mark_stories_read · Claudegram MCP: Risk & Policy

WHAT IT DOES

What mark_stories_read does on Claudegram

AI agents use mark_stories_read to create or update resources in Claudegram — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claudegram environment.

WHY IT NEEDS A POLICY

Why mark_stories_read needs a policy

This tool modifies the read status of stories, which is reversible state change on the user's Telegram account. It does not delete, execute code, transfer money, or retrieve data—it updates metadata flags. The action is reversible (stories can be marked unread or re-read), placing it in Write category.

From the tool's definition Tool name 'mark_stories_read' and description 'Пометить истории прочитанными до указанного id' (Mark stories as read up to specified id) indicates modification of story read status metadata in Telegram account.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_stories_read Rate-limited

mark_stories_read stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mark_stories_read": {
      "limits": [
        {
          "counter": "mark_stories_read_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claudegram, so you can run agents against it safely.

FAQ

Questions about mark_stories_read

What does the mark_stories_read tool do? +

Пометить истории прочитанными до указанного id. It is categorised as a Write tool in the Claudegram MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mark_stories_read? +

Register the Claudegram MCP server in PolicyLayer and add a rule for mark_stories_read: 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 Claudegram. Nothing to install.

What risk level is mark_stories_read? +

mark_stories_read is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit mark_stories_read? +

Yes. Add a rate_limit block to the mark_stories_read 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.

How do I block mark_stories_read completely? +

Set action: deny in the PolicyLayer policy for mark_stories_read. 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.

What MCP server provides mark_stories_read? +

mark_stories_read is provided by the Claudegram MCP server (sanjar-x/claudegram). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.