# Offendersearch (remote · mcp.offendersearch.app)

Search US sex-offender registries and criminal records, with per-source citations.

- Trust score: 74/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-26

## Components

- remote · `mcp.offendersearch.app`: 74/100 (this document), [markdown](https://verifymcp.io/servers/app-offendersearch-offendersearch/mcp.md), [page](https://verifymcp.io/servers/app-offendersearch-offendersearch/mcp)

## Channel facts

- Endpoint: `https://mcp.offendersearch.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.29.1`

## 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 2026-09-26.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 5 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 58/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2607 tokens (~521/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 90/100
  - Stability observed for 27 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.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

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

Offendersearch is a hosted endpoint at https://mcp.offendersearch.app/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 app-offendersearch-offendersearch 'https://mcp.offendersearch.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "app-offendersearch-offendersearch": {
      "url": "https://mcp.offendersearch.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "app-offendersearch-offendersearch": {
      "type": "http",
      "url": "https://mcp.offendersearch.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.app-offendersearch-offendersearch]
url = "https://mcp.offendersearch.app/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add app-offendersearch-offendersearch --url 'https://mcp.offendersearch.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  app-offendersearch-offendersearch:
    url: "https://mcp.offendersearch.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "app-offendersearch-offendersearch": {
      "Transport": "http",
      "Url": "https://mcp.offendersearch.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add app-offendersearch-offendersearch -t streamable-http -u 'https://mcp.offendersearch.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "app-offendersearch-offendersearch": {
      "type": "http",
      "url": "https://mcp.offendersearch.app/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.

### 2026-09-26 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-25 (score 73, 0)

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

### 2026-09-24 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-22 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (5)

### `search_offenders` (~1065 tokens)

Search US sex-offender registries for one person and/or location.

    Fans out across all 58 registries (or the ones named in `jurisdictions`),
    de-duplicates people across registries, scores each match, and returns the
    normalized records. Supply whatever identifiers you have — all args are
    optional but at least a name, location, or free-text `q` should be given.

    Returns a SearchResponse object (docs/openapi.yaml / FIELD-DICTIONARY.md):
      - status: 'complete' | 'partial'  (partial = a source errored, or a source
        could not be searched to completion)
      - counts: { records, sourcesQueried, sourcesIncomplete }
      - warnings: [str] — ALWAYS present, `[]` when the search ran clean
      - sourceStatus: [ { source, status, matched, fromCache, note,
        incomplete, incompleteReason } ]  per-registry outcome

    ★ READ `counts.sourcesIncomplete` BEFORE REPORTING A RESULT. Above 0, `records`
    is a LOWER BOUND: those registries could not be searched to the end, and an
    empty or short result is NOT evidence that a person is unregistered. Say so.
    `warnings[0]` states it in plain language; relay it rather than summarising it
    away.
      - records: [ Record ], each with:
          recordId, matchConfidence, matchBasis[],
          name {first, middle, last, suffix, full}, aliases[], nicknames[],
          dob, dobPrecision, age, sex, race, ethnicity, height, weight,
          eyeColor, hairColor, marks, addresses[{type,line1,city,county,state,zipcode,lat,lng}],
          offense {crime,statute,riskLevel,tier,convictionDate,...}, flags{absconder,predator},
          source {jurisdiction,registryName,recordUrl,scrapedAt,sourceUpdatedAt}, sources[],
          dobVerification, unverified
          (offenses[], stateData, images[] are populated only when extensive=true)

    Auth: uses the caller's X-API-Key (request header or OFFENDERSEARCH_API_KEY env).

Input parameters:

