# nichedb (remote · nichedb.dev)

Real-time public data (nichedb.dev)

- Trust score: 69/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

> **Recent critical change**: Authorization (2026-11-18). See the changelog below before you install this server.

## Components

- remote · `nichedb.dev`: 69/100 (this document), [markdown](https://verifymcp.io/servers/com-profullstack-nichedb/nichedb.md), [page](https://verifymcp.io/servers/com-profullstack-nichedb/nichedb)

## Channel facts

- Endpoint: `https://nichedb.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (update_webhook).
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 7998 tokens (~159/item across 50 items; 49 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 51 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the nichedb MCP server?

nichedb is a hosted endpoint at https://nichedb.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-profullstack-nichedb 'https://nichedb.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-profullstack-nichedb": {
      "url": "https://nichedb.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-profullstack-nichedb": {
      "type": "http",
      "url": "https://nichedb.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-profullstack-nichedb]
url = "https://nichedb.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-profullstack-nichedb": {
      "type": "remote",
      "url": "https://nichedb.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-profullstack-nichedb --url 'https://nichedb.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-profullstack-nichedb:
    url: "https://nichedb.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-profullstack-nichedb": {
      "Transport": "http",
      "Url": "https://nichedb.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-profullstack-nichedb -t streamable-http -u 'https://nichedb.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-profullstack-nichedb": {
      "type": "http",
      "url": "https://nichedb.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 68, +15)

- [critical regression] Authorization: unverified → fail
- [security regression] HSTS header: unverified → fail
- [security improvement] Injection markers: unverified → pass
- [security improvement] TLS certificate: unverified → pass
- [security improvement] Transport: fail → pass
- [security] Tool “where_to_buy_book” rewrote its description, which is the text the model reads
- [functional improvement] Endpoint reachability: unreachable → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] New tool “find_product”

### 2026-11-17 (score 53, −13)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-11-15 (score 66, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] Authorization: fail → unverified
- [security regression] HSTS header: fail → unverified
- [security regression] Stability: 0.07 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] TLS certificate: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-11-14 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 65, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-12 (score 65, +61)

- [critical regression] Authorization: unverified → fail
- [security regression] HSTS header: unverified → fail
- [security improvement] Injection markers: unverified → pass
- [security improvement] TLS certificate: unverified → pass
- [security improvement] Transport: fail → pass
- [security] First check of Judged manipulation: pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: 100
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100

### 2026-11-11 (score 4)

First indexed and scored.

## MCP tools (49)

### `stats` (~24 tokens)

Database Stats

What this deployment holds: collections, sources, items, items added today, feeds.

### `list_collections` (~24 tokens)

List Collections

The collections (niches) with their source, feed and item counts.

### `list_adapters` (~28 tokens)

List Adapters

Every adapter this deployment can run, with the config fields each takes. Use before add_source.

### `list_enrichers` (~51 tokens)

List Enrichers

Every enricher (YouTube videos, Wikipedia, repo stats, downloads, company profiles, TL;DRs) and which collections turn it on by default. Items carry their results under `enrichment`.

### `list_sources` (~44 tokens)

List Sources

Sources with status, last run and item counts. Optionally one collection.

Input parameters:

- `collection` (string): Collection slug, e.g. games (optional; see list_collections)

### `list_feeds` (~40 tokens)

List Feeds

Public feeds, most followed first. Optionally one collection.

Input parameters:

- `collection` (string): Collection slug, e.g. games (see list_collections)

### `feed_items` (~232 tokens)

Feed Items

What a feed selects, newest first. Page with before_id.

Input parameters:

- `bbox` (string): west,south,east,north; west > east crosses the antimeridian
- `before_id` (integer): Keyset cursor: the smallest item id from the previous page, e.g. 81234567; not with sort=distance
- `feed` (string, required): Feed slug, e.g. new-on-steam (see list_feeds)
- `lat` (number): Query center latitude; requires long
- `limit` (integer): Rows to return, integer 1-200, default 30, e.g. 50
- `long` (number): Query center longitude; requires lat
- `offset` (integer): Rows to skip when sort=distance, integer, e.g. 30
- `radius` (number): Default 10; maximum 1000 km
- `sort` (string): Result order. distance (needs lat and long) puts the nearest first, e.g. "distance"; anything else keeps newest first
- `unit` (string): Default km

### `recent_items` (~271 tokens)

Recent Items

Newest items, optionally narrowed to a collection, source or kind.

