# com.skipshit/mcp (remote · mcp.skipshit.com)

People and property search for Claude and ChatGPT. Phones, emails, addresses, relatives, properties.

- Trust score: 77/100 (medium)
- Change this week: +9
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.skipshit.com`: 77/100 (this document), [markdown](https://verifymcp.io/servers/com-skipshit-mcp/mcp.md), [page](https://verifymcp.io/servers/com-skipshit-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.skipshit.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## 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 2026-08-03.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - 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.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 51/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1331 tokens (~443/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http com-skipshit-mcp https://mcp.skipshit.com/mcp
```

### Codex

```toml
[mcp_servers.com-skipshit-mcp]
url = "https://mcp.skipshit.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-skipshit-mcp --url https://mcp.skipshit.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-skipshit-mcp:
    url: "https://mcp.skipshit.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "com-skipshit-mcp": {
      "type": "http",
      "url": "https://mcp.skipshit.com/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.

### 2026-08-03 (score 77, +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.

### 2026-08-01 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 75, +6)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 69, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 68, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 67)

First indexed and scored.

## MCP tools (3)

### `search_person_or_address` (~520 tokens)

Person or Address Search

Returns contact and property records for a person (by name with city/state/zip) or by address. Billed 1 credit per non-null result; empty results are not billed. Results are trimmed per-hit summaries; expand individual records or page through full results with `get_search_history` (free).

Input parameters:

- `address` (string): Street address. Required for address-mode searches (must combine with city + state). Free-form line, no normalization needed.
- `addressRecency` (string): Filter address-based search results by how recently a person was linked to the search address. `all` = no recency filter (broadest, default when omitted); `current` = address is the subject's current…
- `city` (string): City name. Used with lastName for name-mode OR with address + state for address-mode.
- `firstName` (string): Person's first name. Optional but recommended for name-mode searches. Combines with lastName + locality (city/state/zip). Nickname expansion controlled by nicknameSearch.
- `lastName` (string): Person's last name. Required for name-mode searches (must combine with city, state, or zip).
- `middleName` (string): Person's middle name. Optional. Tightens name-mode match precision; rarely required.
- `nicknameSearch` (boolean): Controls how aggressively firstName is expanded to spelling/nickname variants. `true` (default) = broad expansion (Megan → Meagan, Meggan, Meg; Jon → John, Jonathan; Katie → Katy, Kate). `false` = na…
- `state` (string): Two-letter US state code (e.g. CA, NY, TX). Used with lastName for name-mode OR with address + city for address-mode.
- `zip` (string): 5-digit US ZIP code. Used with lastName for name-mode (combines with city/state).

Output parameters:

- `balance`
- `data`
- `error` (object)
- `meta` (object)
- `ok` (boolean)

### `expand_person_record` (~197 tokens)

Expand Person Record

Expand a person id into its full record. If you pass the searchId of a prior result that already contains the id, the record is returned free. A credit is charged only when elevating a stub id (a relative, associate, or property owner) that no prior result contains. The response meta.source reports whether the record came from cache (free) or fresh (billed).

Input parameters:

- `pid` (string, required): Person identifier from a prior result. Pass it with searchId to re-read an already-owned record free; pass it without searchId (or for a stub id no stored result contains) to elevate it into a full r…
- `searchId` (string): Optional. The searchId from a prior result that already contains this pid. When provided and the record is found in your stored results, the full record is returned free (no credit); otherwise a cred…

Output parameters:

- `balance`
- `data`
- `error` (object)
- `meta` (object)
- `ok` (boolean)

### `get_search_history` (~301 tokens)

Search History & Detail

Free detail-expander for prior results, and the way to check the current credit balance. Four call modes: (1) no args → list recent searches and return current credit balance in the response envelope (use this when the user asks how many credits they have left); (2) `searchId` → re-read trimmed envelope; (3) `searchId + pid` → full record for one hit; (4) `searchId + offset + limit` → paged slice of full records (default limit 5, max 25). Use this for follow-ups on existing results — do NOT call `search_person_or_address` again to drill in. Zero credits consumed.

Input parameters:

- `limit` (integer): Max records to return (1-25). Default depends on mode: 20 for list-mode, 5 for paged-slice mode.
- `offset` (integer): Zero-based offset for pagination. Used with limit in paged-slice mode (searchId + offset/limit).
- `pid` (string): Person identifier within a stored search. Pass with searchId to expand that one record from the stored result to its full form. Free.
- `searchId` (string): Identifier from a prior search response (meta.searchId). Pass alone to re-emit the trimmed envelope; pass with pid for full-record expansion; pass with offset/limit for paged full records. All four m…

Output parameters:

- `balance`
- `data`
- `error` (object)
- `meta` (object)
- `ok` (boolean)

## Diagnostics

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

## Score history

- 2026-08-03: 77
- 2026-08-02: 76
- 2026-08-01: 76
- 2026-07-31: 75
- 2026-07-30: 69
- 2026-07-29: 69
- 2026-07-28: 68
- 2026-07-27: 68
- 2026-07-26: 67

## Links

- Remote endpoint: https://mcp.skipshit.com/mcp
- Repository: https://github.com/jeremynashrei/skipshit
- Website: https://skipshit.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-skipshit-mcp/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-skipshit-mcp/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-skipshit-mcp/mcp