# Agent Bookability Index (remote · index.therunup.ai)

NYC-area event vendor prices, areas and booking options, each sourced from the vendor's own site.

- Trust score: 77/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `index.therunup.ai`: 77/100 (this document), [markdown](https://verifymcp.io/servers/ai-therunup-index-agent-bookability-index/index.md), [page](https://verifymcp.io/servers/ai-therunup-index-agent-bookability-index/index)

## Channel facts

- Endpoint: `https://index.therunup.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.10`

## 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**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 76/100
  - 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 2369 tokens (~236/item across 10 items; 9 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 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 Agent Bookability Index MCP server?

Agent Bookability Index is a hosted endpoint at https://index.therunup.ai/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 ai-therunup-index-agent-bookability-index 'https://index.therunup.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-therunup-index-agent-bookability-index": {
      "url": "https://index.therunup.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-therunup-index-agent-bookability-index": {
      "type": "http",
      "url": "https://index.therunup.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-therunup-index-agent-bookability-index]
url = "https://index.therunup.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-therunup-index-agent-bookability-index": {
      "type": "remote",
      "url": "https://index.therunup.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-therunup-index-agent-bookability-index --url 'https://index.therunup.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-therunup-index-agent-bookability-index:
    url: "https://index.therunup.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-therunup-index-agent-bookability-index": {
      "Transport": "http",
      "Url": "https://index.therunup.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-therunup-index-agent-bookability-index -t streamable-http -u 'https://index.therunup.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-therunup-index-agent-bookability-index": {
      "type": "http",
      "url": "https://index.therunup.ai/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.

### 2026-11-21 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 75, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “estimate_event_budget” rewrote its description, which is the text the model reads
- [security] Tool “get_price_summary” rewrote its description, which is the text the model reads
- [security] Tool “shortlist_vendors” rewrote its description, which is the text the model reads
- [functional] Schema quality: excellent → good

### 2026-11-16 (score 75, +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.

### 2026-11-15 (score 74, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “fetch” rewrote its description, which is the text the model reads
- [security] Tool “get_price_summary” rewrote its description, which is the text the model reads
- [security] Tool “get_vendor” rewrote its description, which is the text the model reads
- [security] Tool “list_categories” rewrote its description, which is the text the model reads
- [security] Tool “search” rewrote its description, which is the text the model reads
- [security] Tool “search_vendors” rewrote its description, which is the text the model reads
- [security] Tool “shortlist_vendors” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 151 → 232
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: good → excellent
- [functional] Server version: 0.2.1 → 0.3.11
- [functional] Server version: 0.2.0 → 0.2.1
- [functional] New tool “estimate_event_budget”
- [cosmetic] “search_vendors” added an optional parameter “needs”
- [cosmetic] “search_vendors” added an optional parameter “offset”
- [cosmetic] “search_vendors” added an optional parameter “sort”
- [cosmetic] “shortlist_vendors” added an optional parameter “guests”
- [cosmetic] “shortlist_vendors” added an optional parameter “hours”
- [cosmetic] “shortlist_vendors” added an optional parameter “needs”
- [cosmetic] “get_price_summary” reworded the description of “area”
- [cosmetic] “search_vendors” reworded the description of “area”
- [cosmetic] “shortlist_vendors” reworded the description of “area”

### 2026-11-14 (score 74)

First indexed and scored.

## MCP tools (9)

### `list_categories` (~72 tokens)

List vendor categories

What the index covers: the vendor categories with how many vendors each has, how many publish a price and
the median published starting price for a whole event; the areas, event types and needs (kosher, MC,
lighting...) the other tools accept. Call it first if you are unsure what the index covers.

Output parameters:

- `areas` (array)
- `as_of`
- `categories` (array)
- `cite_as` (string)
- `event_types` (array)
- `needs` (array): Values the needs parameter accepts.

### `search_vendors` (~519 tokens)

Search vendors

Find New York area event vendors, in one category or across all, filtered by area, event type, maximum
published price, online booking or part of a name. Sorted by bookability score (how much an AI agent can
learn and do on the vendor's own site), then price. Each result has the starting price and what it covers,
how to book, and the index page to cite. For a ready shortlist across several categories, use
shortlist_vendors; search is the id-only variant for ChatGPT.