Input parameters:

- `bbox` (string): west,south,east,north; west > east crosses the antimeridian
- `before_id` (integer): Keyset cursor: the smallest item id from the previous page, e.g. 81234567; not with sort=distance
- `collection` (string): Collection slug, e.g. games (see list_collections)
- `kind` (string): Item kind, e.g. release, title, filing (optional)
- `lat` (number): Query center latitude; requires long
- `limit` (integer): Rows to return, integer 1-200, default 30, e.g. 50
- `long` (number): Query center longitude; requires lat
- `offset` (integer): Rows to skip when sort=distance, integer, e.g. 30
- `radius` (number): Default 10; maximum 1000 km
- `sort` (string): Result order. distance (needs lat and long) puts the nearest first, e.g. "distance"; anything else keeps newest first
- `source` (string): Source slug, e.g. steam-new-releases (see list_sources)
- `unit` (string): Default km

### `upcoming` (~201 tokens)

Upcoming Items

Items dated in the future (releases, launches, deadlines), soonest first.

Input parameters:

- `bbox` (string): west,south,east,north; west > east crosses the antimeridian
- `collection` (string): Collection slug, e.g. games (see list_collections)
- `days` (integer): How many days ahead to look, integer, default 30, e.g. 90
- `lat` (number): Query center latitude; requires long
- `limit` (integer): Rows to return, integer 1-200, default 50, e.g. 20
- `long` (number): Query center longitude; requires lat
- `radius` (number): Default 10; maximum 1000 km
- `sort` (string): Result order. distance (needs lat and long) puts the nearest first, e.g. "distance"; anything else keeps newest first
- `unit` (string): Default km

### `search_items` (~215 tokens)

Search Items

Full-text search over titles, summaries and tags. Use this first when you know a name.

Input parameters:

- `bbox` (string): west,south,east,north; west > east crosses the antimeridian
- `collection` (string): Collection slug, e.g. games (see list_collections)
- `kind` (string): Item kind, e.g. release, title, filing (optional)
- `lat` (number): Query center latitude; requires long
- `limit` (integer): Rows to return, integer 1-100, default 20, e.g. 10
- `long` (number): Query center longitude; requires lat
- `q` (string, required): Search words, e.g. elden ring
- `radius` (number): Default 10; maximum 1000 km
- `sort` (string): Result order. distance (needs lat and long) puts the nearest first, e.g. "distance"; anything else keeps newest first
- `unit` (string): Default km

### `match_items` (~429 tokens)

Match Names to Items

Which title, channel or fixture is this name? Give a file name, a release name or a playlist entry ("Top.Gun.Maverick.2022.1080p.mkv", "US: ESPN2 HD"); it is cleaned (year, season and episode, quality tags, playlist decorations) and matched by similarity. A matchup ("NFL: Chiefs vs Bills", "Lakers @ Celtics", "Rangers at Celtic 19:45") is answered by the fixture whose two teams those are, kicking off between 36 hours ago and 7 days ahead unless date narrows it. Each result carries a score in 0..1. Use screen for films and TV, channels for television channels, sports for fixtures.

Input parameters:

- `bbox` (string): west,south,east,north; west > east crosses the antimeridian
- `collection` (string): Collection slug: screen, channels or sports (optional), e.g. screen
- `date` (string): A day (YYYY-MM-DD) to look for a fixture on, plus a day either side, e.g. 2026-11-02
- `kind` (string): Item kind: title, channel or fixture (optional), e.g. title
- `lat` (number): Query center latitude; requires long
- `limit` (integer): Rows to return, integer 1-50, default 5, e.g. 3
- `long` (number): Query center longitude; requires lat
- `q` (string, required): The name as written, e.g. Top.Gun.Maverick.2022.1080p.mkv or US: ESPN2 HD
- `radius` (number): Default 10; maximum 1000 km
- `sort` (string): Result order. distance (needs lat and long) puts the nearest first, e.g. "distance"; anything else keeps newest first
- `unit` (string): Default km
- `year` (integer): A four-digit year to prefer, when known, e.g. 2022

### `get_item` (~37 tokens)

Get Item

One item with its full adapter payload.

