Skip to main content
Glama
cameronrye

AT Protocol MCP Server

get_conversation_messages

Idempotent

Retrieve messages from a Bluesky direct message conversation, newest first with cursor pagination. Optionally clear the unread count.

Instructions

Read the messages of a Bluesky direct-message conversation (chat.bsky.convo.getMessages, proxied to the bsky.chat service), newest first with cursor pagination. Read-only by default: the conversation is only marked read (unread count cleared) when markRead is true. Requires authentication with an app password created with "Allow access to your direct messages" enabled. Use list_conversations to find conversation ids and send_direct_message to reply. Subject to per-tool rate limiting.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
convoIdYesId of the conversation to read, from list_conversations or a send_direct_message response.
limitNoMax messages per page (1-100, default 50). Messages are returned newest first.
cursorNoOpaque pagination cursor from the previous response cursor field; omit for the newest page.
markReadNoWhen true, also mark the conversation read (chat.bsky.convo.updateRead) after fetching, clearing its unread count. Default false: reading is side-effect free.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
successYesWhether the request succeeded.
convoIdYesId of the conversation that was read.
messagesYesThe messages for this page, newest first. Deleted messages keep their id/sender/timestamp but have no text.
cursorNoOpaque cursor for the next (older) page; absent when there are no more messages.
hasMoreYesWhether another (older) page is available (a cursor was returned).
markedReadYesWhether the conversation was marked read by this call (markRead=true).
Behavior5/5

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

Annotations indicate read-only, idempotent, open-world. Description adds side-effect of markRead, authentication requirements (app password with DM access), rate limiting, and that it is proxied. No contradiction.

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 description is a single paragraph that front-loads the main purpose. It is clear but contains some dense technical details. Could be slightly more structured, but still effective.

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?

Covers all key aspects: read-only default, pagination, auth, rate limiting, relationship to siblings. Output schema exists, so return value details are not needed. Complete for a tool of this complexity.

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 has 100% coverage with descriptions. Description adds default values (limit=50, markRead=false), clarifies cursor usage (omit for newest page), and specifies where convoId comes from. Adds extra value beyond 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?

The description clearly states the tool reads messages from a Bluesky DM conversation, specifies ordering (newest first) and pagination method. It distinguishes itself from sibling tools like list_conversations and send_direct_message.

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 guidance on when to use (reading messages), and alternatives: list_conversations for finding conversation IDs, send_direct_message for replying. Also explains the markRead parameter's effect.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cameronrye/atproto-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server