# BotThru (remote · botthru.com)

Free no-auth agent tools: URL to markdown, DNS/RDAP, URL & MCP checks, FX, holidays, embed, rerank.

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

## Components

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

## Channel facts

- Endpoint: `https://botthru.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## 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**: 63/100
  - 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 1 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.
  - 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**: 79/100
  - 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 3726 tokens (~133/item across 28 items; 26 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 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 26 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 28 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 BotThru MCP server?

BotThru is a hosted endpoint at https://botthru.com/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-botthru-drive-thru 'https://botthru.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-botthru-drive-thru": {
      "url": "https://botthru.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-botthru-drive-thru": {
      "type": "http",
      "url": "https://botthru.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-botthru-drive-thru]
url = "https://botthru.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-botthru-drive-thru --url 'https://botthru.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-botthru-drive-thru:
    url: "https://botthru.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-botthru-drive-thru": {
      "Transport": "http",
      "Url": "https://botthru.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-botthru-drive-thru -t streamable-http -u 'https://botthru.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-botthru-drive-thru": {
      "type": "http",
      "url": "https://botthru.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.

### 2026-11-20 (score 69, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “holidays” rewrote its description, which is the text the model reads
- [security] Tool “ask” rewrote its description, which is the text the model reads
- [security] Tool “audit_page” rewrote its description, which is the text the model reads
- [security] Tool “calculate” rewrote its description, which is the text the model reads
- [security] Tool “check_http_security” rewrote its description, which is the text the model reads
- [security] Tool “check_mcp_security” rewrote its description, which is the text the model reads
- [security] Tool “check_mcp_server” rewrote its description, which is the text the model reads
- [security] Tool “check_url” rewrote its description, which is the text the model reads
- [security] Tool “date_math” rewrote its description, which is the text the model reads
- [security] Tool “dns_lookup” rewrote its description, which is the text the model reads
- [security] Tool “echo” rewrote its description, which is the text the model reads
- [security] Tool “embed” rewrote its description, which is the text the model reads
- [security] Tool “exchange_rate” rewrote its description, which is the text the model reads
- [security] Tool “extract_page_data” rewrote its description, which is the text the model reads
- [security] Tool “fetch_page” rewrote its description, which is the text the model reads
- [security] Tool “page_speed” rewrote its description, which is the text the model reads
- [security] Tool “rdap_lookup” rewrote its description, which is the text the model reads
- [security] Tool “read_url” rewrote its description, which is the text the model reads
- [security] Tool “rerank” rewrote its description, which is the text the model reads
- [security] Tool “scan_secrets” rewrote its description, which is the text the model reads
- [security] Tool “site_discovery” rewrote its description, which is the text the model reads
- [security] Tool “time” rewrote its description, which is the text the model reads
- [security] Tool “time_convert” rewrote its description, which is the text the model reads
- [security] Tool “uuid” rewrote its description, which is the text the model reads
- [security] Tool “weather” rewrote its description, which is the text the model reads
- [security] Tool “whoami” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail

### 2026-11-19 (score 69, +8)

- [security improvement] HSTS header: fail → pass
- [security improvement] HTTPS: fail → pass
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “ask” rewrote its description, which is the text the model reads
- [security] Tool “site_discovery” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 91 → 101
- [functional improvement] Tool coverage: 86% → 100%
- [functional improvement] Tool coverage: 75% → 100%
- [functional improvement] Tool “ask” now declares an output schema
- [functional improvement] Tool “echo” now declares an output schema
- [functional improvement] Tool “time” now declares an output schema
- [functional improvement] Tool “uuid” now declares an output schema
- [functional improvement] Tool “whoami” now declares an output schema
- [functional] The server now declares the “resources” capability
- [functional] New resource “llms.txt”
- [functional] New resource “tool-catalog”
- [functional] New tool “audit_page”
- [functional] New tool “check_http_security”
- [functional] New tool “check_mcp_security”
- [functional] New tool “page_speed”
- [functional] New tool “scan_secrets”
- [functional] New tool “weather”
- [cosmetic] “date_math” reworded the description of “add_business_days”
- [cosmetic] “date_math” reworded the description of “add_days”
- [cosmetic] “date_math” reworded the description of “add_hours”
- [cosmetic] “date_math” reworded the description of “subtract_business_days”
- [cosmetic] “date_math” reworded the description of “subtract_days”
- [cosmetic] “date_math” reworded the description of “subtract_hours”

### 2026-11-18 (score 61, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 81 → 91
- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “calculate”
- [functional] New tool “extract_page_data”

### 2026-11-17 (score 61)

First indexed and scored.