Input parameters:

- `id` (integer, required): Numeric item id from any listing, e.g. 81234567

### `population` (~297 tokens)

Population Lookup

Population and demography, drilled down from the world to the ZIP code. Give a `key` (us, us-ca, us-ca-los-angeles, gb, gb-england-london), a US `zip`, or a place name in `q`; no argument is the world. Answers with the area (population, year, measures: age, income, home value, rent, poverty, education, unemployment, race and Hispanic origin for the US; growth, age structure, births, deaths, fertility, life expectancy, migration, GDP per head and Gini for countries), how many areas of each level it contains, and the largest of its children at `level` (country, state, city or zip). Sources: World Bank, US Census ACS 5-year, GeoNames.

Input parameters:

- `key` (string): Area key, e.g. us, us-ca, us-ca-los-angeles, us-90210, de (optional)
- `level` (string): Which children to list: country, state, city or zip (optional)
- `limit` (integer): Children to list, default 20, max 500
- `offset` (integer): Skip this many children, for paging
- `q` (string): A place name to look up, e.g. Springfield (optional)
- `zip` (string): A US ZIP code (optional), 5 digits, e.g. 90210

### `where_to_buy_book` (~371 tokens)

Where to Buy a Book

Where to buy a book. Give an `isbn` (10 or 13 digits, hyphens fine), or a `title` and `author`, or `item` (a books-collection item id). Answers with the edition from Open Library (title, authors, publisher, pages, cover), `online`: links at Amazon, Bookshop.org, Barnes & Noble, Books-A-Million, Target, Walmart, Powell's, ThriftBooks, Better World Books, AbeBooks, eBay, BookFinder, Google Play Books, Kobo, Libby and WorldCat, each with `kind` (new, used, ebook, borrow) and `sponsored`. Give a US `zip` for `inStore`: the chains' store finders for that ZIP and the bookshops and libraries within 10 miles from OpenStreetMap, with address, phone, hours and distance. Most sellers publish no stock or prices, so call a shop with the ISBN; `statedOffers` lists the ones whose own page data does state a price and stock for this ISBN (from the product graph, with `seenAt`).

Input parameters:

- `author` (string): Author, with a title (optional), e.g. Jane Austen
- `isbn` (string): ISBN-10 or ISBN-13, hyphens fine (optional), e.g. 978-0-14-143951-8
- `item` (string): A books-collection item id (optional), e.g. 81234567
- `title` (string): Title, when there is no ISBN (optional), e.g. Pride and Prejudice
- `zip` (string): A US ZIP code for shops near you (optional), 5 digits, e.g. 97209

### `find_product` (~405 tokens)

Find a Product Across Stores

Find a product and every store selling it, from the product graph: offers that stores state in their own product page data (schema.org Product/Offer), read by the pit.world crawler and joined across stores by barcode or part number. Give `gtin` (any UPC, EAN, ISBN-13 or GTIN-14; hyphens fine) or `brand` + `mpn` for an exact product, or `q` for words (a name, brand, part number or SKU; a bare barcode in `q` works too). `host` keeps one store. Each product has `key`, `name`, `brand`, `gtin`, `mpn`, `stores`, `lowPrice` + `currency` (only when every buyable offer shares one currency) and `offers` sorted buyable-first then cheapest: `seller`, `host`, `price`, `currency`, `availability` (schema.org word: InStock, OutOfStock, PreOrder...), `condition`, `variant`, `offerUrl`, `seenAt`. Prices are what the page said when last read, not live; quote `seenAt` with them. No store pays to be listed.

Input parameters:

- `brand` (string): Brand, with mpn (optional), e.g. Bosch
- `gtin` (string): A UPC, EAN, ISBN-13 or GTIN-14 (optional), e.g. 0027242923232
- `host` (string): Only this store (optional), e.g. example-shop.com
- `limit` (integer): Products to return, integer 1-50, default 10, e.g. 5
- `mpn` (string): The maker's part number, with brand (optional), e.g. GSR12V-300B22
- `q` (string): Words to match (optional), e.g. sony wh-1000xm5

### `create_feed` (~360 tokens)

Create Feed

Save a query as a feed (needs a key). Sources, kinds and tags narrow; q is a text match; upcoming keeps only future-dated items.

