Cmf Chile

Cmf Registry

cmf_registry

Read-onlyIdempotent

Look up a legal entity in the CMF registers by RUT or name. Returns (1) supervised-entity register hits: CMF code, name, entity type and whether the registration is current; and (2) the register of financial service providers created by Chile's Fintec law, with the services each provider is authorised for (crowdfunding platform, alternative trading system, credit advice, investment advice, custody, order routing, intermediation) and status. RUT may be written 77.532.023-0 or 77532023. An absent entity returns found:false with the scope searched, which means 'not in these registers', not 'does not exist'. Natural persons are never returned.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "Abaqus"
    },
    "name": "cmf_registry"
  }
}

Input Schema

Name	Required	Description	Default
`rut`	No	Chilean RUT of the entity, e.g. "77.532.023-0".
`name`	No	Entity name or part of it, e.g. "Abaqus".

Output Schema

Name	Required	Description	Default
`found`	No
`query`	No
`source`	No
`data_as_of`	No
`scope_searched`	No
`supervised_entities`	No
`financial_service_providers`	No
`withheld_natural_person_rows`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 26, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavioral context on top: what each of the two registers contributes, that no match returns found:false with the scope searched, and the crucial caveat that absence means 'not in these registers' rather than 'does not exist'. The natural-persons exclusion is another non-obvious scoping rule the agent could not derive from structured fields.

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 purpose, then results, then format and caveat; every sentence carries information an agent needs. The parenthesized service-type enumeration is long but is the only place that vocabulary is defined, so it earns its space.

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?

An output schema exists, so the return-value detail is bonus rather than obligation, and the description still adds the null-result interpretation and scope limits. The remaining gap is invocation mechanics: no statement that one of rut/name must be supplied, and no note on name-match fuzziness or result limits.

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 coverage is 100%, so the baseline is 3, and the description adds one genuinely useful detail beyond the schema example: RUT may be written with or without separators. However, both parameters are optional and the description never says whether they are ANDed, ORed, or that at least one is required, nor how partial name matching behaves – a meaningful gap in parameter semantics.

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

Purpose4/5

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

Names a specific verb and resource ("look up a legal entity in the CMF registers by RUT or name") and enumerates both result sets with their fields, so the agent knows exactly what comes back. It does not explicitly distinguish itself from siblings like cmf_regulation, cmf_sanctions or company_register_search, which an agent would have to infer from the register names alone.

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?

Gives clear selection context (search by RUT or by name), the accepted RUT formats, and an explicit exclusion: natural persons are never returned, so a person lookup is out of scope. It stops short of naming an alternative tool for company-register or sanctions lookups, so routing against siblings is left to inference.

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

All Cmf Chile tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.