inline_query · Claudegram MCP: Risk & Policy

WHAT IT DOES

What inline_query does on Claudegram

AI agents invoke inline_query to trigger actions in Claudegram. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why inline_query needs a policy

An inline query sends a request to an external bot, triggering its processing logic. The effects are determined by the bot and the arguments passed, making this an Execute-category action. Misuse could trigger unintended bot actions or leak query data to third-party bots.

From the tool's definition Сделать inline-запрос к боту (как `@bot query` в любом чате) — triggers an external operation (inline query) to a bot, whose effects depend on the query arguments and the bot's behavior

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

inline_query Rate-limited

inline_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "inline_query": {
      "limits": [
        {
          "counter": "inline_query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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 inline_query

What does the inline_query tool do? +

Сделать inline-запрос к боту (как @bot query в любом чате). It is categorised as a Execute tool in the Claudegram MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on inline_query? +

Register the Claudegram MCP server in PolicyLayer and add a rule for inline_query: 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 inline_query? +

inline_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit inline_query? +

Yes. Add a rate_limit block to the inline_query 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 inline_query completely? +

Set action: deny in the PolicyLayer policy for inline_query. 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 inline_query? +

inline_query 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.