Input parameters:

- `bbox` (string): west,south,east,north; west > east crosses the antimeridian
- `collection` (string, required): Collection slug, e.g. games (see list_collections)
- `description` (string): One line about the feed (optional), e.g. Every Rust crate release
- `enrichers` (array): Enricher names to show (see list_enrichers), e.g. ["youtube"]; omit for the collection defaults
- `kinds` (array): Item kinds to include (optional), e.g. ["release"]
- `lat` (number): Query center latitude; requires long
- `long` (number): Query center longitude; requires lat
- `name` (string, required): Display name for the feed, e.g. Rust releases
- `public` (boolean): Listed publicly, true or false, default true
- `q` (string): Text the items must match (optional), e.g. tokio
- `radius` (number): Default 10; maximum 1000 km
- `sort` (string): Result order. distance (needs lat and long) puts the nearest first, e.g. "distance"; anything else keeps newest first
- `sources` (array): Source slugs to include (optional), e.g. ["crates"]
- `tags` (array): Tags, any one matches (optional), e.g. ["rust", "cli"]
- `unit` (string): Default km
- `upcoming` (boolean): true keeps only items dated in the future, e.g. true; default false

### `follow_feed` (~128 tokens)

Follow Feed

Follow a feed as the key owner (needs a key). Channels: webpush, email, webhook.

Input parameters:

- `channels` (array): Delivery channels: webpush, email, webhook; default ["webpush", "email"]
- `feed` (string, required): Feed slug, e.g. new-on-steam (see list_feeds)
- `webhook_secret` (string): Shared secret the receiver verifies signatures with, any string, e.g. s3cret-value
- `webhook_url` (string): https URL for the webhook channel, e.g. https://example.com/hooks/nichedb

### `list_webhooks` (~32 tokens)

List Webhooks

The key owner's account webhook endpoints (never their secrets) and the event types this site emits. Needs a key.

### `create_webhook` (~149 tokens)

Create Webhook

Add an account webhook: signed POSTs (Standard Webhooks + CloudEvents) to an https URL for events such as feed.item.published (new items in feeds you follow), feed.followed, feed.created, submission.approved. Patterns like feed.* work; omit events for all. Returns the signing secret. Needs a key.

Input parameters:

- `description` (string): A note for yourself (optional), e.g. staging receiver
- `events` (array): Event types or patterns, default all, e.g. ["feed.*", "submission.approved"]
- `url` (string, required): Public https URL that receives the POSTs, e.g. https://example.com/hooks/nichedb

### `update_webhook` (~147 tokens)

Update Webhook

Change an account webhook: url, events, description, or enabled (true turns it back on and clears its failure count). Needs a key.

Input parameters:

- `description` (string): New note (optional), e.g. production receiver
- `enabled` (boolean): true turns it on and clears failures, false pauses it
- `events` (array): New event types or patterns (optional), e.g. ["feed.item.published"]
- `id` (string, required): Webhook id from list_webhooks, e.g. wh_01JB2X3Y4Z
- `url` (string): New https URL (optional), e.g. https://example.com/hooks/v2

### `delete_webhook` (~50 tokens)

Delete Webhook

Remove an account webhook and its delivery log. Needs a key.

Input parameters:

- `id` (string, required): Webhook id from list_webhooks, e.g. wh_01JB2X3Y4Z

### `test_webhook` (~58 tokens)

Send Test Webhook

Send a webhook.test event to one of your endpoints now and report the HTTP status. Needs a key.

Input parameters:

- `id` (string, required): Webhook id from list_webhooks, e.g. wh_01JB2X3Y4Z

### `rotate_webhook_secret` (~61 tokens)

Rotate Webhook Secret

Replace a webhook signing secret; the old one stops working at once. Returns the new secret. Needs a key.

Input parameters:

- `id` (string, required): Webhook id from list_webhooks, e.g. wh_01JB2X3Y4Z

### `webhook_deliveries` (~94 tokens)

Webhook Deliveries

Recent webhook deliveries with status, attempts, last error and payload: for one endpoint, or all of yours. Needs a key.

Input parameters:

- `id` (string): Webhook id (optional; omit for all of yours), e.g. wh_01JB2X3Y4Z
- `limit` (integer): Rows to return, integer 1-200, default 20, e.g. 50

### `submit_feed` (~131 tokens)

Suggest a Feed

Suggest an RSS or Atom feed for the index. No key needed. An admin reviews every suggestion before anything is fetched; approved podcast feeds are handed to rssamplifier, everything else becomes a source here.

