Skip to main content
Glama

Shodan

by io.github.pipeworx-io

Shodan Host Search

shodan_host_search
Read-onlyIdempotent

Search Shodan for hosts matching using Shodan search syntax (e.g. "apache country:US", "port:22 org:"Google""). Returns matching hosts with IP, port, org, hostnames, product, and location. Example: shodan_host_search({ query: "apache country:US", _apiKey: "your-key" })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoResult page number (optional, 100 results/page, default 1)
queryYesShodan search query. Supports filters like country:, org:, port:, product:, os:, e.g. "apache country:US"
_apiKeyYesShodan API key (account.shodan.io; paid membership required)

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds that the tool returns specific fields (IP, port, org, etc.) and uses Shodan syntax, providing additional context beyond annotations without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise: two sentences plus an example call. It front-loads the purpose and includes a practical example, with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description mentions returned fields and pagination (via page parameter). Without an output schema, it provides enough information for typical use. It could mention that 100 results per page is the default, which is already in the schema but not in the description. Still, it is mostly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for all three parameters (query, page, _apiKey), so the baseline is 3. The description adds example usage but does not significantly extend the schema definitions. Score meets baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it searches Shodan for hosts matching a query, provides example syntax, and lists returned fields (IP, port, etc.). This distinguishes it from siblings like 'shodan_host_count' and 'shodan_host' (single IP lookup).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes example queries and Shodan search syntax, aiding usage. However, it does not explicitly state when to use this tool versus alternatives like 'shodan_host_count' or 'shodan_host', which would be helpful. Implicit guidance is sufficient but not explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Shodan toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.5/5.0
Disambiguation2/5

The server name 'Shodan' misleadingly implies a narrow focus on network security scanning, yet the tool set includes many unrelated tools for data lookup (ask_pipeworx, deep_research, etc.), memory management, and subscriptions. Within the pipeworx tools, there is overlap between ask_pipeworx, ask_pipeworx_grounded, and deep_research, which can confuse agents about which to choose.

Naming Consistency2/5

Tool names mix conventions: some use underscores (ai_visibility_check, shodan_host), others use lowercased phrases without clear partitioning (ask_pipeworx, deep_research, entity_profile). Verb-noun patterns are inconsistent (e.g., 'scan_competitor_ai_presence' vs 'compare_entities'). This lack of a predictable naming scheme increases cognitive load.

Tool Count2/5

With 33 tools covering distinct domains (Shodan scanning, pipeworx data, memory, subscriptions), the server feels overloaded and unfocused. While each tool may individually be useful, the bundling contradicts the principle of a single-purpose server. A more appropriate count for a focused Shodan server would be under 10 tools.

Completeness2/5

For the Shodan domain, only three tools are provided (host, host_count, host_search), missing key capabilities like DNS lookups, vulnerability search, or API key management. The pipeworx tool set is extensive but not the server's advertised purpose, leaving gaps in both areas. The addition of memory and subscription tools adds unrelated functionality without completing any single domain.

Resources