fetch_evidence_records

A read tool on the ComplianceCow MCP server.

SERVERComplianceCow MCP Server SOURCEcompliancecow/cow-mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/compliancecow-cow-mcp/fetch-evidence-records.md

WHAT IT DOES

What fetch_evidence_records does on ComplianceCow MCP Server

AI agents call fetch_evidence_records to retrieve information from ComplianceCow MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why fetch_evidence_records is rated Low

The tool name and server context indicate this fetches or retrieves compliance evidence records without modifying, deleting, or executing operations. This is a read-only data retrieval operation. Confidence is slightly reduced (0.85 rather than 0.95) due to the empty description, but the name and server purpose strongly suggest read semantics.

From the tool's definition Tool name 'fetch_evidence_records' indicates data retrieval. Server description states it 'retrieve[s] compliance insights, dashboard data, and auditable evidence' with no mention of side effects for this operation.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs fetch_evidence_records safely

PolicyLayer is an MCP gateway: it sits between your AI agents and ComplianceCow MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fetch_evidence_records, this is the rule to start with:

fetch_evidence_records Allowed

fetch_evidence_records is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "fetch_evidence_records": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect ComplianceCow MCP Server, apply this rule, and every fetch_evidence_records call is checked against it from then on.

FAQ

Questions about fetch_evidence_records

What does the fetch_evidence_records tool do? +

fetch_evidence_records is a read tool on the ComplianceCow MCP Server MCP server. It is categorised as a Read tool in the ComplianceCow MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on fetch_evidence_records? +

Register the ComplianceCow MCP Server MCP server in PolicyLayer and add a rule for fetch_evidence_records: 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 ComplianceCow MCP Server. Nothing to install.

What risk level is fetch_evidence_records? +

fetch_evidence_records is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit fetch_evidence_records? +

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

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

fetch_evidence_records is provided by the ComplianceCow MCP Server MCP server (compliancecow/cow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on ComplianceCow MCP Server, and thousands of servers like it.

This server

All 209 ComplianceCow MCP Server tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →