Rebuild the search index to ensure all content is searchable with current data. Use this tool when search results seem outdated, after bulk imports, or if you suspect the index is corrupted.\n\nWhen to use:\n- After importing multiple tasks from another system\n- If search results are missing rec...
AI agents invoke search_reindex to trigger actions in Scopecraft Command. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an active rebuild operation — scanning files and reconstructing an index — rather than merely reading or writing user data. It executes a background process with side effects (index reconstruction). While it is described as idempotent and safe, misuse could cause performance degradation or temporarily disrupt search availability.
From the tool's definition Rebuild the search index from scratch... Scans all tasks and documentation... Returns success status and indexing time
Documented attack patterns abuse exactly the kind of access search_reindex 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_reindex:
{
"version": "1",
"default": "deny",
"tools": {
"search_reindex": {
"limits": [
{
"counter": "search_reindex_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}search_reindex stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Rebuild the search index to ensure all content is searchable with current data. Use this tool when search results seem outdated, after bulk imports, or if you suspect the index is corrupted.\n\nWhen to use:\n- After importing multiple tasks from another system\n- If search results are missing recently created content\n- After significant structural changes to the project\n- If search performance degrades\n\nWhat it does:\n- Scans all tasks and documentation\n- Rebuilds the search index from scratch\n- Returns success status and indexing time\n- Safe to run anytime (idempotent operation). It is categorised as a Execute tool in the Scopecraft Command MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Scopecraft Command MCP server in PolicyLayer and add a rule for search_reindex: 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_reindex is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the search_reindex 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_reindex. 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_reindex 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.