## MCP tools (26)

### `read_url` (~135 tokens)

Read URL

Read a public http(s) URL as markdown. Uses text/markdown when the server sends it, otherwise Workers AI toMarkdown with images off (no neurons), then a local HTML stripper. Respects robots.txt for BotThruFetcher. Does not cache or store the page. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `max_chars` (integer): Maximum characters of markdown. Default 20000, maximum 100000.
- `url` (string, required): Public http or https URL. No private addresses, no credentials.

Output parameters:

- `approx_tokens` (integer)
- `content_signal` (string)
- `content_type` (string)
- `error` (string)
- `final_url` (string)
- `markdown` (string)
- `ok` (boolean)
- `status` (integer)
- `title` (string)
- `truncated` (boolean)

### `calculate` (~129 tokens)

Calculate

Arithmetic, scientific functions, percentages, and unit conversion. No network and no eval. expression is at most 500 characters. precision is 1 to 34 significant digits, default 15. An unknown symbol returns the supported unit list. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `expression` (string, required): Math expression or '<number> <unit> to <unit>'. At most 500 characters.
- `precision` (integer): Significant digits from 1 to 34. Default 15.

Output parameters:

- `error` (string)
- `normalized_expression` (string)
- `ok` (boolean)
- `result` (string)
- `result_number` (number)
- `supported_units` (array)
- `unit` (string)
- `warnings` (array)

### `extract_page_data` (~178 tokens)

Extract page data

Fetch one public HTML page and return title, meta, Open Graph, JSON-LD, links, headings, feeds, and tables. Same SSRF guard and per-network limit as read_url. Cached 10 minutes by final URL. Does not store the page. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `include` (string): Comma-separated: meta, opengraph, jsonld, links, headings, tables, feeds. Default is all except tables.
- `max_links` (integer): 1 to 200. Default 100.
- `max_tables` (integer): 1 to 5. Default 5.
- `url` (string, required): Public http or https URL. No private addresses, no credentials.

Output parameters:

- `feeds` (array)
- `final_url` (string)
- `headings` (array)
- `jsonld` (array)
- `links` (array)
- `meta` (object)
- `ok` (boolean)
- `opengraph` (object)
- `status` (integer)
- `tables` (array)
- `truncated` (object)

### `site_discovery` (~106 tokens)

Site discovery

Fetch a site's agent-facing files (robots.txt, llms.txt, sitemap, well-known MCP and agent cards, AI Catalog, ARD, OpenAPI, security.txt) and say what was found. Does not change the site. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `domain_or_url` (string, required): Domain or http(s) URL, for example example.com.

Output parameters:

- `files` (array)
- `ok` (boolean)
- `origin` (string)

### `check_url` (~90 tokens)

Check URL

Request a public URL and report status, final URL, latency, content type, size, TLS, and a few response headers. Does not follow into private networks. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `url` (string, required): Public http or https URL. No private addresses, no credentials.

Output parameters:

- `content_type` (string)
- `error` (string)
- `final_url` (string)
- `headers` (object)
- `latency_ms` (integer)
- `message` (string)
- `ok` (boolean)
- `size` (integer)
- `status` (integer)
- `tls_ok` (boolean)

### `check_mcp_server` (~96 tokens)

Check MCP server

Connect to a remote streamable-HTTP MCP server: initialize, notifications/initialized, and tools/list. Also lists prompts or resources when advertised. Never calls the remote server's tools. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `url` (string, required): Remote MCP endpoint, for example https://example.com/mcp.