- `address`: Fuzzy street-address filter (every token must appear in some record address).
- `age`: Age filter, used when DOB is unknown. Matched +/-1 year for birthday drift.
- `city`: Residence city filter.
- `deadline_ms` (integer): Max time to wait, in ms (default 120000 / 2 min). Lower for a faster bounded response; partial results return status='partial'.
- `dob`: Date of birth 'YYYY-MM-DD'. Improves match precision; drives dobVerification (dob_match / year_match).
- `extensive` (boolean): If true, request extensive detail (retains offenses[], stateData, images). A light call drops them.
- `first_name`: Given name, e.g. 'John'.
- `freshness` (string): Cache/pricing tier: daily=<=24h (default), weekly=<=7d.
- `jurisdictions`: Registry codes to query (e.g. ['IL','TX']). Omit/null = ALL 58 registries. See get_registry_coverage for codes.
- `last_name`: Surname — the primary match key, e.g. 'Smith'.
- `lat`: Latitude for a GIS radius search (pair with lng).
- `lng`: Longitude for a GIS radius search (pair with lat).
- `location_scoped` (boolean): OPT-IN ONLY, and never inferred from `state`. If true AND a state is set, run only the registries covering that state instead of all 58. It is a cost knob that COSTS RECALL: anyone registered by anot…
- `match` (string): Fuzzy tolerance: strict=exact; balanced=nicknames/variants/initials/typos on first name, exact last; broad=also prefix/typo on last name.
- `q`: Free-text search across name/alias/address/city/state/zip (all tokens must appear).
- `radius_miles`: GIS radius in miles around lat/lng. Defaults to 1 when a point is given; capped at 100.
- `state`: 2-letter state/territory code (e.g. 'IL', 'PR'), or the full name. A residence FILTER — it does NOT change which registries run; all 58 are still searched. It filters as a UNION: a record is kept whe…
- `zipcode`: Residence ZIP (first 5 digits used).

### `batch_search` (~376 tokens)

Run many person/location lookups in one call (row-in / row-out).

    Each row goes through the SAME engine as search_offenders, so a row's records
    are identical to what a single search would return. A row that fails is
    reported with status='error' in place and never aborts the batch. Max 1000 rows.

    Returns: { count, results: [ { index, status, counts{records,sourcesQueried,
    sourcesIncomplete}, warnings: [str], records: [Record], error? } ] } in input
    order. ★ A row with `counts.sourcesIncomplete > 0` could not be searched to the
    end — its `records` are a LOWER BOUND, not a clean 'no match'.

    Auth: uses the caller's X-API-Key (request header or OFFENDERSEARCH_API_KEY env).

Input parameters:

- `extensive` (boolean): Request extensive detail (offenses[], stateData, images) for every row.
- `freshness` (string): Cache/pricing tier applied to every row: daily=<=24h (default), weekly=<=7d.
- `jurisdictions`: Registry codes applied to EVERY row (e.g. ['FL','TX']). Omit = all 58 registries.
- `location_scoped` (boolean): Apply per-state scoping to every row (see search_offenders).
- `match` (string): Fuzzy tolerance applied to every row (see search_offenders).
- `queries` (array, required): List of query objects (max 1000). Each may set any of: firstName, lastName, dob (YYYY-MM-DD), age, city, state, zipcode, address, lat, lng, radiusMiles, q. One row in = one result out, in input order.

### `get_registry_coverage` (~336 tokens)

List every registry we cover plus its scope, legal status, and health.

    Public coverage catalog (no API key required). Use it to discover the
    `jurisdictions` codes accepted by search_offenders / batch_search and to
    check per-registry freshness/health before relying on a result.

    Returns: { count, registries: [ SourceInfo ] } where each SourceInfo is:
      - id: registry code (e.g. 'IL', 'TX', 'PR')
      - name: human-readable registry name
      - covers: [state codes] a registry covers ('*' = national / all)
      - scope: 'state' | 'national'
      - status: 'live' | 'building'
      - legal: { commercialUse: 'allowed'|'restricted'|'prohibited'|'unknown' }
      - health: { lastSuccessAt, typicalLatencyMs, ageSeconds, freshFor }

    `health` is OPERATIONAL COVERAGE METADATA about our ingest schedule, published
    for transparency. It is NOT a quality warning about a search result: a search
    serves every registry's best available data regardless of `freshFor`, so a
    registry listing only 'weekly' still contributes its records to a
    freshness='daily' search. Do NOT tell a user their search results are stale,
    unreliable or out of date on the basis of these fields — they are not. The only
    completeness signal that belongs in an answer is `counts.sourcesIncomplete` /
    `warnings[]` from the search response itself.

### `search_criminal` (~509 tokens)

Search US criminal records — county jail bookings, state prison custody, court cases and warrants.

    Covers county jail rosters, statewide prison systems, court sources, warrant
    systems and statewide registries across the states, DC and the territories,
    plus the federal layer — which is a separate system holding offences no state
    search will surface.