Input parameters:

- `collection` (string): Collection slug it belongs in, e.g. podcasts (optional; an admin decides otherwise)
- `email` (string): Where to hear back, if you are not sending a key (optional)
- `note` (string): Why it belongs here: who publishes it, what it covers (optional)
- `url` (string, required): The feed URL, starting with https://

### `search_profiles` (~272 tokens)

Search Profiles

People: one entry per person assembled from every app that serves their OpenProfile.md (podcasters from p0dcasters, public profiles from OutreachGraph). Search by name, headline or anything in the document; newest change first. Each answer carries the page, the openprofile.md URL, accounts, topics, Broadcast shows, the Guest section, and the job title, company and seniority the person published (filter on them with title, company, seniority or tags).

Input parameters:

- `company` (string): Company domain, URL or name (optional), e.g. example.com
- `limit` (integer): Rows to return, integer 1-200, default 30, e.g. 50
- `q` (string): Text to match against the name, headline and document (optional)
- `seniority` (string): Seniority derived from the title (optional)
- `since` (string): ISO 8601 time: only profiles changed after it (optional), e.g. 2026-10-01T00:00:00Z
- `tags` (array): Facet tags every result must carry: title:…, company:…, seniority:…
- `title` (string): Job title, matched as its tag (`CTO` is title:cto) (optional)

### `find_profile_by_linkedin` (~72 tokens)

Find Profile by LinkedIn

The public profile a LinkedIn profile or company URL belongs to (linkedin.com/in/… or /company/…), or null. LinkedIn only: profiles are never looked up by email.

Input parameters:

- `url` (string, required): A LinkedIn URL, e.g. https://www.linkedin.com/in/ada

### `get_profile` (~64 tokens)

Get Profile

One person by id, `<slug>-<id>` or handle: the parsed view and the OpenProfile.md as served.

Input parameters:

- `ref` (string, required): Profile id, slug-id or handle, e.g. 4821, ada-lovelace-4821 or ada

### `claim_profile` (~118 tokens)

Claim Profile

Claim a profile as the key owner (needs a key). Proven when the key owner’s email is one the profile lists, or when the person’s site or show page links back to the profile’s nichedb page. An admin may claim on behalf of an email.

Input parameters:

- `email` (string): Admins only: claim it for this email address, e.g. ada@example.com
- `ref` (string, required): Profile id, slug-id or handle, e.g. 4821, ada-lovelace-4821 or ada

### `update_profile` (~355 tokens)

Update Profile

Edit a profile you own (needs a key). Send `markdown`, a whole OpenProfile.md that replaces what you wrote before, or any of `name`, `headline`, `emoji`, `pronouns`, `web`, `identity` (key: value, null removes), `sections` (name: body, `none` removes), `handle`, `public`. What you write wins over every source and survives every re-read.

Input parameters:

- `emoji` (string): Your mark next to your name: one emoji or an OpenEmoji :shortcode:; empty removes
- `handle` (string): Your URL handle, lowercase letters, digits and dashes, e.g. ada for /c/profiles/ada
- `headline` (string): One-line headline, e.g. Founder at Example Labs
- `identity` (object): Identity keys: Kind, Emoji, Pronouns, Web, Email, Location, ...; null removes
- `markdown` (string): A complete OpenProfile.md document as Markdown, starting "# Name"
- `name` (string): Display name, e.g. Ada Lovelace
- `pronouns` (string): As you write them (she/her, they/them, any); empty removes, never inferred
- `public` (boolean): Listed and pulled by other directories
- `ref` (string, required): Profile id, slug-id or handle, e.g. 4821, ada-lovelace-4821 or ada
- `sections` (object): Section bodies by name (accounts, topics, broadcast, guest, ...); the word none removes one
- `web` (string): Your home page (Website, Homepage and Site are the same key); empty removes

### `add_source` (~146 tokens)

Add Source

Add a source: an adapter with a config, fetched on a schedule (needs a key; admins and Pro). Call list_adapters first for the fields.

Input parameters:

- `adapter` (string, required): Adapter name from list_adapters, e.g. github-releases
- `cadence_minutes` (integer): Minutes between fetches, integer 5-1440, e.g. 60
- `collection` (string): Collection slug, e.g. packages; defaults to the adapter's
- `config` (object): Adapter config fields from list_adapters, e.g. {"repo": "oven-sh/bun"}
- `name` (string): Display name, e.g. Bun releases

### `run_source` (~48 tokens)

Run Source Now

Fetch a source now instead of waiting for its schedule (needs a key; owner or admin).

