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...
AI agents call search_within to retrieve information from Mcp Speedrun without modifying anything — 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.
search_within is a retrieval and filtering tool that operates on already-fetched text. It uses embeddings-based semantic search to extract relevant passages from large documents, returning text segments with metadata (offsets, similarity scores). There are no side effects: no data is created, modified, deleted, or executed.
From the tool's definition The tool description explicitly states it performs 'Semantic search INSIDE a fetched record' and 'returns only the passages that matter.' It retrieves and filters existing data without creating, modifying, deleting, or executing external operations.
Risk signalsAccepts freeform code/query input (query) · Bulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
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 Mcp Speedrun 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 Mcp Speedrun 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 Mcp Speedrun. 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 Mcp Speedrun MCP server (pipeworx-io/mcp-speedrun). 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 →