    A surname is REQUIRED. Supply firstName and a DOB or birth year wherever you
    have them: a bare common surname returns thousands of people, and the scoring
    cannot tell you which one is yours.

    Each record carries `recordType`, and YOU MUST READ IT BEFORE CHARACTERISING
    ANYONE:
      - a jail booking is an ARREST-stage record — charges at booking are
        frequently reduced, dismissed, or never filed. It is NOT a conviction.
      - prison custody implies a sentence, and therefore a conviction.
      - a court record carries the DISPOSITION — the authoritative statement of
        how a case actually ended.
      - a warrant means the person is SOUGHT. Nothing has been tested.
    Never describe someone as convicted on the strength of a booking record.

    Records also carry: name, aliases, dob/birthYear/dobPrecision, sex, race,
    state, county, custody status and facility, sentence and parole detail,
    `cases`, `sources` (per-source citation), and `matchConfidence`/`matchBasis`
    explaining why it matched. `counts.records` is the total found and
    `counts.recordsReturned` the number in this page.

    Not a consumer report: results must not be used for FCRA-covered decisions
    (employment, tenancy, credit) without appropriate process.

Input parameters:

- `age`: Approximate current age, when neither DOB nor birth year is known.
- `birthYear`: Birth year alone, when a full DOB is unknown.
- `county`: County name, to narrow within a state.
- `dob`: Date of birth, YYYY-MM-DD. The single strongest disambiguator.
- `firstName`: Given name. Strongly recommended: a bare common surname returns thousands.
- `lastName` (string, required): REQUIRED surname. The criminal corpus refuses an unbounded query — a name is the field that cannot be enumerated.
- `limit`: Max records to return. Default 50.
- `state`: 2-letter state code (e.g. 'TX'). Narrows to that state's jurisdictions.

### `get_criminal_coverage` (~138 tokens)

List the criminal-record jurisdictions searched, with kind and status.

    Use it to discover which states and counties are reachable and which are
    answering today, before relying on an empty result. Depth is uneven by design:
    counties publish independently, so a state with many county jurisdictions is
    not "better covered" than one that publishes a single statewide source — it is
    differently structured.

    Returns the jurisdiction roster; each entry carries its code, the state it
    belongs to, the kind of records it holds (jail / prison / court / warrant /
    registry) and whether it is currently answering.

## Diagnostics

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

## Score history

- 2026-09-26: 74
- 2026-09-25: 73
- 2026-09-24: 73
- 2026-09-23: 72
- 2026-09-22: 72
- 2026-09-21: 71
- 2026-09-20: 71
- 2026-09-19: 71
- 2026-09-18: 70
- 2026-09-17: 70
- 2026-09-16: 69
- 2026-09-15: 69
- 2026-09-14: 68
- 2026-09-13: 68
- 2026-09-12: 67
- 2026-09-11: 67
- 2026-09-10: 66
- 2026-09-09: 66
- 2026-09-08: 65
- 2026-09-07: 65
- 2026-09-06: 64
- 2026-09-05: 64
- 2026-09-04: 64
- 2026-09-03: 63
- 2026-09-02: 63
- 2026-09-01: 62
- 2026-08-31: 62
- 2026-08-30: 61

## Common questions

### What is the Offendersearch MCP server?

Offendersearch is an MCP server listed in the public MCP registry as app.offendersearch/offendersearch. Search US sex-offender registries and criminal records, with per-source citations. This page covers its hosted endpoint (https://mcp.offendersearch.app/mcp).

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

Offendersearch scores 74 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 Offendersearch MCP server expose?

Offendersearch exposes 5 tools: search_offenders, batch_search, get_registry_coverage, search_criminal, get_criminal_coverage. Their descriptions and schemas cost roughly 2,424 tokens of context every time the server is loaded.

### Does the Offendersearch MCP server require authentication?

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

### Is the Offendersearch MCP server still maintained?

Offendersearch is still listed as active in the MCP registry. We last reached this channel on 26 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.offendersearch.app/mcp
- Repository: https://github.com/Clavaa/offendersearch-quickstart
- Website: https://offendersearch.app/
- Changelog RSS feed: https://verifymcp.io/servers/app-offendersearch-offendersearch/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/app-offendersearch-offendersearch/mcp.json
- HTML version of this page: https://verifymcp.io/servers/app-offendersearch-offendersearch/mcp