AI agents use create_custom_metric to create or update resources in Symbolic Algebra MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Symbolic Algebra MCP Server environment.
Based on the naming pattern 'create_*' consistent with sibling tools like 'create_matrix', 'create_vector_field', 'create_predefined_metric', this tool likely creates a custom metric tensor or mathematical object in memory. This is a Write operation (creating data). No evidence of destructive, financial, or execution behavior. Confidence is low due to empty description.
From the tool's definition Tool name 'create_custom_metric' and server context (symbolic algebra, SymPy, mathematical expressions). Description is empty.
Documented attack patterns abuse exactly the kind of access create_custom_metric gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Symbolic Algebra MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_custom_metric:
{
"version": "1",
"default": "deny",
"tools": {
"create_custom_metric": {
"limits": [
{
"counter": "create_custom_metric_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_custom_metric 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.
Free to start. No card required.
create_custom_metric. It is categorised as a Write tool in the Symbolic Algebra MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Symbolic Algebra MCP Server MCP server in PolicyLayer and add a rule for create_custom_metric: 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 Symbolic Algebra MCP Server. Nothing to install.
create_custom_metric is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_custom_metric 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.
Set action: deny in the PolicyLayer policy for create_custom_metric. 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.
create_custom_metric is provided by the Symbolic Algebra MCP Server MCP server (sdiehl/sympy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 32 Symbolic Algebra MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
32 Symbolic Algebra MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.