Input parameters:

- `area`: Optional area: NYC (any of the five boroughs), Manhattan, Brooklyn, Queens, Bronx, Staten Island, Long Island, Westchester, North Jersey or Central Jersey, or New Jersey for both; a county or town al…
- `books_online` (boolean): Only vendors whose own site shows online booking.
- `category`: Vendor category in plain words ("DJ", "wedding photographer", "florist"). Omit to search every category.
- `event_type`: Optional event type in plain words: "wedding", "bar mitzvah", "sweet 16", "birthday", "corporate holiday party", "baby shower".
- `has_price` (boolean): Only vendors that publish a price.
- `limit` (integer): How many vendors to return, 1 to 25 (larger values are capped).
- `max_price_usd`: Only vendors whose published starting price is at or under this, in US dollars.
- `name_contains`: Part of the vendor's name.
- `needs`: Optional things the vendor must offer, as its own website states: "kosher", "halal" (caterers), "MC", "lighting", "photo booth" (DJs, bands), "second shooter" (photographers), "second videographer",…
- `offset` (integer): How many matches to skip, to page through a long list: pass next_offset from the previous result.
- `sort` (string): "score" (default: most bookable first, then price) or "price" (lowest published starting price first, vendors without a price last; check starting_price.per, as a per-hour or per-guest rate is not a…

Output parameters:

- `area`
- `category`
- `cite_as` (string)
- `list_page` (string): The index page listing these vendors.
- `matched` (integer): How many vendors matched before the limit.
- `next_offset`: Pass this as offset to get the next page; None when there is no more.
- `note` (string)
- `offset` (integer): How many matches were skipped before these.
- `shown` (integer)
- `vendors` (array)

### `shortlist_vendors` (~464 tokens)

Shortlist vendors for an event

A shortlist for one event: for each service asked for, the most bookable New York area vendors that serve
the area and event type. Ranked by how directly a consumer can act (book online, instant quote or open
dates, quote form), then by fit with the budget, bookability score and price. Pass guests and hours to get each
vendor's published rate worked out for the event (estimate). Use it to answer "help me find a DJ, caterer and
florist for a 120-guest bar mitzvah in Brooklyn, 4 hours, under $3,000 each".

Input parameters:

- `area`: Optional area: NYC (any of the five boroughs), Manhattan, Brooklyn, Queens, Bronx, Staten Island, Long Island, Westchester, North Jersey or Central Jersey, or New Jersey for both; a county or town al…
- `budget_usd`: Optional budget per service, US dollars. Vendors whose published starting price fits come first.
- `categories` (array, required): The services needed, in plain words, e.g. ["DJ", "photographer", "florist"]. Up to 6.
- `event_type`: Optional event type in plain words: "wedding", "bar mitzvah", "sweet 16", "birthday", "corporate holiday party", "baby shower".
- `guests`: Optional number of guests. Per-guest prices (catering, cakes) are worked out for this many.
- `hours`: Optional length of the event in hours. Per-hour prices (some DJs, photographers, bands) are worked out for this long.
- `needs`: Optional things the vendor must offer, as its own website states: "kosher", "halal" (caterers), "MC", "lighting", "photo booth" (DJs, bands), "second shooter" (photographers), "second videographer",…
- `per_category` (integer): Vendors per service, 1 to 10.

Output parameters:

- `area`
- `budget_usd`
- `cite_as` (string)
- `event_type`
- `groups` (array)
- `guests`
- `hours`
- `how_ranked` (string)

### `get_vendor` (~141 tokens)

Get one vendor

Everything the index knows about one vendor: category, areas, bookability score, website, how to book,
and every published fact (starting price and what it covers, packages, deposit, booking lead time,
cancellation policy and more), each with the quote from the vendor's own site, its page and the date read.
If a name matches several vendors, the error lists them with their index_page. (fetch returns the same facts
as text, for ids that came from search.)

Input parameters:

- `vendor` (string, required): The vendor's name (or part of it), its index_page URL from another tool, or its slug such as "448-studio".

Output parameters:

- `areas` (array)
- `category` (string)
- `checked`
- `cite_as` (string)
- `facts` (object): Every published fact, by name (starting_price, packages, deposit...).
- `how_to_book`
- `index_page` (string)
- `name` (string)
- `price_from_usd`
- `score` (integer)
- `website`

### `compare_vendors` (~88 tokens)

Compare vendors

Two to five vendors side by side: starting price and what it covers, areas, event types, deposit, booking
lead time, cancellation policy and how to book, with every fact's source. Use it when a consumer is choosing
between vendors from a search or shortlist.

Input parameters:

- `vendors` (array, required): 2 to 5 vendors, each a name, index_page URL or slug.

Output parameters:

- `cite_as` (string)
- `side_by_side` (array): One row per vendor with the facts most used to choose.
- `vendors` (array)

### `get_price_summary` (~238 tokens)

Price summary for a service

One service's price. What New York area vendors in one category publish as a starting price for a whole event: the median and
the middle half (25th to 75th percentile), from how many vendors and when, optionally for one area, plus
per-hour or per-guest figures where the category is priced that way. Comes with a one-sentence summary
and the page to cite. Use it to answer "how much does a wedding DJ cost in Brooklyn".

Input parameters:

- `area`: Optional area: NYC (any of the five boroughs), Manhattan, Brooklyn, Queens, Bronx, Staten Island, Long Island, Westchester, North Jersey or Central Jersey, or New Jersey for both; a county or town al…
- `category` (string, required): Vendor category in plain words: "photographers", "DJ", "caterer", "florist", "planner", "live band", "videographer", "photo booth", "hair and makeup" or "cakes". list_categories gives the full list.

