Skip to main content
Glama
FirstReply MCP Server

FirstReply MCP Server

Official
by FirstReply

Channel Create

channel_create

Creates a channel for email, webchat, Telegram, Bluesky, or app store connections with settings and credentials, verified before saving and ready for onboarding support conversations.

Instructions

Create a channel that is set up with settings or credentials: EMAIL, WEBCHAT, BLUESKY, TELEGRAM, APPSTORE, PLAYSTORE (website chat needs none; the result carries the webchatKey of its embed snippet). Pass the fields of that type. Accounts that are connected by signing in (MESSENGER, INSTAGRAM, LINKEDIN, WHATSAPP, THREADS, X, TIKTOK, YOUTUBE, GOOGLE_BUSINESS, MASTODON) are started with channel_connect instead. FirstReply checks the credentials with the platform before it saves. Needs manager rights and a free channel in the plan (organization_usage).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "organizationId": "<organizationId>",
      "type": "<type>",
      "name": "<name>"
    },
    "name": "channel_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesName of the channel as the team sees it.
typeYesThe channel type.
emailSslNoEMAIL: connect with SSL/TLS.
emailHostNoEMAIL: mail server host name, e.g. mail.example.com.
emailPortNoEMAIL: SMTP port, e.g. 465 or 587.
commentModeNoSocial accounts: which comments on posts become conversations. ALL, QUESTIONS (emoji-only and off-topic comments are closed quietly) or NONE.
telegramChatNoTELEGRAM: the Telegram channel the bot posts to (@name, a t.me link or the id); the bot has to be an administrator of it. Optional: without it the channel only receives messages to the bot.
webchatColorNoWEBCHAT: accent color as hex, e.g. #2563eb.
webchatThemeNoWEBCHAT: widget theme.
webchatTitleNoWEBCHAT: title shown in the widget.
appstoreAppIdNoAPPSTORE: the app's Apple ID (the number in its App Store link).
appstoreKeyIdNoAPPSTORE: key id of the App Store Connect API key.
blueskyHandleNoBLUESKY: the account's handle, e.g. example.bsky.social.
emailPasswordNoEMAIL: the mailbox password. Stored encrypted, never returned.
emailPortImapNoEMAIL: IMAP port, e.g. 993.
emailUsernameNoEMAIL: the mailbox address, which is also the login.
organizationIdYesThe organization id. Use organization_list to find it.
appstoreAppNameNoAPPSTORE: the app's name.
webchatPositionNoWEBCHAT: side of the page the launcher sits on.
appstoreIssuerIdNoAPPSTORE: issuer id of the App Store Connect API key.
commentAutoReplyNoSocial accounts: send AI replies to comments right away instead of keeping them as drafts.
telegramBotTokenNoTELEGRAM: the token of the bot from @BotFather. Stored encrypted.
publishingEnabledNoSocial accounts: let posts be published to this channel (post_schedule). Counts against the plan's publishing limit; the channel has to be allowed to publish (publishingAuthorized, see channel_connect).
appstorePrivateKeyNoAPPSTORE: content of the .p8 private key file. Stored encrypted.
blueskyAppPasswordNoBLUESKY: an app password (Bluesky settings, Privacy and security, App passwords), never the account password. Stored encrypted.
playstorePackageNameNoPLAYSTORE: the app's package name, e.g. com.example.app. The organization's service account (channel_playstore_service_account) has to be invited in the Play Console first.
webchatLauncherLabelNoWEBCHAT: text next to the launcher button.
webchatAllowedDomainsNoWEBCHAT: comma-separated domains the widget may be embedded on. Empty allows every site.
webchatRequireContactNoWEBCHAT: ask visitors for name and email before they can write.
webchatWelcomeMessageNoWEBCHAT: first message visitors see.
playstoreApplicationNameNoPLAYSTORE: the app's name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.3.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already flag openWorldHint=true and readOnlyHint=false, but the description adds real behavior beyond them: FirstReply validates credentials against the remote platform before saving, manager rights and plan capacity are enforced, and the WEBCHAT result carries a webchatKey. It stops short of covering failure/partial-save behavior or what happens if validation fails.

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 the core action and type list, then alternatives, then validation and permission notes. Every sentence carries information, though the parentheticals make the opening sentence dense.

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?

For a 31-parameter creation tool with no output schema and no annotation detail on authorization, the description covers type routing, credential validation, permission gating, and the one notable return value (webchatKey). Remaining gap is error handling on failed credential checks.

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 schema already documents all 31 parameters with type-prefixed labels (EMAIL:, WEBCHAT:, APPSTORE:). The description adds the organizing rule 'Pass the fields of that type' and notes website chat needs no credentials, but contributes no format or syntax detail beyond the schema.

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 (Create) plus resource (channel) and enumerates the six supported types (EMAIL, WEBCHAT, BLUESKY, TELEGRAM, APPSTORE, PLAYSTORE), making it immediately distinguishable from credential-signin siblings routed to channel_connect.

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?

Explicitly names the alternative (channel_connect) and the exact condition selecting it — sign-in-connected accounts like MESSENGER, INSTAGRAM, WHATSAPP. Also states prerequisites: manager rights, a free channel in the plan, and points to organization_usage to check it.

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