summarize_extractive
Extractive summary with TextRank (Mihalcea & Tarau 2004): sentences are split (abbreviation / initial / decimal aware), linked by stemmed content-word overlap, ranked with PageRank, and the top N are returned in original order. No LLM, no hallucination: every summary sentence is verbatim from the...
This record as markdown: /tools/com-it-scorptech-x402/summarize-extractive.md
What summarize_extractive does on ScorpTech x402 API
AI agents call summarize_extractive to retrieve information from ScorpTech x402 API 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 | Text to summarise (English works best) |
ratio | number | — | Keep this fraction of sentences instead (overrides sentences) |
sentences | integer | — | Sentences to keep |
Parameters from the server's own tool schema.
Why summarize_extractive is rated Low
Even though summarize_extractive only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs summarize_extractive safely
PolicyLayer is an MCP gateway: it sits between your AI agents and ScorpTech x402 API, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For summarize_extractive, this is the rule to start with:
summarize_extractive 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 ScorpTech x402 API, apply this rule, and every summarize_extractive call is checked against it from then on.
Questions about summarize_extractive
Extractive summary with TextRank (Mihalcea & Tarau 2004): sentences are split (abbreviation / initial / decimal aware), linked by stemmed content-word overlap, ranked with PageRank, and the top N are returned in original order. No LLM, no hallucination: every summary sentence is verbatim from the input, with its index, score and offset. Choose a sentence count or a ratio. Offline, deterministic; 200 KB input. Price: $0.003 USDC per successful call (x402, Solana). Same tool over HTTPS: POST https://scorptech.it.com/api/x402/v1/summarize-extractive. It is categorised as a Read tool in the ScorpTech x402 API MCP Server, which means it retrieves data without modifying state.
summarize_extractive accepts 3 parameters: text, ratio, sentences. Required: text. The full parameter table on this page comes from the server's own tool schema.
Register the ScorpTech x402 API MCP server in PolicyLayer and add a rule for summarize_extractive: 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 ScorpTech x402 API. Nothing to install.
summarize_extractive 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 summarize_extractive 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 summarize_extractive. 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.
summarize_extractive is provided by the ScorpTech x402 API MCP server (https://scorptech.it.com/api/x402/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on ScorpTech x402 API, and thousands of servers like it.
This server
Across the catalogue