Search tasks and documentation using full-text search with filtering capabilities. Returns matching results with relevance scores and text excerpts showing matched content. Use this tool for discovering tasks by keywords, finding related work, or locating specific information across the project.\...
AI agents call search to retrieve information from Scopecraft Command without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure read operation that queries and retrieves task data with filtering and ranking, returning only excerpts and metadata. It has no side effects, cannot modify data, execute code, or delete anything. It enables discovery and information retrieval only, making it a Read category tool with low severity risk.
From the tool's definition Tool description explicitly states 'Search tasks and documentation using full-text search' with 'Returns matching results with relevance scores and text excerpts' and 'returns only metadata + excerpt, not full content'.
Documented attack patterns abuse exactly the kind of access search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Scopecraft Command, and nothing reaches the server without passing your rules. This is the rule we recommend for search:
{
"version": "1",
"default": "deny",
"tools": {
"search": {}
}
}search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search tasks and documentation using full-text search with filtering capabilities. Returns matching results with relevance scores and text excerpts showing matched content. Use this tool for discovering tasks by keywords, finding related work, or locating specific information across the project.\n\nKey features:\n- Full-text search across task titles, content, and documentation\n- Filter by task metadata (status, area, tags, workflow state)\n- Returns excerpts with highlighted matched terms\n- Results sorted by relevance score\n- Token-efficient: returns only metadata + excerpt, not full content\n\nUsage tips:\n- For broad discovery: search with just a query term\n- For focused results: combine query with filters\n- To get full task content: use task_get with the returned ID\n- Empty query with filters: browse tasks by metadata only. It is categorised as a Read tool in the Scopecraft Command MCP Server, which means it retrieves data without modifying state.
Register the Scopecraft Command MCP server in PolicyLayer and add a rule for search: 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 Scopecraft Command. Nothing to install.
search 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 search 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 search. 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.
search is provided by the Scopecraft Command MCP server (scopecraft/command). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 18 Scopecraft Command tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
18 Scopecraft Command tools catalogued and risk-classified — across an index of 42,500+ MCP servers.