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). Post-retrieval ordering: if RERANK_URL...
Accepts freeform code/query input (query); High parameter count (13 properties); Single-target operation
Part of the Vibe Hnindex MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
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.
tools:
search:
rules:
- action: allowSee the full Vibe Hnindex policy for all 21 tools.
Agents calling read-class tools like search have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
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). 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.
Add a rule in your Intercept YAML policy under the tools section for search. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Vibe Hnindex MCP server.
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 Intercept 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 Intercept 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). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept