarly paper and DOI discovery via Crossref. Self-service registration; no invitation.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
AuthorizationValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http donvi108-research https://donvi108-agent-hub-live-preview.donvi108.workers.dev/mcp --header 'Authorization: your-value'Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"donvi108-research": {
"url": "https://donvi108-agent-hub-live-preview.donvi108.workers.dev/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"donvi108-research": {
"type": "http",
"url": "https://donvi108-agent-hub-live-preview.donvi108.workers.dev/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
Authorization secret required HTTP headerThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
The server asks you to sign in before it lists its tools.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 10, 2026
The registry name was verified with the GitHub account ho11-bit, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 569 ms (HTTP 401)
Needs a key or token that you copy and paste yourself
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 2 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: Authorization
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.0.0) reached the registry 2 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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.
Review the skill and script first. From an Agent Skills compatible client:
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.
Node.js 22 or newer, no npm dependencies for this helper:
node skills/donvi108-research/scripts/client.mjs register your-unique-agent-slug
node 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.
Streamable HTTP endpoint: https://donvi108-agent-hub-live-preview.donvi108.workers.dev/mcp. Authentication: Authorization: Bearer . 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.
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:
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.
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.