Real-time web search, reasoning, and research through Perplexity's API
NestDaddy is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Live web search, news from 45+ countries, full article text and research papers for AI agents.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http nestdaddy-mcp https://mcp.nestdaddy.com/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'
# 2 — ask your agent for something these tools do
# web_search, news_search, news and 6 more
It needs AUTHORIZATION (Bearer followed by your NestDaddy API key. Get a key at https://nestdaddy.com/mcp): this sends it in the Authorization header from your environment, so export it first — its endpoint answers 401 without it.
NestDaddy costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads AUTHORIZATION (Bearer followed by your NestDaddy API key. Get a key at https://nestdaddy.com/mcp) from your environment each time it connects and sends it in the Authorization header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx AUTHORIZATION … and open a new terminal (Windows).
claude mcp add --scope user --transport http nestdaddy-mcp https://mcp.nestdaddy.com/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'Reconnect, or start a new session, and the tools appear in the model’s tool list.
It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — Bearer followed by your NestDaddy API key. Get a key at https://nestdaddy.com/mcp. You set it in your own client’s config, on your machine — this marketplace never holds it.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
9 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search the web with NestDaddy's own index: title, url, snippet and domain of each page. For time-sensitive queries (a year, "latest", "today", "harga ...") fresh news articles are mixed in on top (type "news"). Official sources are mixed in too: Stack Overflow answers for programming errors (type "qa"), Wikipedia for people, places and "what is" questions (type "wiki"), and an answer
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| limit | integer | no | — |
Find news articles about anything by key words: every article NestDaddy collected from 45+ countries in the last 120 days, best match and newest first. The best tool for questions about recent events, people, companies and places. Use the words a headline would use, in the local language for local news (e.g. "Najib perintah pelepasan"). country: optional two-letter code (MY, SG, US ...
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| country | string | no | — |
| days | integer | no | — |
| limit | integer | no | — |
| full_text | boolean | no | — |
Latest news headlines with links and summaries, refreshed every few minutes. topic: global, tech or financial. category: a section inside the topic (e.g. 'ai', 'crypto', 'stocks', 'politics'), or 'all'. limit: 1-50 (default 10). full_text: true to also get the full text of the first 5 articles (each article read counts as one extra API call). To find news about a subject, use news_sear
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | no | — |
| category | string | no | — |
| limit | integer | no | — |
| full_text | boolean | no | — |
Latest local news from one country. country: two-letter code, e.g. MY, SG, ID, TH, PH, KR, US, GB, JP, IN, AU. category: all, breaking, business, sports, entertainment, politics, health or science. limit: 1-50. full_text: true to also get the full text of the first 5 articles (each read counts as one extra API call). To find news about a subject, use news_search with country.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| country | string | yes | — |
| category | string | no | — |
| limit | integer | no | — |
| full_text | boolean | no | — |
Read the full text of one web page or news article (title, author, date and the main text, without menus or ads). Use it after news or web_search when you need the details behind a headline. url: the page link from a search or news result. max_chars: 500-30000 (default 8000).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| max_chars | integer | no | — |
Scientific papers from arXiv, PubMed, CORE, OpenAlex, CrossRef, Europe PMC and bioRxiv. Returns title, authors, year, abstract and link. limit: 1-50 (default 10).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| limit | integer | no | — |
AI models, apps and open-source projects, updated daily: every new model on OpenRouter (with prices per million tokens), trending Hugging Face models and apps, fast-growing GitHub AI / agent / MCP projects, and the big assistants with their newest models. query: optional words (name, use or vendor, e.g. "video", "claude", "mcp server"). category: all, llm, image, video, audio, code, wr
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | — |
| category | string | no | — |
| sort | string | no | — |
| limit | integer | no | — |
Software and developer tools with their current version, updated daily (Homebrew installs of the last 30 days): name, description, category, platform, latest_version, install command (in tags) and link. query: optional words. category: all, development, productivity, design, security, utilities, multimedia, browser, communication, ai, cloud. sort: trending (most installed), latest (rec
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | — |
| category | string | no | — |
| sort | string | no | — |
| limit | integer | no | — |
Games, updated daily from Steam: top sellers, new releases, coming soon, deals and the most played right now, with description, genre, platforms, price, release date, rating (0-10 from player reviews) and players_now. query: optional words (title, genre or developer). genre: all, action, adventure, rpg, strategy, sports, racing, puzzle, simulation. sort: trending (most played now), lat
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | — |
| genre | string | no | — |
| sort | string | no | — |
| limit | integer | no | — |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install NestDaddy or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| web_search | untrusted-input | untrusted-input: keyword "web_search", declares openWorldHint: true (interacts with entities outside the server) |
| news_search | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| news | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| country_news | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| read_page | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| research_papers | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| ai_tools | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| software | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| games | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.1.1.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish NestDaddy can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.