Input parameters:

- `source` (string, required): Source slug, e.g. steam-new-releases (see list_sources)

### `search_tlds` (~404 tokens)

Search TLDs

Top-level domains: every label in IANA's root, with type, registry, RDAP server and each registrar's one-year register/renew/transfer price (Porkbun, Dynadot, Cloudflare, OVHcloud). Sorted by renewal by default, because the first year is a promotion. `best` is the cheapest USD price across registrars; with `registrar` it is that registrar's own price in its currency. Answers carry facet counts. `trap: true` keeps only labels that renew at 2x the first year or more.

Input parameters:

- `idn` (boolean): true: internationalised labels only; false: ASCII only
- `limit` (integer): Rows to return, integer 1-500, default 50, e.g. 100
- `manager` (string): Exact registry name, as IANA writes it (optional)
- `max_register` (number): Highest first-year price (optional)
- `max_renew` (number): Highest renewal price (optional)
- `offset` (integer): Rows to skip for paging, integer, default 0, e.g. 50
- `order` (string): Sort direction: asc or desc, e.g. desc
- `q` (string): Text in the label, its Unicode form or the registry name (optional)
- `registrar` (string): porkbun, dynadot, cloudflare, ovh (optional): only labels it sells, at its prices
- `sort` (string): renew (default), register, transfer, restore, ratio, tld, registrars, type, manager, first_seen
- `status` (string): delegated (default), removed, or all, e.g. removed
- `trap` (boolean): Only labels renewing at 2x the first year or more
- `type` (string): generic, country-code, sponsored, generic-restricted, infrastructure, test; comma separated (optional)

### `get_tld` (~76 tokens)

Get TLD

One top-level domain: type, registry, RDAP server, when it entered or left the root, every registrar price (register, renew, transfer, restore, promotions, privacy, restrictions) and its change history.

Input parameters:

- `tld` (string, required): The label, with or without the dot; Unicode or xn-- both work

### `tld_changes` (~124 tokens)

TLD Changes

Top-level domains added to or removed from IANA's root, newest first, with the IANA list version each happened in. Nobody else publishes this diff.

Input parameters:

- `change` (string): added, removed or returned (optional), e.g. added
- `limit` (integer): Rows to return, integer 1-1000, default 100, e.g. 25
- `since` (string): ISO 8601 time: only changes after it (optional), e.g. 2026-01-01T00:00:00Z

### `check_domain` (~191 tokens)

Check Domain Registration

Is a domain name registered? Asks each registry over RDAP. Give `name` as a full name (foo.watches), or a bare word with `tlds` (foo + com,dev,io), or several names comma separated. Each answer is registered (with registrar and expiry), not_registered, or unknown. not_registered means the registry holds no registration; the name may still be reserved or premium, so it is not a promise that it is for sale. unknown (no RDAP server, a timeout, a 429) is never a yes. Each answer carries the cheapest known USD price for its ending.

Input parameters:

- `name` (string, required): A full name, a bare word with tlds, or names comma separated, e.g. foo.watches or a.com,b.dev
- `tlds` (string): Endings to try a bare word under, comma separated (optional)

### `airplane_lookup` (~156 tokens)

Aircraft Lookup

An aircraft by N-number (N172SP, or 172SP), Mode S hex (A2D8E1) or flight callsign (UAL1895), or words to search the US register (Cessna 172). Answers `record` (the FAA registration: maker, model, year, seats, engines, airworthiness, status, expiry, hex; private owners are withheld) and `live` (where adsb.lol sees it now: lat, lon, altitude, speed, squawk), or `matches` for words. A foreign aircraft has no record but may be live.

Input parameters:

- `query` (string, required): N-number, hex, callsign or words, e.g. N172SP

### `satellite_lookup` (~140 tokens)

Satellite Lookup

A satellite, rocket stage or piece of debris by NORAD number (25544), international designator (1998-067A) or name. Answers `record` (GCAT: owner, country, maker, launch and reentry dates, mass, orbit, status), `tle` (latest elements from SatNOGS) and `position` (where it is over the Earth now: lat, lon, altitude km, speed, period, and how old the elements are), or `matches` for a designator or name.

