Skip to main content
Glama

Open Sanctions

by io.github.pipeworx-io

Search Entities

search_entities
Read-onlyIdempotent

Search global sanctions, watchlists, and PEP (politically exposed persons) databases. Returns matched entities with names, countries, datasets, and sanctions details. Example: search_entities("Vladimir Putin") or search_entities("Huawei", schema="Company"). Requires your own OpenSanctions API key, passed as _apiKey.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesName or keyword to search (e.g., "Gazprom", "Kim Jong")
schemaNoEntity type: "Person", "Company", "Organization", "Vessel", "Aircraft"
_apiKeyYesYour own OpenSanctions API key (BYO — Pipeworx does not supply one; OpenSanctions is a commercial service). Get one at opensanctions.org/api — free for non-commercial use, paid for commercial. For a keyless US sanctions/export-control screen, use the sanctions-screening pack (sanctions_screen) instead.
countriesNoComma-separated country codes (e.g., "ru,cn,ir")

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesThe search query string provided
totalYesTotal number of matching entities
entitiesYesFormatted entity objects
returnedYesNumber of entities in this response

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is known. The description adds valuable non-obvious context: the API key requirement, the global data scope, and the returned fields. No contradictions with annotations.

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?

Four sentences with no waste: core action, return contents, concrete examples, and the critical key requirement. Every sentence earns its place, and the most important scoping information is front-loaded.

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?

Given the full schema documentation and read-only annotations, the description covers the essential requirements: scope, return fields, authentication, and a keyless alternative. It does not mention pagination, result limits, or sorting, but the presence of an output schema softens that gap.

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?

Schema description coverage is 100%, with each parameter having a meaningful description (query, schema entity types, countries format, and _apiKey explanation). The description's examples show valid combinations but do not add meaning beyond the schema. Baseline of 3 applies.

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 names a specific verb (Search) and a precise resource (global sanctions, watchlists, and PEP databases), then lists return fields (names, countries, datasets, sanctions details). The examples with 'Vladimir Putin' and 'Huawei' make the scope immediately concrete and distinguish it from generic entity lookups.

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 makes the when-to-use context clear: searching global sanctions/PEP data with a user-supplied OpenSanctions key. It explicitly gives a when-not and alternative in the _apiKey parameter: for keyless US screening, use sanctions_screen. However, it does not contrast with sibling tools like get_entity, compare_entities, or resolve_entity.

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

All Open Sanctions 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

A3.6/5.0
Disambiguation2/5

Multiple tools have overlapping purposes, especially the ask_pipeworx variants (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, bet_research) which all serve to query data but with subtle differences. An agent would struggle to distinguish which to use without deep understanding of their nuances.

Naming Consistency3/5

Most tool names follow a verb_noun or noun_noun pattern in snake_case, but there are exceptions like 'forget', 'recall', 'remember' which are single verbs, and names like 'ask_pipeworx' mix verb and proper noun. Overall pattern is discernible but not uniform.

Tool Count2/5

33 tools is high for a server named 'Open Sanctions' which implies a focused domain. The tool set spans sanctions, meta-querying, prediction markets, memory, subscriptions, and more, making it feel bloated and unfocused relative to the server's name.

Completeness2/5

For a sanctions server, only two tools (search_entities, get_entity) directly address the domain, missing obvious operations like update, delete, or list. Many tools are unrelated to sanctions, leaving the core domain incomplete.

Resources