Output parameters:

- `auth_required` (boolean)
- `capabilities` (object)
- `errors` (array)
- `latency_ms` (integer)
- `ok` (boolean)
- `protocol_version` (string)
- `server_info` (object)
- `tools` (array)

### `check_http_security` (~136 tokens)

Check HTTP security

Grade the security headers of one public URL. One GET, plus a single check that HTTP redirects to HTTPS. Scores HSTS, CSP, nosniff, framing, referrer policy, permissions policy, cookie flags, CORS wildcard with credentials, and server version leaks. Returns an A–F grade, one sentence, and findings with a fix. Read-only. No fuzzing. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `url` (string, required): Public http or https URL. No private addresses, no credentials.

Output parameters:

- `error` (string)
- `findings` (array)
- `grade` (string|null)
- `message` (string)
- `ok` (boolean)
- `score` (integer|null)
- `suggestions` (array)
- `summary` (string)

### `scan_secrets` (~155 tokens)

Scan secrets

Scan pasted text (up to 200KB) or one public page or script for leaked credentials: AWS, GitHub, OpenAI, Anthropic, Stripe, Google, Slack, a Supabase service_role JWT, private keys, and high-entropy secret assignments. Matches are redacted to the first 4 and last 2 characters and are not stored. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `text` (string): Text to scan, up to 200000 characters. Do not send this with url.
- `url` (string): One public page or script. Do not send this with text.

Output parameters:

- `error` (string)
- `findings` (array)
- `grade` (string|null)
- `message` (string)
- `ok` (boolean)
- `score` (integer|null)
- `suggestions` (array)
- `summary` (string)

### `check_mcp_security` (~141 tokens)

Check MCP security

Connect to a remote MCP server over Streamable HTTP, run initialize and tools/list, and never call a tool. Flags missing TLS, prompt injection in tool text, hidden Unicode, lookalike tool names, shell or file-write tools, destructive tools without auth, and CORS *. Returns an A–F grade and findings with a fix. If initialize is not JSON-RPC, there is no grade. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `url` (string, required): Remote MCP endpoint, for example https://example.com/mcp.

Output parameters:

- `error` (string)
- `findings` (array)
- `grade` (string|null)
- `message` (string)
- `ok` (boolean)
- `score` (integer|null)
- `suggestions` (array)
- `summary` (string)

### `audit_page` (~107 tokens)

Audit page

Audit a live web page in one call: grade A-F for security headers, SEO meta and agent-readiness, with the top fixes. AI Catalog, ARD, and a WebMCP script reference are noted and do not change the grade. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `url` (string, required): Public http or https URL. No private addresses, no credentials.

Output parameters:

- `final_url` (string)
- `fixes` (array)
- `grade` (string)
- `ok` (boolean)
- `score` (integer)
- `sections` (object)
- `status` (integer)
- `verdict` (string)

### `page_speed` (~176 tokens)

Page speed

Lab speed estimate for one public page from a server-side fetch. Reports TTFB, total fetch time, HTML size, content-encoding, Cache-Control, ETag, CDN cache headers, the redirect chain, render-blocking scripts and stylesheets in head, images missing width/height or loading=lazy, preconnect and preload counts, and third-party origins. HEADs up to 10 subresources for sizes. Returns an A–F grade, a score, and the top fixes with expected impact. This is not Core Web Vitals field data and it does not call Google. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `url` (string, required): Public http or https URL. No private addresses, no credentials.

Output parameters:

- `applied` (object)
- `disclaimer` (string)
- `error` (string)
- `facts` (object)
- `field_data` (boolean)
- `final_url` (string)
- `fixes` (array)
- `grade` (string|null)
- `lab_estimate` (boolean)
- `ok` (boolean)
- `score` (integer|null)
- `summary` (string)

### `dns_lookup` (~139 tokens)

DNS lookup

Look up a hostname via Cloudflare DNS (A, AAAA, CNAME, MX, TXT, NS, CAA, SOA). type email_auth returns MX, SPF, DMARC, and the DNSSEC AD flag. Does not connect to the name. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `name` (string, required): Hostname. No scheme or path.
- `type` (string): A, AAAA, CNAME, MX, TXT, NS, CAA, SOA, or email_auth. Default A.

