Skip to content
Botscope logo

Botscope MCP server

Which MCP servers are Botscope's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-13

← Back to Botscope

Whose server it is
  • Addresshttps://mcp.botscope.io/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on botscope.io when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools13
  • Server calls itselfbotscope
  • Server version1.3.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 534 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • set_agent_policy change data without a sign-in: anyone with the address can call them.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer261 ms
  • Space in an agent's context≈ 2,404 tokensthe definitions of all its tools (13), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 13 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · classify and block malicious bots while observing AI agents
  • not sure · detect fake conversions and scrapers corrupting analytics data
  • not sure · track which AI assistants cite your pages and send traffic

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that change data, on a server that answers without a sign-in: set_agent_policy

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers13 tools · read 2026-10-27
  • lookup_crawler

    Returns the catalogue record of a known bot by slug: operator, category, how it can be verified, its default policy and the URL of its record. Use when the user asks about a specific bot by name or slug.

  • search_crawlers

    Searches the catalogue of known bots by name, slug, operator or robots.txt token, optionally filtered by category or operator. Returns up to 15 records. Use when a bot name is ambiguous or the user asks which bots an operator runs.

  • identify_crawler

    Matches a User-Agent string against the catalogue and, when an IP is given, checks it against the cached published IP ranges of the matched record. Does not perform reverse DNS or signature checks. Use when the user has a User-Agent…

  • robots_policy

    Builds a robots.txt fragment from the catalogue for one intent: block_training (disallow AI training crawlers, allow search engines), block_all_ai (disallow all AI agent categories, allow search engines) or catalog_defaults (each bot per…

  • list_sites

    Lists the sites the signed-in user can access in their account: id, name, domain and whether the site is in observe or enforce mode. Use when the user asks about their own site and its id is not known yet.

  • traffic_summary

    Returns aggregated traffic for one of the user's sites over 1 to 28 days: bot versus human share, traffic categories, number of distinct agents, top AI vendors and the top agents with hit counts. No IP addresses or visitor data. Use when…

  • list_agent_hits

    Lists the agents that reached one of the user's sites over 1 to 28 days, up to 25, each with hit count, share, change against the previous period and the site's effective policy for it. Use when the user asks how specific agents are…

  • get_agent_policy

    Returns the policy one of the user's sites applies to one catalogue agent: catalogue default, effective action, whether the catalogue pins it, the site mode and the matching robots.txt directive. Use when the user asks what policy is set…

  • get_site_robots_txt

    Returns how the robots.txt generated for one of the user's sites is composed: counts of agents per action, the site mode and an ETag. The file text is included only when include_body is true. Use when the user asks about their site's…

  • list_alerts

    Lists the traffic, crawler-access and Site Checks incidents of one of the user's sites, newest first, up to 25: what happened, severity, the hours it covers, observed against usual values, the crawlers or checks involved and whether it is…

  • site_checks

    Returns the latest nightly Site Checks of one of the user's sites: for each check (data arriving, search crawlers not refused, AI crawler access, robots.txt and sitemap readable by automated clients, visitor addresses reaching the…

  • acknowledge_alert

    Marks one alert on one of the user's sites as acknowledged, as the Acknowledge button on the Alerts page does. It does not resolve, snooze or delete the alert, and acknowledging an already acknowledged alert changes nothing. Use when the…

  • set_agent_policy

    Sets the policy for one catalogue agent on one of the user's sites to allow, observe, challenge or block. Changes one agent on one site per call and is recorded in the site audit log. Does not change the site mode, rules or bans. Returns…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "botscope": {
      "type": "http",
      "url": "https://mcp.botscope.io/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http botscope https://mcp.botscope.io/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.botscope.io/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.