10 tools from the Ai Dossier MCP Server, categorised by risk level.
View the Ai Dossier policy →get_journey_status Get the current state of a journey session: completed steps, current step, remaining steps, and collected outputs. list_dossiers Discover available dossiers in a directory. Scans for *.ds.md files and returns metadata. 2/5 read_dossier Read and parse a dossier file. Returns metadata and content. Should be called AFTER verify_dossier passes. 2/5 search_dossiers Search the dossier registry for available dossiers by keyword. Returns matching dossiers with metadata. 2/5 verify_dossier Security verification - Verify integrity (checksum) and authenticity (signature) of a dossier. Returns pass/fail with stage details. 2/5 verify_graph Batch security verification for a dossier dependency graph. Verifies all dossiers in a resolved graph and returns an aggregate security report with... resolve_graph Resolve a dossier dependency graph into an execution plan. Reads relationships (preceded_by, followed_by, conflicts_with) and produces a DAG with o... 2/5 step_complete Mark the current journey step as complete or failed. Advances to the next step and returns its dossier content with injected context from previous ... 2/5 The Ai Dossier MCP server exposes 10 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 Ai Dossier server.
Ai Dossier tools are categorised as Read (6), Write (2), Destructive (1), Execute (1). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept