repair_index
Apply a targeted repair to the local SQLite index. Modes: drop-orphans (delete embedding rows whose symbol_id no longer exists), drop-vec (drop the entire vector store — search falls back to BM25; embed_repo rebuilds), rebuild-fts (drop and reload symbols_fts from the symbols table). Each mode ru...
This record as markdown: /tools/nikolai-vysotskyi-trace-mcp/repair-index.md
What repair_index does on Trace
AI agents call repair_index to permanently remove resources in Trace, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why repair_index is rated Critical
The tool performs irreversible data deletion operations (DROP, DELETE) on a local SQLite index. While wrapped in transactions to prevent partial failures, the core operations—dropping embedding rows, dropping vector stores, and dropping/reloading full-text search tables—are all destructive and cannot be undone without a backup. The tool's own documentation explicitly labels it DESTRUCTIVE.
From the tool's definition 'DESTRUCTIVE — verify_index first', 'drop-orphans (delete embedding rows...)', 'drop the entire vector store', 'drop and reload symbols_fts from the symbols table'
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs repair_index safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Trace, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For repair_index, this is the rule to start with:
repair_index is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Trace, apply this rule, and every repair_index call is checked against it from then on.
Questions about repair_index
Apply a targeted repair to the local SQLite index. Modes: drop-orphans (delete embedding rows whose symbol_id no longer exists), drop-vec (drop the entire vector store — search falls back to BM25; embed_repo rebuilds), rebuild-fts (drop and reload symbols_fts from the symbols table). Each mode runs in a transaction so a partial failure leaves the DB unchanged. DESTRUCTIVE — verify_index first to find out which mode is needed. Returns JSON: { mode, ok, detail, affected }. It is categorised as a Destructive tool in the Trace MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Trace MCP server in PolicyLayer and add a rule for repair_index: 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 Trace. Nothing to install.
repair_index is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the repair_index 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 repair_index. 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.
repair_index is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Trace, and thousands of servers like it.
Across the catalogue