19 tools from the Cantrip MCP Server, categorised by risk level.
View the Cantrip policy →cantrip_history Query the append-only audit trail of all actions taken on the project. cantrip_meter_balance Check remaining credits, reserved credits (in-progress), and total balance. cantrip_meter_history View recent credit transactions (debits, purchases, and running balance). cantrip_meter_tiers View available credit packs with tier name, credits included, and price. cantrip_next List gap-analysis opportunities that would move the project closer to ideal state. cantrip_next_prompt Generate a context-rich LLM prompt for an opportunity. Zero credit cost. cantrip_review List all items pending review (inferred entities and open escalations). 2/5 cantrip_review_accept Accept an inferred entity, marking it as verified ground truth. cantrip_review_dismiss Dismiss an inferred entity or open escalation without accepting or rejecting. cantrip_snapshot Browse project data at three zoom levels: project overview, entity type listing, or single entity detail. cantrip_status Check daemon health, authentication, and current project. Returns setup instructions when CANTRIP_API_KEY is missing. cantrip_connect Connect this workspace to a Cantrip project by writing a .cantrip.json file. Call without arguments to check the current connection. 2/5 cantrip_entity_add Create a new entity (icp, pain_point, value_prop, experiment, channel, competitor, contact). Automatically marked as accepted. 2/5 cantrip_entity_edit Edit an existing entity. Fields vary by type (same as cantrip_entity_add). 2/5 cantrip_init Create a new project and connect this workspace to it. Optionally ingests a product brief to extract ICPs, pain points, and value props. 2/5 cantrip_review_reject Reject an inferred entity (soft-delete, kept for history). 2/5 cantrip_review_resolve Resolve an open escalation with a resolution message. 2/5 The Cantrip MCP server exposes 19 tools across 4 categories: Read, Write, Destructive, Execute.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Cantrip server.
Cantrip tools are categorised as Read (11), Write (6), Destructive (1), Execute (1). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept