// SCAN REPORT

Sage MCP Server

29 tools. 6 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 30 Jun 2026

6 can modify or destroy data

23 read-only

29 tools total

Community server · catalogue entry verified 30/06/2026

How to control Sage MCP Server ↓

TOOL MAP

What Sage MCP Server exposes to your agents

Read (23) Write / Execute (5) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Sage MCP Server tools

Destructive · High force_remove_job This tool permanently deletes a job from the scheduler without the ability to undo or recover it. Execute · High submit_multi_plugin_job The tool name strongly implies submitting a job involving multiple plugins to the Sage Grande Testbed. Execute · High submit_plugin_job The tool name 'submit_plugin_job' strongly implies submitting a job for execution on the Sage Grande Testbed infrastructure. Execute · High submit_sage_job The tool name strongly implies submitting a job for execution on the Sage testbed infrastructure.

6 of Sage MCP Server's 29 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Sage MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Sage MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "force_remove_job": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_plugin": {
    "limits": [
      {
        "counter": "create_plugin_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ask_sage_docs": {
    "limits": [
      {
        "counter": "ask_sage_docs_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Sage MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON SAGE →

Instant setup, no code required.

FULL CATALOGUE

All 29 Sage MCP Server tools

DESTRUCTIVE 1 tools

Destructive force_remove_job Force remove a job from the scheduler

EXECUTE 3 tools

Execute submit_multi_plugin_job submit_multi_plugin_job Execute submit_plugin_job submit_plugin_job Execute submit_sage_job submit_sage_job

WRITE 2 tools

Write create_plugin Create a new Sage plugin from description Write suspend_job Suspend a job from the scheduler

READ 23 tools

Read ask_sage_docs Ask questions about Sage documentation and get comprehensive answers with examples and links Read check_job_status Check the status of a submitted Sage job Read find_plugins_for_task find_plugins_for_task Read get_cloud_images Get recent cloud images from Sage nodes. If no node_id is specified, searches across all nodes. Read get_environmental_summary Get environmental data summary (temperature, humidity, pressure) for a node or all nodes Read get_image_data Get recent image data from Sage nodes. Supports filtering by node and plugin pattern. Read get_image_proxy_url Get a proxy URL for a Sage image that can be accessed by clients. Read get_measurement_stat_by_location get_measurement_stat_by_location Read get_node_all_data get_node_all_data Read get_node_iio_data Get IIO (Industrial I/O) sensor data for a specific node Read get_node_info Get detailed information about a specific Sage node, including its sensors, location, and hardware Read get_node_temperature Get current temperature data for a specific node/sensor. Defaults to environment (bme680) temperature. Use sen Read get_nodes_by_location Find nodes in a specific geographic location or region (city, state, region, etc.) Read get_plugin_data Query and format data from a specific plugin Read get_sensor_details Get detailed information about a specific type of sensor used in Sage nodes Read get_temperature_summary Get a summary of current temperature readings across all sensors. Defaults to environment (bme680) temperature Read list_all_nodes List all Sage nodes and their basic information Read list_available_nodes List all available sensor nodes and their last activity Read query_job_data Query data generated by a running Sage job Read query_plugin_data_nl Query plugin data using natural language. Examples: Read sage_faq Get answers to frequently asked questions about SAGE. Available topics: getting_started, plugin_development, d Read search_measurements Search for specific measurement types using a pattern (regex supported) Read search_sage_docs Search Sage documentation for specific topics, commands, or concepts

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Sage MCP Server

Can an AI agent delete data through the Sage MCP Server MCP server? +

Yes. The Sage MCP Server server exposes 1 destructive tools including force_remove_job. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Sage MCP Server? +

The Sage MCP Server server has 2 write tools including create_plugin, suspend_job. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Sage MCP Server.

How many tools does the Sage MCP Server MCP server expose? +

29 tools across 3 categories: Destructive, Read, Write. 23 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Sage MCP Server? +

Register the Sage MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Sage MCP Server tool call.

Deterministic rules across all 29 Sage MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SAGE →

Instant setup, no code required.

29 Sage MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.