Search the indexed codebase. Returns matching code chunks with file paths, line numbers, and relevance scores. Modes: keyword (FTS5), semantic (vector), hybrid (RRF fusion), auto (heuristic when SEARCH_AUTO_ROUTE), symbol (SQLite symbol index by identifier), regex (pattern matching with /pattern/...
Risk signalsAccepts freeform code/query input (query) · High parameter count (14 properties)
Part of the Vibe Hnindex server.
Free to start. No card required.
AI agents call search to retrieve information from Vibe Hnindex without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though search only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"search": {}
}
}See the full Vibe Hnindex policy for all 22 tools.
These attack patterns abuse exactly the kind of access search gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Search the indexed codebase. Returns matching code chunks with file paths, line numbers, and relevance scores. Modes: keyword (FTS5), semantic (vector), hybrid (RRF fusion), auto (heuristic when SEARCH_AUTO_ROUTE), symbol (SQLite symbol index by identifier), regex (pattern matching with /pattern/flags). Results are cached (LRU, 5min TTL) for non-regex modes. Filter by symbol_kind to only see files with functions, classes, etc. Enable fuzzy:true to boost results with approximate string matching (Levenshtein) — useful for misspelled queries. Post-retrieval ordering: if RERANK_URL is set, the server POSTs {query, documents} for optional cross-encoder-style scores; if not set, results are still reordered by Qdrant semantic similarity (no extra service). Ollama (OLLAMA_URL + OLLAMA_MODEL) is only for embeddings at index/query time—not the same as RERANK_URL. Agents: you do not need to "enable" rerank manually unless the user asks to skip it (use rerank:false) or tune env; default behavior is already optimal for most tasks. Prefer a narrow file_pattern and a small limit on the first pass.. It is categorised as a Read tool in the Vibe Hnindex MCP Server, which means it retrieves data without modifying state.
Register the Vibe Hnindex 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 Vibe Hnindex. 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 Vibe Hnindex MCP server (vibe-hnindex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 22 Vibe Hnindex tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.