Input parameters:

- `query` (string, required): NORAD number, designator or name, e.g. 25544

### `ship_lookup` (~109 tokens)

Ship Lookup

A ship or boat by MMSI (9 digits), IMO number (7 digits) or name, from open AIS (Digitraffic, northern Baltic). Answers `record` (name, type, flag, size, call sign, stated destination, last position) and `live` (position, speed, course, navigation status now, when in range), or `matches` for a name.

Input parameters:

- `query` (string, required): MMSI, IMO or name, e.g. 230629000

### `train_lookup` (~156 tokens)

Train Lookup

A train by number (Amtrak 5, VIA 1, IC 1, or a bare number) or a European station by name. Answers `record` (the stored run: operator, route, origin, destination, state, delay, last and next stop, every stop with scheduled and actual times; or a station with UIC code, coordinates and operators) and `live` (the same run rebuilt from the upstream now), or `matches` when several runs or stations fit. Amtrak and VIA Rail via Amtraker, Finland via Fintraffic, stations via Trainline (ODbL).

Input parameters:

- `query` (string, required): Train number, run id or station name, e.g. Amtrak 5

### `transit_station` (~147 tokens)

Transit Station Arrivals

Next arrivals and the timetable at a public transit station. Give `city` (nyc, boston, bay-area, chicago, london) and `station` (a station id from transit_city, or a name to match). Answers the station (lines, place, step-free), `arrivals` (line, toward, due time, minutes away; live from the agency) and `schedule` (per line and direction on weekdays, Saturday and Sunday: first and last departure, trips and busiest hour).

Input parameters:

- `city` (string, required): City slug, e.g. nyc
- `station` (string, required): Station id or name, e.g. 127 or Times Sq

### `transit_city` (~93 tokens)

City Transit Overview

A city’s public transit now: its lines, its stations (id, name, lines), the service alerts in force and, with `vehicles: true`, every vehicle position the agency publishes. Cities: nyc, boston, bay-area, chicago, london, toronto, philadelphia.

Input parameters:

- `city` (string, required): City slug, e.g. london
- `vehicles` (boolean): Include live vehicle positions

### `business_standing` (~258 tokens)

Business Standing Check

Is a business on anybody's list? Give its `name`, and any of `domain`, `state` (two letters), `number` (state entity number) and `ein`. Answers with `standing` (flagged, incomplete or clear; clear only when every list was checked and found nothing), the `findings` behind it, and each section: US Treasury OFAC sanctions (SDN and consolidated, aliases included), GLEIF LEI records, SEC EDGAR filers, state registry status (OpenCorporates) and SAM.gov exclusions when keyed, and the domain over RDAP plus Spamhaus/URIBL/SURBL/Safe Browsing when the operator enabled them. A name match is not an identity: confirm against address and identifiers.

Input parameters:

- `domain` (string): Its website or mail domain (optional)
- `ein` (string): US EIN, kept to identify it, never checked (optional)
- `name` (string): Company name, e.g. Profullstack, Inc.
- `number` (string): State entity number, e.g. 4218574 (optional)
- `state` (string): Two-letter US state it is registered in (optional), e.g. CA

### `reputation_lookup` (~271 tokens)

IP and Domain Reputation

Is an IP address or a domain on a blocklist? Give `indicator` (an IPv4/IPv6 address or a domain; a URL is reduced to its host). Answers `listed`, a rough 0-100 `score` with the `reasons` behind it, the nichedb /traffic record (addresses our own servers banned and a person approved), the abuse.ch indicators (ThreatFox, URLhaus, Feodo Tracker; a domain is checked with its parent domains), the SURBL standing of a watched domain, and live DNS blocklists in `dnsbl` (an address: Spamhaus ZEN with SBL/CSS/XBL/PBL decoded, SpamCop, PSBL, Mailspike; a domain and its parents: Spamhaus DBL, URIBL, SURBL). A domain is also resolved and each A/AAAA address is checked the same way, in `addresses` (each with `ip`, `listed`, `traffic`, `indicators`, `dnsbl`). A list whose own test entry failed is named in `unknown`, not treated as a miss. Not listed is not the same as clean.