Output parameters:

- `area`
- `area_note`: Set when the area had too few prices and the whole region is used.
- `as_of`
- `category` (string)
- `cite_as` (string)
- `cost_pages` (array): More specific index pages answering what this costs (wedding, per hour, per guest), each with a one-sentence summary.
- `high_quartile` (number)
- `low_quartile` (number)
- `median` (number)
- `per_unit` (array)
- `sentence` (string): One sentence that states the figures with their source.
- `source` (string)
- `unit`
- `vendors` (integer): How many vendors' published prices the figures come from.

### `estimate_event_budget` (~264 tokens)

Budget for an event

Several services together. The published starting prices of a whole event's vendors: for each service, the low, median and high published
starting price in the area, worked out for the guests and hours given, and the sum. Use it to answer "what
will a DJ, photographer and caterer cost for a 120-guest bar mitzvah in Brooklyn". For one service in
detail use get_price_summary; for actual vendors use shortlist_vendors.

Input parameters:

- `area`: Optional area: NYC (any of the five boroughs), Manhattan, Brooklyn, Queens, Bronx, Staten Island, Long Island, Westchester, North Jersey or Central Jersey, or New Jersey for both; a county or town al…
- `categories` (array, required): The services the event needs, in plain words, e.g. ["DJ", "photographer", "caterer", "cake"]. Up to 8.
- `guests`: Number of guests. Catering and cakes, usually priced per guest, are worked out for this many.
- `hours`: Length of the event in hours. Where a service has per-hour prices, they are worked out for this long.

Output parameters:

- `area`
- `as_of`
- `cite_as` (string)
- `guests`
- `hours`
- `notes` (array)
- `sentence` (string): One sentence that states the total with its source.
- `services` (array)
- `total_high_usd` (number): Sum of each service's 75th percentile: a rough high end.
- `total_low_usd` (number): Sum of each service's 25th percentile: a rough low end, not a quote.
- `total_median_usd` (number)

### `search` (~142 tokens)

Search the index (ChatGPT-compatible)

For ChatGPT connectors and deep research only; other clients use search_vendors. Free-text search in the id-only shape they require: returns ids,
titles and URLs of vendors, price summaries and cost pages, to open with fetch. Words for a service, an area, an
event type and a dollar amount narrow the results. Other clients get full results in one call from
search_vendors (structured filters, vendor cards) or get_price_summary (what a service costs).

Input parameters:

- `query` (string, required): What to look for in plain words, e.g. "wedding DJ Brooklyn under 2000" or "how much does a florist cost in Queens".

Output parameters:

- `results` (array)

### `fetch` (~116 tokens)

Fetch a result (ChatGPT-compatible)

For ChatGPT connectors and deep research only; other clients use get_vendor. Opens one id returned by search (a vendor, a price summary or a cost page) as plain text with the URL to
cite, in the shape ChatGPT expects. To look up a vendor by name, URL or slug without searching first, use
get_vendor, which returns the same facts as structured fields.

Input parameters:

- `id` (string, required): An id from search, e.g. "vendor:448-studio" or "price:djs:brooklyn".

Output parameters:

- `id` (string)
- `metadata` (object)
- `text` (string)
- `title` (string)
- `url` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-therunup-index-agent-bookability-index/index#diagnostics

## Score history

- 2026-11-21: 77
- 2026-11-20: 76
- 2026-11-19: 76
- 2026-11-18: 76
- 2026-11-17: 75
- 2026-11-16: 75
- 2026-11-15: 74
- 2026-11-14: 74

## Common questions

### What is the Agent Bookability Index MCP server?

Agent Bookability Index is an MCP server listed in the public MCP registry as ai.therunup.index/agent-bookability-index. NYC-area event vendor prices, areas and booking options, each sourced from the vendor's own site. This page covers its hosted endpoint (https://index.therunup.ai/mcp).

### Is the Agent Bookability Index MCP server safe to use?

Agent Bookability Index scores 77 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 Agent Bookability Index MCP server expose?

Agent Bookability Index exposes 9 tools: list_categories, search_vendors, shortlist_vendors, get_vendor, compare_vendors, and 4 more. Their descriptions and schemas cost roughly 2,044 tokens of context every time the server is loaded.

### Does the Agent Bookability Index MCP server require authentication?

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

### Is the Agent Bookability Index MCP server still maintained?

Agent Bookability Index 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 Agent Bookability Index MCP server?

VerifyMCP ran 13 checks on Agent Bookability Index, 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://index.therunup.ai/mcp
- Website: https://index.therunup.ai/agents/
- Changelog RSS feed: https://verifymcp.io/servers/ai-therunup-index-agent-bookability-index/index.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-therunup-index-agent-bookability-index/index/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ai-therunup-index-agent-bookability-index/index.json
- HTML version of this page: https://verifymcp.io/servers/ai-therunup-index-agent-bookability-index/index
