# telegram_agent_route Classify the conversation direction for an enrolled chat and return the Agent View of the PolicyLayer registry record for `telegram_agent_route`. HTML page: https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/telegram-agent-route ## Facts - Tool: `telegram_agent_route` - Server: Odoo Claude MCP (`rosenvladimirov/odoo-claude-mcp`) — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp.md - Homepage: https://github.com/rosenvladimirov/odoo-claude-mcp - Risk category: Read (Low risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Allowed ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "telegram_agent_route", "arguments": {} } } ``` ## Why telegram_agent_route is rated Low The tool appears to analyze and classify existing chat conversation direction. The verb 'classify' and 'return' indicate a query operation that reads chat metadata or content to determine routing, with no indication of data modification, deletion, or external state changes. The incomplete description limits confidence slightly, but the name and partial description strongly suggest a read-only classification function. From the tool's own definition: "Tool name 'telegram_agent_route' and description 'Classify the conversation direction for an enrolled chat and return the' suggest a routing/classification operation that reads chat state and returns a direction classification without modifying data." ## Use case AI agents call telegram_agent_route to retrieve information from Odoo Claude MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere. ## Recommended policy (PolicyLayer) Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Odoo Claude MCP: ```json { "version": "1", "default": "deny", "tools": { "telegram_agent_route": {} } } ``` ## Other tools on Odoo Claude MCP (245) - `cf_dns_delete` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/cf-dns-delete.md - `cf_tunnel_route_remove` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/cf-tunnel-route-remove.md - `ee_unlink` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/ee-unlink.md - `google_calendar_delete_event` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/google-calendar-delete-event.md - `memory_delete` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/memory-delete.md - `module_deploy_rollback` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/module-deploy-rollback.md - `odoo_disconnect` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/odoo-disconnect.md - `odoo_fp_remove_action` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/odoo-fp-remove-action.md - `odoo_stock_initial_delete` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/odoo-stock-initial-delete.md - `odoo_stock_mo_delete_draft` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/odoo-stock-mo-delete-draft.md - `odoo_unlink` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/odoo-unlink.md - `odoo_web_logout` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/odoo-web-logout.md - `odoo_website_remove_snippet` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/odoo-website-remove-snippet.md - `provision_revoke_api_key` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/provision-revoke-api-key.md - `s3_bucket_delete` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/s3-bucket-delete.md - `s3_object_delete` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/s3-object-delete.md - `s3_objects_delete_prefix` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/s3-objects-delete-prefix.md - `secrets_revoke` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/secrets-revoke.md - `session_handoff_cancel` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/session-handoff-cancel.md - `session_link_revoke` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/session-link-revoke.md - `session_revoke` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/session-revoke.md - `telegram_agent_unenroll` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/telegram-agent-unenroll.md - `telegram_sub_remove` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/telegram-sub-remove.md - `tenant_restore` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/tenant-restore.md - `user_connection_delete` — Destructive — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/user-connection-delete.md - `ai_invoice_pipeline_run` — Execute — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/ai-invoice-pipeline-run.md - `ai_invoice_plugins_reload` — Execute — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/ai-invoice-plugins-reload.md - `ai_pipeline_run` — Execute — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/ai-pipeline-run.md - `ai_pipeline_step_execute` — Execute — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/ai-pipeline-step-execute.md - `ai_tokenize_collection` — Execute — https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp/ai-tokenize-collection.md - …and 215 more: https://policylayer.com/tools/rosenvladimirov-odoo-claude-mcp.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=rosenvladimirov-odoo-claude-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/rosenvladimirov-odoo-claude-mcp