Input parameters:

- `indicator` (string, required): An IP address or a domain, e.g. 203.0.113.9 or evil.example

### `vuln_lookup` (~311 tokens)

Vulnerability Lookup

Everything known about one vulnerability, as an OpenVuln record (a valid OSV record). Give `id`: a CVE (CVE-2026-12537), GHSA, OSV, PYSEC, GO, RUSTSEC, MAL (malicious package) or NDB (nichedb.dev write-up) id. Answers OSV fields (`aliases`, `summary`, `details`, `affected` with version ranges, `severity` vectors, `references`) and `database_specific.openvuln`: `label` (critical/high/medium/low), `fix` (`status` fixed/partial/mitigated/unfixed/unknown, first fixed `versions`, `workaround`), `exploitation` (`status` exploited-ransomware/exploited/poc-public/none-known; `kev` from CISA with added/due/ransomware, null when checked and absent; `epss` score and percentile read live from FIRST; `ai`, AI exploit benchmark tasks such as ExploitGym with `result`, where `unstated` means in the benchmark with no published result), `subject` (package, agent, campaign...), `class`, and `sources` naming where each field came from. Never contains exploit code.

Input parameters:

- `id` (string, required): A vulnerability id, e.g. CVE-2026-12537, GHSA-wpqr-6v78-jr5g, MAL-2026-18177

### `traffic_list` (~196 tokens)

Traffic Blocklist

The nichedb /traffic blocklist: IP addresses our own servers banned for exploit attempts, scanning, brute force or spam, each published only after a reviewer (a person, or riotcoder applying published rules) read the evidence and approved it. Newest approvals first. Optional `days` keeps addresses seen in the last N days, `category` one of exploit, brute-force, scanner, spam, other. Without an API key the newest 100 are returned; with one, `limit` (up to 1000) and `offset` page the whole list.

Input parameters:

- `category` (string): exploit, brute-force, scanner, spam or other (optional)
- `days` (number): Only addresses seen in the last N days (optional)
- `limit` (number): Rows to return, up to 1000 with an API key
- `offset` (number): Rows to skip, with an API key

### `redeem_code` (~81 tokens)

Redeem Credit Code

Redeem a credit code (CR-XXXX-XXXX-XXXX-XXXX) for the key owner. A code is worth days of Premium, added after any term already held. Needs a key.

Input parameters:

- `code` (string, required): The credit code, any case, dashes optional, e.g. CR-AB12-CD34-EF56-GH78

### `list_invites` (~41 tokens)

List Invites

The key owner's invites: how many are left of the quota, and each invite with its status (open, used, expired, revoked). Needs a key.

### `create_invite` (~78 tokens)

Create Invite

Make one invite link as the key owner. Invites are scarce (a few per account); when the invited person signs up, both get days of Premium. The link is returned once. Needs a key.

Input parameters:

- `note` (string): Who it is for, only the owner sees it (optional), e.g. Grace at Example Labs

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-profullstack-nichedb/nichedb#diagnostics

## Score history

- 2026-11-21: 69
- 2026-11-20: 69
- 2026-11-19: 68
- 2026-11-18: 68
- 2026-11-17: 53
- 2026-11-16: 66
- 2026-11-15: 66
- 2026-11-14: 66
- 2026-11-13: 65
- 2026-11-12: 65
- 2026-11-11: 4

## Common questions

### What is the nichedb MCP server?

nichedb is an MCP server listed in the public MCP registry as com.profullstack/nichedb. Real-time public data (nichedb.dev). This page covers its hosted endpoint (https://nichedb.dev/mcp).

### Is the nichedb MCP server safe to use?

nichedb scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the nichedb MCP server expose?

nichedb exposes 49 tools: stats, list_collections, list_adapters, list_enrichers, list_sources, and 44 more. Their descriptions and schemas cost roughly 7,786 tokens of context every time the server is loaded.

### Does the nichedb MCP server require authentication?

No. We connected to nichedb without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the nichedb MCP server still maintained?

nichedb is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the nichedb MCP server?

VerifyMCP ran 13 checks on nichedb, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://nichedb.dev/mcp
- Website: https://nichedb.dev/
- Changelog RSS feed: https://verifymcp.io/servers/com-profullstack-nichedb/nichedb.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-profullstack-nichedb/nichedb/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-profullstack-nichedb/nichedb.json
- HTML version of this page: https://verifymcp.io/servers/com-profullstack-nichedb/nichedb
