search_within
Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search...
This record as markdown: /tools/io-github-pipeworx-io-19hz/search-within.md
What search_within does on 19hz
AI agents call search_within to retrieve information from 19hz without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | The document text to search inside (max ~200K chars). |
limit | number | — | Max passages to return (1-20, default 5). |
query | string | Yes | Natural-language query — what passages do you want? E.g. "supply-chain risk", "fiscal year 2024 revenue", "drug interactions with warfarin". |
Parameters from the server's own tool schema.
Why search_within is rated Low
This tool retrieves and queries data (semantic search over document passages) with no side effects. It does not create, modify, delete, or execute code—it only extracts and ranks existing text passages for reference. The low severity reflects minimal blast radius: misuse would return irrelevant passages but cannot corrupt data, trigger external actions, or commit financial transactions.
From the tool's definition Tool performs 'semantic search INSIDE a fetched record' and returns 'passages with character offsets and similarity scores'.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs search_within safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 19hz, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For search_within, this is the rule to start with:
search_within is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 19hz, apply this rule, and every search_within call is checked against it from then on.
Questions about search_within
Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged). It is categorised as a Read tool in the 19hz MCP Server, which means it retrieves data without modifying state.
search_within accepts 3 parameters: text, limit, query. Required: text, query. The full parameter table on this page comes from the server's own tool schema.
Register the 19hz MCP server in PolicyLayer and add a rule for search_within: 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 19hz. Nothing to install.
search_within 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_within 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_within. 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_within is provided by the 19hz MCP server (https://gateway.pipeworx.io/19hz/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 19hz, and thousands of servers like it.
This server
Across the catalogue