Skip to main content
Glama
ProjectMakersDE

horizOn MCP Server

Official
by ProjectMakersDE
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Create Group

horizon_create_group
Idempotent

Creates a server-identified group and its leader atomically after the player confirms settings, using the current revision to prevent duplicate creation on replay.

Instructions

Creates a fresh server-identified group and its leader atomically. Use when: the player explicitly confirms the group settings. Not for: choosing/reusing a group ID or resending uncertain writes with a new revision. Requires: userId and the player's session: sign in with horizon_signin_email or horizon_signin_anonymous and pass its accessToken as sessionToken. The current MyGroupsView revision. Side effects: Creates one group and membership within both limits. The retained player revision prevents duplicate creation on replay. Returns: {groups:MyGroupsView,group:GroupView|null}. groups is the actor's complete snapshot, never the target's private state. group is null after leave/delete; nonmembers never receive private data. Replace only the matching host/project/player cache. Errors: Use horizon_get_groups and horizon_get_group_pending to reconcile state. 409 REVISION_CONFLICT or uncertain response: read and reconcile intent, never refresh the revision and repeat automatically. Pending decisions require the original requestId; REQUEST_NOT_FOUND means it was removed/replaced. INBOX_FULL rolls back the entire action. 403 rejects group role, session or bilateral block violations. 429 is reported without automatic retry. 401 means the session is missing or expired: sign in again and retry with the new accessToken. 403 for a session means the token belongs to another user: pass the userId that signed in. Needs HORIZON_API_KEY. Every failure returns an error result (isError) with the HTTP status and body: a 401 that horizon_test_connection also returns means HORIZON_API_KEY is wrong, 429 means the account's per-minute rate limit was reached (wait a minute, then retry).

Input Schema

NameRequiredDescriptionDefault
dataYesRequired finite JSON object; current maxDataBytes/maxDataDepth are server policies. Client JSON bytes can differ from stored dataJson after number normalization; the server validates the complete stored representation. No default2048-byte/depth16 clamp. Only members/admins can read it.
nameYesNonblank display name under current maxNameBytes; server enforces the complete BSON envelope
userIdYesSigned-in player matching the Bearer session
joinModeYesWhether players join directly, request admission or need an invitation
descriptionYesPublic description under current maxDescriptionBytes
sessionTokenYesPlayer accessToken, sent only in Authorization
expectedPlayerRevisionYesExact reviewed revision; never replace automatically after an uncertain response

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.9.1

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations: requires prior sign-in via horizon_signin_email/anonymous and passing accessToken as sessionToken, explains that the retained player revision prevents duplicate creation on replay (consistent with idempotentHint), specifies that INBOX_FULL rolls back the entire action, that 403 covers bilateral block violations, and that 429 must not be auto-retried. This is exactly the extra context annotations cannot express.

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?

Well front-loaded with labelled Use when / Not for / Requires / Side effects / Returns / Errors sections. It is on the long side and repeats the 'never refresh the revision and repeat automatically' instruction twice (in the Not-for line and the Errors block), which is redundant rather than harmful.

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?

No output schema exists, and the description compensates by documenting the return shape ({groups, group}), the null-group case after leave/delete, the privacy boundary on private state, and which cache entries to replace. For a mutating, 7-param, nested-object tool, nothing an agent needs to call it safely 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 baseline is 3. The description adds a small amount of genuine value: it names where expectedPlayerRevision comes from (the current MyGroupsView revision) and clarifies that userId must match the signed-in Bearer session. It does not elaborate on joinMode or data, which the schema handles.

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?

States a specific verb and resource ('Creates a fresh server-identified group and its leader atomically') and the atomicity constraint distinguishes it from horizon_update_group and horizon_join_group. An agent knows exactly what this call produces without opening the 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?

Explicit 'Use when' (player confirms group settings) and 'Not for' (choosing/reusing a group ID, resending uncertain writes with a new revision) sections, plus named alternatives (horizon_get_groups, horizon_get_group_pending) for reconciliation. This routing guidance is unusually complete.

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

Deploy Server

Other Tools