Output parameters:

- `answers` (array)
- `dnssec_ad` (boolean)
- `name` (string)
- `ok` (boolean)
- `rcode` (string)
- `type` (string)

### `rdap_lookup` (~162 tokens)

RDAP lookup

Registration data for a domain (IANA bootstrap, then the registry RDAP server), or an IP or ASN via rdap.org with RIPEstat as fallback. Returns registrar, dates, status, and nameservers or the network name, country, and holder. No contact emails or street addresses. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `asn` (string): ASN, for example AS13335.
- `domain` (string): Domain name, for example example.com.
- `ip` (string): IPv4 or IPv6 address.
- `query` (string): A domain, IP, or ASN when the kind is not given separately.

Output parameters:

- `kind` (string)
- `nameservers` (array)
- `ok` (boolean)
- `query` (string)
- `registrar` (string)
- `status` (array)

### `time_convert` (~114 tokens)

Convert time

Convert a civil time from one IANA time zone to another using Intl. Does not call the network. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `from_tz` (string, required): IANA time zone the time is in.
- `time` (string, required): YYYY-MM-DDTHH:mm in from_tz, or an ISO timestamp.
- `to_tz` (string, required): IANA time zone to convert to.

Output parameters:

- `from` (object)
- `ok` (boolean)
- `to` (object)
- `utc` (string)

### `date_math` (~199 tokens)

Date math

Add or subtract days, hours, or business days (Monday to Friday, holidays not skipped), or diff two dates. Intl and UTC calendar dates only. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `add_business_days` (number): Monday-to-Friday days to add. Holidays are not skipped.
- `add_days` (number): Calendar days to add. Negative values move backward.
- `add_hours` (number): Hours to add. Negative values move backward.
- `date` (string, required): YYYY-MM-DD or an ISO timestamp.
- `diff` (string): Second date. Returns days, hours, and business days between them.
- `subtract_business_days` (number): Monday-to-Friday days to subtract. Holidays are not skipped.
- `subtract_days` (number): Calendar days to subtract.
- `subtract_hours` (number): Hours to subtract.

Output parameters:

- `diff` (object)
- `ok` (boolean)
- `result` (string)

### `holidays` (~102 tokens)

Public holidays

Public holidays for a country and year from date.nager.at. Cached for 24 hours. Returns date, name, and local name. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `country_code` (string, required): ISO country code, for example US, or a common country name.
- `year` (integer): Calendar year. Defaults to the current UTC year.

Output parameters:

- `country` (string)
- `holidays` (array)
- `ok` (boolean)
- `year` (integer)

### `exchange_rate` (~124 tokens)

Exchange rate

Fiat exchange rate from Frankfurter (ECB). No crypto. Cached for 1 hour. amount is converted locally. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `amount` (number): Amount in from. Default 1.
- `date` (string): YYYY-MM-DD. Omit for the latest rate.
- `from` (string, required): 3-letter fiat code, for example USD.
- `to` (string, required): 3-letter fiat code, for example EUR.

Output parameters:

- `converted` (number)
- `date` (string)
- `ok` (boolean)
- `rate` (number)

### `weather` (~242 tokens)

Weather

Current conditions and a 1 to 7 day forecast from Open-Meteo. Pass place (a city name, geocoded) or latitude and longitude. days defaults to 3. units is metric or imperial. The result starts with one plain-language sentence, then current and daily data. Every result includes attribution: Weather data by Open-Meteo.com (CC BY 4.0). Identical requests are cached for 10 minutes. Free for non-commercial use under 10k calls a day. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `days` (integer): Forecast length from 1 to 7, counting today. Default 3.
- `latitude` (number): Decimal degrees. Required with longitude when place is omitted. Coordinates win when both are sent.
- `longitude` (number): Decimal degrees. Required with latitude when place is omitted.
- `place` (string): City name, geocoded by Open-Meteo. Use this or latitude and longitude.
- `units` (string): metric or imperial. Default metric.

Output parameters:

- `attribution` (string)
- `current` (object)
- `daily` (array)
- `error` (string)
- `ok` (boolean)
- `summary` (string)

### `embed` (~139 tokens)

Embed text

Embed up to 32 strings (8000 characters each) with Workers AI. Default model @cf/baai/bge-m3. Also @cf/google/embeddinggemma-300m. Stops with budget_exhausted before it can use the neurons reserved for /v1/ask. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `model` (string): Optional. @cf/baai/bge-m3 or @cf/google/embeddinggemma-300m.
- `texts` (array, required): 1 to 32 strings.

