// MCP TOOL REFERENCE

CANTRIP TOOLS

19 tools from the Cantrip MCP Server, categorised by risk level.

View the Cantrip policy → Token cost: 3,213 tokens →

// ALL 19 CANTRIP TOOLS

READ 9 tools

Read cantrip_history Query the append-only audit trail of all actions taken on the project. Pass `project` to override `.cantrip... Read cantrip_meter_balance Check remaining credits. Returns available credits, reserved credits (held by in-progress operations), and ... Read cantrip_meter_history View recent credit transactions. Shows usage debits, purchases, and running balance. Pass `project` to over... Read cantrip_meter_tiers View available credit packs. Shows tier name, credits included, and price. Read cantrip_next List gap-analysis opportunities — things that would move the project closer to ideal state. Each opportunit... Read cantrip_next_prompt Generate a context-rich LLM prompt for an opportunity. Returns a ready-to-use prompt with all relevant onto... Read cantrip_review List all items pending review (inferred entities and open escalations). Pass `project` to override `.cantri... Read cantrip_snapshot Browse project data at three zoom levels. No args: project overview with entity counts by type and review s... Read cantrip_status Check daemon health, authentication, and current project. Returns daemon reachability, authenticated identi...

WRITE 7 tools

Write cantrip_review_accept Accept an inferred entity, marking it as verified ground truth. Pass `project` to override `.cantrip.json` ... Write cantrip_connect Start here. Connect this workspace to a Cantrip project by writing a .cantrip.json file. All subsequent com... Write cantrip_entity_add Create a new entity. Automatically marked as 'accepted'. Fields vary by type: - icp: name, description, dem... Write cantrip_entity_edit Edit an existing entity. Fields vary by type (same as cantrip_entity_add). Pass well-known fields directly,... Write cantrip_init Create a new project and connect this workspace to it. Pass 'brief_text' (product brief as text) to auto-ex... Write cantrip_review_reject Reject an inferred entity (soft-delete, kept for history). Pass `project` to override `.cantrip.json` — use... Write cantrip_review_resolve Resolve an open escalation with a resolution message. Pass `project` to override `.cantrip.json` — useful i...

DESTRUCTIVE 2 tools

Destructive cantrip_project Manage projects. Actions: - list (default): List all projects in the current team. - update: Update a proje... Destructive cantrip_review_dismiss Dismiss an inferred entity or open escalation. For entities: removes from review queue without accepting or...

EXECUTE 1 tools

Execute cantrip_next_run Execute an enrichment opportunity with AI. Runs the LLM-powered enrichment inline — either updating existin...

// RUNNING THIS SERVER

The managed route: connect Cantrip through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y mcp-server-cantrip

// FAQ

How many tools does the Cantrip MCP server have? +

The Cantrip MCP server exposes 19 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Cantrip tools? +

Route the Cantrip server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Cantrip tools fall into? +

Cantrip tools are categorised as Read (9), Write (7), Destructive (2), Execute (1). Each category has a recommended default policy.

Enforce policy on every Cantrip tool call.

Start from Cantrip, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.