Get statistics about the philosophy corpus (total entries, by section, by language).
AI agents call corpus_stats to retrieve information from Philosophy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves aggregate metadata about the corpus without modifying, executing, or deleting any data. Misuse poses minimal risk: an agent could spam requests but cannot corrupt data, execute commands, or commit financial obligations.
From the tool's definition Tool returns corpus statistics (counts of entries by section and language) — a read-only query with no side effects, matching the 'get' and 'list' pattern of other tools on this server.
Attacks that exploit this kind of access
Get statistics about the philosophy corpus (total entries, by section, by language). It is categorised as a Read tool in the Philosophy MCP Server, which means it retrieves data without modifying state.
Register the Philosophy MCP server in PolicyLayer and add a rule for corpus_stats: 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 Philosophy. Nothing to install.
corpus_stats is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the corpus_stats 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 corpus_stats. 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.
corpus_stats is provided by the Philosophy MCP server (s3b4hjr/philosophy-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 →