Output parameters:

- `budget_remaining` (number)
- `embeddings` (array)
- `error` (string)
- `estimated_neurons` (number)
- `model` (string)
- `ok` (boolean)

### `rerank` (~105 tokens)

Rerank documents

Score up to 32 documents against a query with @cf/baai/bge-reranker-base. Returns indexes and scores, not a rewritten answer. Same daily neuron guard as embed. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `documents` (array, required): 1 to 32 documents.
- `query` (string, required): The question, max 8000 characters.

Output parameters:

- `budget_remaining` (number)
- `error` (string)
- `estimated_neurons` (number)
- `ok` (boolean)
- `results` (array)

### `fetch_page` (~106 tokens)

Fetch page

Alias of read_url. Same markdown result, including title, final URL, status, approx_tokens, and any Content-Signal header. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `max_chars` (integer): Maximum characters of text. Default 20000, maximum 100000.
- `url` (string, required): Public http or https URL. No private addresses, no credentials.

Output parameters:

- `approx_tokens` (integer)
- `content_signal` (string)
- `content_type` (string)
- `error` (string)
- `final_url` (string)
- `markdown` (string)
- `ok` (boolean)
- `status` (integer)
- `title` (string)
- `truncated` (boolean)

### `ask` (~145 tokens)

Ask

Order window. need is required. status is answered only when a BotThru tool ran, routed when Workers AI wrote a pointer and the task was not done, unsupported when the need was only logged, note when the message is an operator note, onboarding probe, verification notice, or a liveness or echo probe (the reply is OK). Do not send secrets or personal data. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `agent` (string): Optional name of the calling agent.
- `need` (string, required): What you need. Do not include secrets or personal data.

Output parameters:

- `answer` (string)
- `error` (string)
- `id` (string)
- `ok` (boolean)
- `status` (string)

### `time` (~79 tokens)

Current time

Current UTC time, plus the same instant in an IANA time zone. Defaults to UTC. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Input parameters:

- `timezone` (string): IANA time zone, for example America/New_York. Omit for UTC.

Output parameters:

- `error` (string)
- `local` (string)
- `ok` (boolean)
- `timezone` (string)
- `utc` (string)

### `uuid` (~45 tokens)

UUID

One random UUID (crypto.randomUUID). Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Output parameters:

- `uuid` (string)

### `echo` (~57 tokens)

Echo request

Headers, country, and bot classification of this HTTP request. Cookie and authorization values are redacted. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Output parameters:

- `bot` (object)
- `colo` (string|null)
- `country` (string|null)
- `method` (string)
- `path` (string)

### `whoami` (~50 tokens)

Who am I

Which bot BotThru thinks is calling, and why. Call anytime: POST https://botthru.com/mcp tools/call, or POST https://botthru.com/a2a message/send.

Output parameters:

- `bot` (object)
- `user_agent` (string|null)

## Diagnostics

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

## Score history

- 2026-11-21: 69
- 2026-11-20: 69
- 2026-11-19: 69
- 2026-11-18: 61
- 2026-11-17: 61

## Common questions

### What is the BotThru MCP server?

BotThru is an MCP server listed in the public MCP registry as com.botthru/drive-thru. Free no-auth agent tools: URL to markdown, DNS/RDAP, URL & MCP checks, FX, holidays, embed, rerank. This page covers its hosted endpoint (https://botthru.com/mcp).

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

BotThru 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 BotThru MCP server expose?

BotThru exposes 26 tools: read_url, calculate, extract_page_data, site_discovery, check_url, and 21 more. Their descriptions and schemas cost roughly 3,257 tokens of context every time the server is loaded.

### Does the BotThru MCP server require authentication?

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

### Is the BotThru MCP server still maintained?

BotThru 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 BotThru MCP server?

VerifyMCP ran 12 checks on BotThru, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about BotThru: Authorization. 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://botthru.com/mcp
- Website: https://botthru.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-botthru-drive-thru/botthru.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-botthru-drive-thru/botthru/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-botthru-drive-thru/botthru.json
- HTML version of this page: https://verifymcp.io/servers/com-botthru-drive-thru/botthru
