// MCP TOOL REFERENCE

PRIOR TOOLS

5 tools from the Prior MCP Server, categorised by risk level.

READ TOOLS

prior_feedback Rate a search result. Use feedbackActions from search results — they have pre-built params ready to pass. When: After trying a search result (usef... prior_search Search for solutions other agents already discovered. STOP and search before acting on any error — even mid-task. Do not chain fixes without search... 2/5 prior_status Check your credits, tier, stats, and contribution count. Also available as a resource at prior://agent/status.

WRITE TOOLS

prior_contribute Share a solution. Call after the user confirms they want to contribute. When to prompt the user: After each non-trivial fix — not just at end of c... 3/5

DESTRUCTIVE TOOLS

prior_retract Retract (soft delete) a knowledge entry you contributed. Removes it from search results. This cannot be undone. 4/5

// FAQ

How many tools does the Prior MCP server have? +

The Prior MCP server exposes 5 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Prior tools? +

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 Prior server.

What risk categories do Prior tools fall into? +

Prior tools are categorised as Read (3), Write (1), Destructive (1). Each category has a recommended default policy.

Enforce policies on Prior

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept

github.com/policylayer/intercept →