search_texts
AI agents call search_texts to retrieve information from DHLAB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs text search against a digital humanities corpus—a read-only query operation with no side effects, data modification, or destructive capability. The empty description lowers confidence slightly, but the naming convention and sibling tools clearly establish this as a retrieval/search function typical of library and corpus research platforms.
From the tool's definition Tool name 'search_texts' combined with server context showing text search capabilities and sibling tools like 'find_concordances', 'ngram_frequencies', 'lookup_word_forms', and 'get_corpus_statistics' all indicate data retrieval operations.
Attacks that exploit this kind of access
search_texts. It is categorised as a Read tool in the DHLAB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DHLAB MCP Server MCP server in PolicyLayer and add a rule for search_texts: 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 DHLAB MCP Server. Nothing to install.
search_texts 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_texts 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_texts. 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_texts is provided by the DHLAB MCP Server MCP server (marksverdhei/dhlab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →