PostRite

Read a conversation

get_conversation_messages

Read-only

Read one conversation: the conversation itself (contact, window, status) and its messages, newest first. direction INBOUND is the contact, OUTBOUND the account (sentById set when a person or assistant sent it, flowRunId when an automation did). Attachments a contact sent are not stored by PostRite (external: true): describe them, do not claim to have seen them. Needs the organization's "Let AI assistants answer comments and messages" setting (owner-only; without it the api answers MCP_INBOX_DISABLED) and a connection authorized with the comments/chat permissions — one authorized before they existed must reconnect, and a client that kept its own registration from before then must remove PostRite and add it again.

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": {
      "conversationId": "<conversationId>"
    },
    "name": "get_conversation_messages"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Messages per page, up to 100 (default 50)
`cursor`	No	nextCursor from the previous page of messages
`conversationId`	Yes	Conversation ID from list_conversations
`organizationId`	No	Organization to act in — an id from list_organizations. Required when this connection was authorized for more than one organization; omit it when there is only one.

Output Schema

Name	Required	Description	Default
`messages`	No
`nextCursor`	No
`conversation`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations only cover read-only and open-world; the description adds substantive behavior beyond that: newest-first ordering, the INBOUND/OUTBOUND direction model, why sentById vs flowRunId appear, the external:true attachment caveat telling the agent not to claim to have seen files, and the exact MCP_INBOX_DISABLED failure mode.

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?

The core read behavior is front-loaded in sentence one and the direction/attachment semantics follow logically. The final sentence on authorization, reconnect, and re-adding PostRite is dense and a bit long, but it is operationally necessary rather than 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?

An output schema exists, yet the definition still explains the domain semantics an agent would misread from raw fields (direction, sentById vs flowRunId, external attachments) and covers the failure modes and permission prerequisites, leaving nothing needed to call it correctly.

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 every parameter already carries its own description, which sets the baseline at 3. The description explains direction and attribution fields that are outputs rather than inputs, so it adds little input-level meaning 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 and resource ('Read one conversation') and enumerates what comes back (contact, window, status, messages newest first), which cleanly separates it from list_conversations and get_comment_thread in the sibling set.

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?

Implies when to use it via the conversationId description pointing at list_conversations, and spells out the precise preconditions (owner-only AI-assistant setting, comments/chat permissions, reconnect cases). It never explicitly says when to prefer a sibling like get_comment_thread instead, so it stops short of a 5.

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

All PostRite 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.

Resources

Need Help?