add_facts_and_rules
AI agents use add_facts_and_rules to create or update resources in Pyke MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pyke MCP Server environment.
This tool creates or modifies the knowledge base by adding facts and rules, which are reversible operations (facts and rules can be deleted or cleared via 'delete_session' or 'clear_program'). It does not execute arbitrary code, delete irreversibly, move money, or query existing data.
From the tool's definition Tool name 'add_facts_and_rules' directly indicates creation of data (facts and rules) in the knowledge base. Sibling tools 'add_fact' and 'add_rule' confirm this server's pattern of write operations.
Attacks that exploit this kind of access
add_facts_and_rules. It is categorised as a Write tool in the Pyke MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pyke MCP Server MCP server in PolicyLayer and add a rule for add_facts_and_rules: 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 Pyke MCP Server. Nothing to install.
add_facts_and_rules 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 add_facts_and_rules 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 add_facts_and_rules. 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.
add_facts_and_rules is provided by the Pyke MCP Server MCP server (newjerseystyle/pyke-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →