@shieldlabs-ai/mcp

Official

by ShieldLabs-ai

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

Search history

shieldlabs_search_history

Read-onlyIdempotent

Retrieve individual ShieldLabs identifications by user, device, visitor, IP, session, or cookie, newest first, with paging for account and device investigations.

Instructions

List identifications for one identifier from the ShieldLabs History API, newest first, with paging.

Use it to see individual identifications of an account (user_hid), a device (device_id), a browser visitor (visitor_id), a cookie (cookie_id), a visit (session_id) or an IPv4 address (ip). For counts and aggregates over many identifications, prefer shieldlabs_summarize_entity.

Args:

type ('request_id' | 'user_hid' | 'device_id' | 'visitor_id' | 'ip' | 'session_id' | 'cookie_id')
value (string): UUID for the ID types, dotted IPv4 for ip, exact User HID for user_hid
limit (number): 1-100, default 20
offset (number): default 0
response_format ('markdown' | 'json'): default 'markdown'

Returns (json): { "lookup": { type, value }, "total": number, "count": number, "offset": number, "limit": number, "has_more": boolean, "next_offset": number (only when has_more), "identifications": [same shape as shieldlabs_get_identification], "untrusted_data_note": string, "truncated"?: boolean, "truncation_message"?: string }

Examples:

Every identification of one account: type="user_hid", value=""
Which accounts used this device: type="device_id", value=""
Next page: repeat with offset=next_offset

Errors: invalid values are refused before any request (UUID or IPv4 expected; IPv6 is not searchable; a User HID that contains "/" cannot be searched). 401 means a wrong key; 429 means the History API rate limit (about 15 requests per second per domain) was reached.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`type`	Yes	Identifier to search by: request_id (one identification), user_hid (one of your accounts, exact and case-sensitive), device_id (one device), visitor_id (one browser visitor), ip (IPv4 only), session_id (one visit) or cookie_id (one browser profile)
`limit`	No	Identifications per page, from 1 to 100 (default 20)
`value`	Yes	Identifier value: a UUID for request_id, device_id, visitor_id, session_id and cookie_id; a dotted IPv4 address such as 203.0.113.24 for ip; the exact User HID string for user_hid ("anonymous" lists anonymous checks; a User HID that contains "/" cannot be searched)
`offset`	No	Number of identifications to skip, for paging (default 0). Use next_offset from the previous page.
`response_format`	No	Output format: 'markdown' (default) for readable text, 'json' for structured data	markdown

Output Schema

TableJSON Schema

Name	Required	Description
`count`	Yes	Identifications in this response
`limit`	Yes
`total`	Yes	Identifications matching the lookup
`lookup`	Yes
`offset`	Yes
`has_more`	Yes
`truncated`	No
`next_offset`	No
`identifications`	Yes
`truncation_message`	No
`untrusted_data_note`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Oct 5, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/openWorld/destructive=false, and the description goes well beyond them: pre-request validation refusal, IPv6 not searchable, User HIDs containing '/' unsearchable, 401 = wrong key, and a concrete 429 rate limit (~15 req/s per domain). It also flags that results contain untrusted data via untrusted_data_note and possible truncation.

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

Conciseness4/5

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

Front-loaded with the purpose and the routing decision, then organized into Args/Returns/Examples/Errors sections that are each useful. It is on the long side and the Args block overlaps the schema, but no section is padding.

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

Completeness5/5

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

Despite an output schema existing, the description adds the paging contract (next_offset, has_more) and error semantics an agent needs to drive the loop correctly. For a 5-parameter, enum-heavy search tool, nothing material is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description's Args block largely restates the schema but does reinforce value formats and adds concrete examples (type="user_hid", type="device_id", reusing offset=next_offset), which clarifies how the parameters combine in practice.

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 opening sentence states a specific verb (list), resource (identifications for one identifier from the History API), ordering (newest first), and paging behavior. It explicitly distinguishes itself from the sibling shieldlabs_summarize_entity, so an agent can route between the two without opening a schema.

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

Usage Guidelines5/5

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

It names exactly when to use this tool (individual identifications of an account, device, visitor, cookie, visit or IP) and when to prefer the alternative (counts and aggregates over many identifications -> shieldlabs_summarize_entity). Worked examples cover the three main call patterns, including how to page.

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

Deploy Server