list_external_channel_messages
Read persisted Telegram contact-channel messages or assess why an external provider cannot be read safely. For provider=telegram, resolve channel by exact stored value or stable contact-channel ID and return newest contentMarkdown, direction, stored Huly sendOn timestamp, and attachment count; re...
This record as markdown: /tools/io-github-dearlordylord-huly-mcp/list-external-channel-messages.md
What list_external_channel_messages does on Huly
AI agents call list_external_channel_messages to retrieve information from Huly without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why list_external_channel_messages is rated Low
Tool retrieves stored message data without modification, creation, or deletion capabilities.
From the tool's definition Read persisted Telegram contact-channel messages, return newest contentMarkdown, direction, timestamp
Attacks that exploit this kind of access
The rule that runs list_external_channel_messages safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Huly, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_external_channel_messages, this is the rule to start with:
list_external_channel_messages is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Huly, apply this rule, and every list_external_channel_messages call is checked against it from then on.
Questions about list_external_channel_messages
Read persisted Telegram contact-channel messages or assess why an external provider cannot be read safely. For provider=telegram, resolve channel by exact stored value or stable contact-channel ID and return newest contentMarkdown, direction, stored Huly sendOn timestamp, and attachment count; returns supported=false when the workspace model or channel is unavailable. Inbound attachment creation is asynchronous, so attachmentCount can temporarily lag the message; attachment bytes are not returned. This proves only Huly-stored records, not provider freshness, an active Telegram connection, or provider delivery/read status. Gmail returns supported=false because Huly does not expose the live deployment-wide v1/v2 writer version needed to distinguish current legacy records from stale data. The limit defaults to 50 and is capped at 200. This tool never sends, replies, deletes, or mutates. It is categorised as a Read tool in the Huly MCP Server, which means it retrieves data without modifying state.
Register the Huly MCP server in PolicyLayer and add a rule for list_external_channel_messages: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Huly. Nothing to install.
list_external_channel_messages is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_external_channel_messages rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_external_channel_messages. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_external_channel_messages is provided by the Huly MCP server (@firfi/huly-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Huly, and thousands of servers like it.
This server
Across the catalogue