Horizon MCP Server

horizon_login

Authenticate to Horizon with AD credentials to obtain access and refresh tokens and update the server's active token, so subsequent API calls work without re-entering credentials.

Instructions

Authenticate to Horizon and return access and refresh tokens.

The access_token is valid for ~8 hours. The refresh_token can be used with horizon_refresh_token to obtain a new access_token without re-entering credentials.

This tool also updates the running server's active token so subsequent tool calls work immediately without restarting the server.

SECURITY: Copy the returned access_token to your MCP client config (HORIZON_ACCESS_TOKEN env var), then clear it from the conversation. Treat both tokens as passwords — do not share or log them.

Input Schema

TableJSON Schema

Name	Required	Description
`domain`	Yes	AD domain name, e.g. CORP or corp.example.com
`base_url`	No	Horizon server URL, e.g. https://horizon.corp.example.com. Defaults to HORIZON_BASE_URL env var if not provided.
`password`	Yes	AD password — masked in logs and server-side traces
`username`	Yes	AD username (without domain prefix)

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 10, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations provided, the description carries the full behavioral burden. It discloses a meaningful side effect (updating the running server's active token), token validity duration, and security requirements for handling tokens. This is strong transparency for an authentication tool.

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 well-structured: purpose first, then token behavior, side effect, and security guidance. Every sentence adds useful information and there is no filler.

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?

For an authentication tool with an output schema, the description covers what the agent needs: token lifetimes, refresh path, active-token side effect, and security handling. It is complete enough to call the tool correctly and manage the resulting credentials.

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%, and the schema already describes each parameter including base_url's default behavior. The description does not add new parameter-level meaning, so the baseline score 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 uses a specific verb ('Authenticate') and resource ('Horizon') and clearly states the return of access and refresh tokens. It also differentiates itself from the sibling horizon_refresh_token by explaining that the refresh token is used there.

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 explains when to use horizon_refresh_token instead of re-entering credentials, which provides alternative guidance. It does not explicitly state when not to call horizon_login, but the refresh-token flow is clear enough that an agent can infer the intended lifecycle.

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

Deploy Server