Skip to main content
Glama
ProjectMakersDE

horizOn MCP Server

Official
by ProjectMakersDE
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Send Original Chat Message

horizon_send_chat_message
DestructiveIdempotent

Sends a plain-text chat message for an explicit hosted chat action and can replay the exact original operation using its saved identifiers and text.

Instructions

Sends plain text once or explicitly replays the exact original operation. Use when: explicit hosted chat actions after reading horizon://docs/chat. Not for: automatic sends, repeated polling, rich-text rendering or exposing moderation credentials. Use horizon_get_chat_operation to reconcile original sends, then horizon_send_chat_message only for the explicit identical replay. Requires: userId and the player's session: sign in with horizon_signin_email or horizon_signin_anonymous and pass its accessToken as sessionToken. Side effects: One HTTP attempt. Persist project+player operationId/issuedAt/channel/full text before sending. The original live message provides its receipt; replay never recreates expired/deleted text. Direct/group windows are15 messages/30seconds, project windows20/seven days. A monotone player time fence rejects unknown older sends; no per-player message/receipt copy. Returns: {receipt,replayed,serverTime} Errors: 404 hides private/missing/expired channels or source messages. 409 OPERATION_CONFLICT/OPERATION_EXPIRED or STATE_CONFLICT requires explicit original-intent reconciliation. Never replace an unknown send UUID/time/text. 429 does not schedule a retry. CHAT_MUTED/CHAT_BANNED restrict current chat access. 501 NOT_SUPPORTED means simpleServer has no chat or polling fallback. 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
textYesExact original plain text, never silently rewritten
userIdYesActive player matching the current session and project
issuedAtYesOriginal canonical timestamp including .SSSZ; never replace issuedAt on retry
channelIdYesOriginal canonical lowercase UUID
operationIdYesOriginal canonical lowercase UUID
sessionTokenYesPlayer accessToken sent only as Bearer

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 annotations: one HTTP attempt, mandatory persistence of operationId/issuedAt/channel/text before sending, per-window rate limits, monotone player time fence, no per-player message copy, and replay never recreating expired text. Error semantics (404, 409, 429, 501, 401, 403) and the isError result contract are also disclosed. This is consistent with idempotentHint and destructiveHint.

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 and sectioned (Use when/Not for/Requires/Side effects/Returns/Errors), with little filler. It is very dense and repeats 429 handling in two places ("does not schedule a retry" vs "wait a minute, then retry"), which mildly muddies the otherwise disciplined structure.

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 a destructive, open-world mutation with no output schema, the description supplies return shape ({receipt,replayed,serverTime}), auth prerequisites, side effects, rate limits, and error handling. An agent has enough to call it correctly and interpret failures.

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, but the description adds real meaning: sessionToken must be the accessToken from horizon_signin_email/anonymous, userId must match the signed-in player, and operationId/issuedAt/text are the immutable original-send identity never to be replaced. That linkage to auth and replay semantics exceeds the schema text.

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 ("Sends plain text once or explicitly replays the exact original operation") and distinguishes the two modes. Naming horizon_get_chat_operation as the reconciliation path separates it from siblings clearly.

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" and "Not for" sections name automatic sends, polling, rich-text rendering, and credential exposure as exclusions. It also names horizon_get_chat_operation and the signin tools as alternatives, leaving little inference.

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