Medium Risk

upload_evidence

Upload evidence files to support cybersecurity control implementation

How to control upload_evidence ↓

AI agents use upload_evidence to create or update resources in NIST CSF 2 0 Assessment Platform — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your NIST CSF 2 0 Assessment Platform environment.

Medium Risk

This tool creates or modifies data by adding evidence files to the platform, which is a reversible operation. Users can typically delete or replace uploaded evidence. While it involves data persistence, it does not execute arbitrary code, delete irreversibly, move financial assets, or trigger external system operations.

From the tool's definition Tool name is 'upload_evidence' and description states 'Upload evidence files to support cybersecurity control implementation'. The verb 'Upload' indicates creation/addition of data to the system.

Documented attack patterns abuse exactly the kind of access upload_evidence gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and NIST CSF 2 0 Assessment Platform, and nothing reaches the server without passing your rules. This is the rule we recommend for upload_evidence:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "upload_evidence": {
      "limits": [
        {
          "counter": "upload_evidence_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

upload_evidence 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.

  1. Create a free account and register NIST CSF 2 0 Assessment Platform — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the upload_evidence tool do? +

Upload evidence files to support cybersecurity control implementation. It is categorised as a Write tool in the NIST CSF 2 0 Assessment Platform MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on upload_evidence? +

Register the NIST CSF 2 0 Assessment Platform MCP server in PolicyLayer and add a rule for upload_evidence: 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 NIST CSF 2 0 Assessment Platform. Nothing to install.

What risk level is upload_evidence? +

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

Can I rate-limit upload_evidence? +

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

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

upload_evidence is provided by the NIST CSF 2 0 Assessment Platform MCP server (rocklambros/nist-csf-2-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every NIST CSF 2 0 Assessment Platform tool call.

Deterministic rules across all 49 NIST CSF 2 0 Assessment Platform tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

49 NIST CSF 2 0 Assessment Platform tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.